ORCID Profile
0000-0002-0512-880X
Current Organisation
Zhejiang University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Research Topics
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Top 5 Research Topics
ANZSRC Field of Research (FoR)
Pattern Recognition and Data Mining | Artificial Intelligence and Image Processing | Database Management | Computer Vision | Artificial Intelligence and Image Processing not elsewhere classified | Information Systems | Neural, Evolutionary and Fuzzy Computation | Multimedia Programming
ANZSRC Socio-Economic Objective (SEO)
Information Processing Services (incl. Data Entry and Capture) | Electronic Information Storage and Retrieval Services | Film and Video Services (excl. Animation and Computer Generated Imagery) | Media Services not elsewhere classified | Application Tools and System Utilities | Expanding Knowledge in the Information and Computing Sciences | Health Policy Evaluation |
Related Links
Publications
Recognizing Cartoon Image Gestures for Retrieval and Interactive Cartoon Clip Synthesis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2010
Web Image Annotation Via Subspace-Sparsity Collaborated Feature Selection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2012
Learning Latent Stable Patterns for Image Understanding With Weak and Noisy Labels
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Semantic Pooling for Complex Event Analysis in Untrimmed Videos
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2017
Recurrent Attention Network with Reinforced Generator for Visual Dialog
Publisher: Association for Computing Machinery (ACM)
Date: 05-07-2020
DOI: 10.1145/3390891
Abstract: In Visual Dialog, an agent has to parse temporal context in the dialog history and spatial context in the image to hold a meaningful dialog with humans. For ex le, to answer “what is the man on her left wearing?” the agent needs to (1) analyze the temporal context in the dialog history to infer who is being referred to as “her,” (2) parse the image to attend “her,” and (3) uncover the spatial context to shift the attention to “her left” and check the apparel of the man. In this article, we use a dialog network to memorize the temporal context and an attention processor to parse the spatial context. Since the question and the image are usually very complex, which makes it difficult for the question to be grounded with a single glimpse, the attention processor attends to the image multiple times to better collect visual information. In the Visual Dialog task, the generative decoder (G) is trained under the word-by-word paradigm, which suffers from the lack of sentence-level training. We propose to reinforce G at the sentence level using the discriminative model (D), which aims to select the right answer from a few candidates, to ameliorate the problem. Experimental results on the VisDial dataset demonstrate the effectiveness of our approach.
Discriminative Cellets Discovery for Fine-Grained Image Categories Retrieval
Publisher: ACM
Date: 04-2014
Adaptive Boosting for Domain Adaptation: Toward Robust Predictions in Scene Segmentation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Indexing of the CNN features for the large scale image search
Publisher: Springer Science and Business Media LLC
Date: 15-06-2018
Manifold Learning Based Cross-media Retrieval: A Solution to Media Object Complementary Nature
Publisher: Springer Science and Business Media LLC
Date: 03-02-2007
Heterogeneous multimedia data semantics mining using content and location context
Publisher: ACM
Date: 26-10-2008
DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
DMRNet++: Learning Discriminative Features With Decoupled Networks and Enriched Pairs for One-Step Person Search
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2023
Sparse Multi-Modal Hashing
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2014
Context Matters: Distilling Knowledge Graph for Enhanced Object Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Semantics-Aware Spatial-Temporal Binaries for Cross-Modal Video Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
IcoCap: Improving Video Captioning by Compounding Images
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Learning to predict health status of geriatric patients from observational data
Publisher: IEEE
Date: 05-2012
Mining Semantic Correlation of Heterogeneous Multimedia Data for Cross-Media Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2008
DevNet: A Deep Event Network for multimedia event detection and evidence recounting
Publisher: IEEE
Date: 06-2015
Weakly Supervised Human Fixations Prediction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2016
Few-Shot Object Recognition from Machine-Labeled Web Images
Publisher: IEEE
Date: 07-2017
Bayesian query expansion for multi-camera person re-identification
Publisher: Elsevier BV
Date: 02-2020
Dynamic Affinity Graph Construction for Spectral Clustering Using Multiple Features.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2018
Complex Event Detection via Multi-source Video Attributes
Publisher: IEEE
Date: 06-2013
Hierarchical Temporal Modeling With Mutual Distance Matching for Video Based Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2021
U-Turn: Crafting Adversarial Queries with Opposite-Direction Features
Publisher: Springer Science and Business Media LLC
Date: 20-12-2022
Pose-Invariant Embedding for Deep Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2019
More is Less: A More Complicated Network with Less Inference Complexity
Publisher: IEEE
Date: 07-2017
Learning frame relevance for video classification
Publisher: ACM
Date: 28-11-2011
Filter Pruning by Switching to Neighboring CNNs With Good Attributes
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2023
Local image tagging via graph regularized joint group sparsity
Publisher: Elsevier BV
Date: 05-2013
Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising
Publisher: IEEE
Date: 06-2014
Understanding Atomic Hand-Object Interaction With Human Intention
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
3D human pose recovery from image by efficient visual feature selection
Publisher: Elsevier BV
Date: 03-2011
Rank-Constrained Spectral Clustering With Flexible Embedding
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2018
Adaptive Unsupervised Feature Selection With Structure Regularization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2018
Late Fusion via Subspace Search With Consistency Preservation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Deep Top-$k$ Ranking for Image–Sentence Matching
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2020
Semi-Supervised Multiple Feature Analysis for Action Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2014
Infrared Patch-Image Model for Small Target Detection in a Single Image
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2013
Soft Person Reidentification Network Pruning via Blockwise Adjacent Filter Decaying
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Semisupervised feature analysis by mining correlations among multiple tasks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2016
Fusing Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2018
Ranking with local regression and global alignment for cross media retrieval
Publisher: ACM
Date: 19-10-2009
Person Re-identification in the Wild
Publisher: IEEE
Date: 07-2017
Classification by semi-supervised discriminative regularization
Publisher: Elsevier BV
Date: 06-2010
Personal health indexing based on medical examinations: A data mining approach
Publisher: Elsevier BV
Date: 2016
Transfer tagging from image to video
Publisher: ACM
Date: 28-11-2011
Effective multiple feature hashing for large-scale near-duplicate video retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2013
Image Classification by Cross-Media Active Learning With Privileged Information
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2016
Harry Potter's Marauder's Map: Localizing and Tracking Multiple Persons-of-Interest by Nonnegative Discretization
Publisher: IEEE
Date: 06-2013
Knowledge Adaptation with PartiallyShared Features for Event DetectionUsing Few Exemplars
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2014
Few-shot text and image classification via analogical transfer learning
Publisher: Association for Computing Machinery (ACM)
Date: 29-10-2018
DOI: 10.1145/3230709
Abstract: Learning from very few s les is a challenge for machine learning tasks, such as text and image classification. Performance of such task can be enhanced via transfer of helpful knowledge from related domains, which is referred to as transfer learning. In previous transfer learning works, instance transfer learning algorithms mostly focus on selecting the source domain instances similar to the target domain instances for transfer. However, the selected instances usually do not directly contribute to the learning performance in the target domain. Hypothesis transfer learning algorithms focus on the model arameter level transfer. They treat the source hypotheses as well-trained and transfer their knowledge in terms of parameters to learn the target hypothesis. Such algorithms directly optimize the target hypothesis by the observable performance improvements. However, they fail to consider the problem that instances that contribute to the source hypotheses may be harmful for the target hypothesis, as instance transfer learning analyzed. To relieve the aforementioned problems, we propose a novel transfer learning algorithm, which follows an analogical strategy. Particularly, the proposed algorithm first learns a revised source hypothesis with only instances contributing to the target hypothesis. Then, the proposed algorithm transfers both the revised source hypothesis and the target hypothesis (only trained with a few s les) to learn an analogical hypothesis. We denote our algorithm as Analogical Transfer Learning. Extensive experiments on one synthetic dataset and three real-world benchmark datasets demonstrate the superior performance of the proposed algorithm.
Delay-Aware Quality Optimization in Cloud-Assisted Video Streaming System
Publisher: Association for Computing Machinery (ACM)
Date: 13-12-2017
DOI: 10.1145/3152116
Abstract: Cloud-assisted video streaming has emerged as a new paradigm to optimize multimedia content distribution over the Internet. This article investigates the problem of streaming cloud-assisted real-time video to multiple destinations (e.g., cloud video conferencing, multi-player cloud gaming, etc.) over lossy communication networks. The user ersity and network dynamics result in the delay differences among multiple destinations. This research proposes underline D /underline ifferentiated cloud- underline A /underline ssisted underline VI /underline deo underline S /underline treaming (DAVIS) framework, which proactively leverages such delay differences in video coding and transmission optimization. First, we analytically formulate the optimization problem of joint coding and transmission to maximize received video quality. Second, we develop a quality optimization framework that integrates the video representation selection and FEC (Forward Error Correction) packet interleaving. The proposed DAVIS is able to effectively perform differentiated quality optimization for multiple destinations by taking advantage of the delay differences in cloud-assisted video streaming system. We conduct the performance evaluation through extensive experiments with the Amazon EC2 instances and Exata emulation platform. Evaluation results show that DAVIS outperforms the reference cloud-assisted streaming solutions in video quality and delay performance.
Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Multiple feature hashing for real-time large scale near-duplicate video retrieval
Publisher: ACM
Date: 28-11-2011
Image Attribute Adaptation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2014
RCAA: Relational context-aware agents for person search
Publisher: Springer International Publishing
Date: 2018
Avoiding optimal mean ℓ2,1 -norm maximization-based robust PCA for reconstruction
Publisher: MIT Press - Journals
Date: 04-2017
DOI: 10.1162/NECO_A_00937
Abstract: Robust principal component analysis (PCA) is one of the most important dimension-reduction techniques for handling high-dimensional data with outliers. However, most of the existing robust PCA presupposes that the mean of the data is zero and incorrectly utilizes the average of data as the optimal mean of robust PCA. In fact, this assumption holds only for the squared [Formula: see text]-norm-based traditional PCA. In this letter, we equivalently reformulate the objective of conventional PCA and learn the optimal projection directions by maximizing the sum of projected difference between each pair of instances based on [Formula: see text]-norm. The proposed method is robust to outliers and also invariant to rotation. More important, the reformulated objective not only automatically avoids the calculation of optimal mean and makes the assumption of centered data unnecessary, but also theoretically connects to the minimization of reconstruction error. To solve the proposed nonsmooth problem, we exploit an efficient optimization algorithm to soften the contributions from outliers by reweighting each data point iteratively. We theoretically analyze the convergence and computational complexity of the proposed algorithm. Extensive experimental results on several benchmark data sets illustrate the effectiveness and superiority of the proposed method.
Holistic LSTM for Pedestrian Trajectory Prediction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Towards efficient search for activity trajectories
Publisher: IEEE
Date: 04-2013
Learning Part-based Convolutional Features for Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2021
Image Clustering Using Local Discriminant Models and Global Integration
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2010
Dark Knowledge Balance Learning for Unbiased Scene Graph Generation
Publisher: ACM
Date: 26-10-2023
Monitoring and Coaching the Use of Home Medical Devices
Publisher: Springer International Publishing
Date: 2015
Bi-level semantic representation analysis for multimedia event detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2017
Retrieval based interactive cartoon synthesis via unsupervised bi-distance metric learning
Publisher: ACM
Date: 19-10-2009
Pedestrian Alignment Network for Large-scale Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2019
Each Part Matters: Local Patterns Facilitate Cross-View Geo-Localization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2022
Multi-feature fusion via hierarchical regression for multimedia analysis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2013
Joint Representation Learning and Keypoint Detection for Cross-View Geo-Localization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
A Differentiable Parallel Sampler for Efficient Video Classification
Publisher: Association for Computing Machinery (ACM)
Date: 25-02-2023
DOI: 10.1145/3569584
Abstract: It is crucial to s le a small portion of relevant frames for efficient video classification. The existing methods mainly develop hand-designed s ling strategies or learn sequential selection policies. However, there are two challenges to be solved. First, hand-designed s ling strategies are intrinsically non-adaptive to different video backbones. Second, sequential frame selection policies ignore temporal relations among all video frames. The sequential selection process also hinders the application of these video s lers in speed-critical systems. In this article, we propose a differentiable parallel video s ling network (PSN) to tackle the aforementioned challenges, First, we optimize the video s ler with a differentiable surrogate loss, allowing to dynamically learn the s ler with the cooperation from the video classification model. Our s ler considers the feedback from all frames jointly, eliminating the learning difficulties of sequential decision making. The learning process is fully gradient-based, making the s ler be learned efficiently. Our video s ler can assess a set of frames swiftly and determine the importance of each frame in parallel. Second, we propose to model the inter-relation among contextual frames, which encourages the s ler to select frames based on a comprehensive inspection of the entire video. We observe that a simple context relation mining instantiation would significantly improve the classification performance. The experimental results on three standard video recognition benchmarks demonstrate the efficacy and efficiency of our framework.
Few-Example Object Detection with Model Communication
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2019
A discriminative CNN video representation for event detection
Publisher: IEEE
Date: 06-2015
Convolutional Reconstruction-to-Sequence for Video Captioning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2020
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro
Publisher: IEEE
Date: 10-2017
Point Spatio-Temporal Transformer Networks for Point Cloud Video Modeling
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2023
Discovering Discriminative Graphlets for Aerial Image Categories Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2013
Guest Editorial: Special issue on large scale multimedia semantic indexing
Publisher: Elsevier BV
Date: 07-2014
Weakly Supervised Multilabel Clustering and its Applications in Computer Vision
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2016
Cascaded Revision Network for Novel Object Captioning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2020
Revisiting EmbodiedQA: A Simple Baseline and Beyond
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Two-Stream Multirate Recurrent Neural Network for Video-Based Pedestrian Reidentification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2018
Circulating SARS-CoV-2 spike N439K variants maintain fitness while evading antibody-mediated immunity
Publisher: Elsevier BV
Date: 03-2021
Space-Time Robust Representation for Action Recognition
Publisher: IEEE
Date: 12-2013
Exploiting the entire feature space with sparsity for automatic image annotation
Publisher: ACM
Date: 28-11-2011
IDE: Image Dehazing and Exposure Using an Enhanced Atmospheric Scattering Model
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Semisupervised Feature Selection via Spline Regression for Video Semantic Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2015
Fast and Low Memory Cost Matrix Factorization: Algorithm, Analysis and Case Study
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2020
How Related Exemplars Help Complex Event Detection in Web Videos?
Publisher: IEEE
Date: 12-2013
E-LAMP: integration of innovative ideas for multimedia event detection
Publisher: Springer Science and Business Media LLC
Date: 09-07-2013
Video Pivoting Unsupervised Multi-Modal Machine Translation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Online compressed robust PCA
Publisher: IEEE
Date: 05-2017
Combining location and feature information for multimedia retrieval
Publisher: Inderscience Publishers
Date: 2010
Uncovering the Temporal Context for Video Question Answering
Publisher: Springer Science and Business Media LLC
Date: 13-07-2017
Unified Dictionary Learning and Region Tagging with Hierarchical Sparse Representation
Publisher: Elsevier BV
Date: 08-2013
Collaborative Content-Dependent Modeling: A Return to the Roots of Salient Object Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Penalizing the Hard Example But Not Too Much: A Strong Baseline for Fine-Grained Visual Classification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Retrieval-based cartoon gesture recognition and applications via semi-supervised heterogeneous classifiers learning
Publisher: Elsevier BV
Date: 2013
Graph Structure Fusion for Multiview Clustering
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2019
Guest Editorial: Ad Hoc Web Multimedia Analysis with Limited Supervision
Publisher: Springer Science and Business Media LLC
Date: 2015
Convex Sparse PCA for Unsupervised Feature Learning
Publisher: Association for Computing Machinery (ACM)
Date: 20-07-2016
DOI: 10.1145/2910585
Abstract: Principal component analysis (PCA) has been widely applied to dimensionality reduction and data pre-processing for different applications in engineering, biology, social science, and the like. Classical PCA and its variants seek for linear projections of the original variables to obtain the low-dimensional feature representations with maximal variance. One limitation is that it is difficult to interpret the results of PCA. Besides, the classical PCA is vulnerable to certain noisy data. In this paper, we propose a Convex Sparse Principal Component Analysis (CSPCA) algorithm and apply it to feature learning. First, we show that PCA can be formulated as a low-rank regression optimization problem. Based on the discussion, the l 2, 1 -normminimization is incorporated into the objective function to make the regression coefficients sparse, thereby robust to the outliers. Also, based on the sparse model used in CSPCA, an optimal weight is assigned to each of the original feature, which in turn provides the output with good interpretability. With the output of our CSPCA, we can effectively analyze the importance of each feature under the PCA criteria. Our new objective function is convex, and we propose an iterative algorithm to optimize it. We apply the CSPCA algorithm to feature selection and conduct extensive experiments on seven benchmark datasets. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art unsupervised feature selection algorithms.
Weakly Supervised Moment Localization with Decoupled Consistent Concept Prediction
Publisher: Springer Science and Business Media LLC
Date: 19-03-2022
IDBP: Image Dehazing Using Blended Priors Including Non-Local, Local, and Global Priors
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2022
Bag-of-Discriminative-Words (BoDW) Representation via Topic Modeling
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2017
Temporal Cross-Layer Correlation Mining for Action Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Self-Correction for Human Parsing
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2022
The Many Shades of Negativity
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2017
Align and Tell: Boosting Text-Video Retrieval With Local Alignment and Fine-Grained Supervision
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Discriminative Feature Learning for Thorax Disease Classification in Chest X-ray Images
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
A Discriminatively Learned CNN Embedding for Person Reidentification
Publisher: Association for Computing Machinery (ACM)
Date: 13-12-2017
DOI: 10.1145/3159171
Abstract: In this article, we revisit two popular convolutional neural networks in person re-identification (re-ID): verification and identification models. The two models have their respective advantages and limitations due to different loss functions. Here, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a Siamese network that simultaneously computes the identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two input images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus taking full usage of the re-ID annotations. Our method can be easily applied on different pretrained networks. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show that our architecture can also be applied to image retrieval. The code is available at ayumi/2016_person_re-ID.
Compound Rank-k Projections for Bilinear Analysis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2016
Active learning for social image retrieval using Locally Regressive Optimal Design
Publisher: Elsevier BV
Date: 10-2012
Boosting Cross-Media Retrieval by Learning with Positive and Negative Examples
Publisher: Springer Berlin Heidelberg
Date: 2006
A Dual-Network Progressive Approach to Weakly Supervised Object Detection
Publisher: ACM
Date: 19-10-2017
Identifying Visible Parts via Pose Estimation for Occluded Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2022
We are not equally negative
Publisher: ACM
Date: 21-10-2013
Cross-media retrieval using query dependent search methods
Publisher: Elsevier BV
Date: 08-2010
Multiview Consensus Graph Clustering
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2019
Instance as Identity: A Generic Online Paradigm for Video Instance Segmentation
Publisher: Springer Nature Switzerland
Date: 2022
Unsupervised Person Re-identification via Cross-Camera Similarity Exploration
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Compact and Discriminative Descriptor Inference Using Multi-Cues
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2015
Compound Memory Networks for Few-Shot Video Classification
Publisher: Springer International Publishing
Date: 2018
Learning With Noisy Labels via Self-Reweighting From Class Centroids
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2022
Dynamic Slimmable Denoising Network
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Content-Based Video Search over 1 Million Videos with 1 Core in 1 Second
Publisher: ACM
Date: 22-06-2015
Pyramidal Multiple Instance Detection Network With Mask Guided Self-Correction for Weakly Supervised Object Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Unsupervised Visual Representation Learning via Dual-Level Progressive Similar Instance Selection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2022
On the influence propagation of web videos
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2014
Guest editorial: web multimedia semantic inference using multi-cues
Publisher: Springer Science and Business Media LLC
Date: 23-06-2015
Progressive Learning for Person Re-Identification With One Example
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2019
Contrastive Adaptation Network for Single- and Multi-Source Domain Adaptation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2022
Learning a 3D Human Pose Distance Metric from Geometric Pose Descriptor
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2011
Partial Alignment for Object Detection in the Wild
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2022
Event Oriented Dictionary Learning for Complex Event Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2015
SIFT Meets CNN: A Decade Survey of Instance Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2018
Classifier-specific intermediate representation for multimedia tasks
Publisher: ACM
Date: 05-06-2012
Robust top-k multiclass SVM for visual category recognition
Publisher: ACM
Date: 04-08-2017
Switchable Novel Object Captioner
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Understanding Multimedia Document Semantics for Cross-Media Retrieval
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11581772_87
Query-Efficient Black-Box Adversarial Attack With Customized Iteration and Sampling
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2023
Symbiotic Attention for Egocentric Action Recognition With Object-Centric Alignment
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2023
Feature Weighting via Optimal Thresholding for Video Analysis
Publisher: IEEE
Date: 12-2013
Differentiable Multi-Granularity Human Parsing
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Sketch-Guided Scenery Image Outpainting
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Identifying Objective and Subjective Words via Topic Modeling
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2018
Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
SemGloVe: Semantic Co-Occurrences for GloVe From BERT
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Self-produced Guidance for Weakly-Supervised Object Localization
Publisher: Springer International Publishing
Date: 2018
Augmenting Image Descriptions Using <newline/>Structured Prediction Output
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2014
A Probabilistic Associative Model for Segmenting Weakly Supervised Images
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2014
Cross-media relevance mining for evaluating text-based image search engine
Publisher: IEEE
Date: 07-2014
VehicleNet: Learning Robust Visual Representation for Vehicle Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Event Detection Using Multi-level Relevance Labels and Multiple Features
Publisher: IEEE
Date: 06-2014
DOI: 10.1109/CVPR.2014.20
ART-UP: A Novel Method for Generating Scanning-Robust Aesthetic QR Codes
Publisher: Association for Computing Machinery (ACM)
Date: 28-02-2021
DOI: 10.1145/3418214
Abstract: Quick response (QR) codes are usually scanned in different environments, so they must be robust to variations in illumination, scale, coverage, and camera angles. Aesthetic QR codes improve the visual quality, but subtle changes in their appearance may cause scanning failure. In this article, a new method to generate scanning-robust aesthetic QR codes is proposed, which is based on a module-based scanning probability estimation model that can effectively balance the tradeoff between visual quality and scanning robustness. Our method locally adjusts the luminance of each module by estimating the probability of successful s ling. The approach adopts the hierarchical, coarse-to-fine strategy to enhance the visual quality of aesthetic QR codes, which sequentially generate the following three codes: a binary aesthetic QR code, a grayscale aesthetic QR code, and the final color aesthetic QR code. Our approach also can be used to create QR codes with different visual styles by adjusting some initialization parameters. User surveys and decoding experiments were adopted for evaluating our method compared with state-of-the-art algorithms, which indicates that the proposed approach has excellent performance in terms of both visual quality and scanning robustness.
Robust cross-media transfer for visual event detection
Publisher: ACM
Date: 29-10-2012
Tag localization with spatial correlations and joint group sparsity
Publisher: IEEE
Date: 06-2011
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
Publisher: ACM
Date: 26-10-2023
SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2020
Fine-Grained Image Categorization by Localizing TinyObject Parts from Unannotated Images
Publisher: ACM
Date: 22-06-2015
Large-Scale Geosocial Multimedia [Guest editorial]
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2014
DOI: 10.1109/MMUL.2014.43
Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in the Dark
Publisher: ACM
Date: 26-10-2023
Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2020
Zero-Shot Video Event Detection With High-Order Semantic Concept Discovery and Matching
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Cross-media hashing with kernel regression
Publisher: IEEE
Date: 07-2014
Infrared Action Detection in the Dark via Cross-Stream Attention Mechanism
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Strategies for searching video content with text queries or video examples
Publisher: Institute of Image Information and Television Engineers
Date: 2016
DOI: 10.3169/MTA.4.227
Spline Regression Hashing for Fast Image Search
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2012
A plasmid DNA-launched SARS-CoV-2 reverse genetics system and coronavirus toolkit for COVID-19 research
Publisher: Public Library of Science (PLoS)
Date: 25-02-2021
DOI: 10.1371/JOURNAL.PBIO.3001091
Abstract: The recent emergence of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), the underlying cause of Coronavirus Disease 2019 (COVID-19), has led to a worldwide pandemic causing substantial morbidity, mortality, and economic devastation. In response, many laboratories have redirected attention to SARS-CoV-2, meaning there is an urgent need for tools that can be used in laboratories unaccustomed to working with coronaviruses. Here we report a range of tools for SARS-CoV-2 research. First, we describe a facile single plasmid SARS-CoV-2 reverse genetics system that is simple to genetically manipulate and can be used to rescue infectious virus through transient transfection (without in vitro transcription or additional expression plasmids). The rescue system is accompanied by our panel of SARS-CoV-2 antibodies (against nearly every viral protein), SARS-CoV-2 clinical isolates, and SARS-CoV-2 permissive cell lines, which are all openly available to the scientific community. Using these tools, we demonstrate here that the controversial ORF10 protein is expressed in infected cells. Furthermore, we show that the promising repurposed antiviral activity of apilimod is dependent on TMPRSS2 expression. Altogether, our SARS-CoV-2 toolkit, which can be directly accessed via our website at mrcppu-covid.bio/ , constitutes a resource with considerable potential to advance COVID-19 vaccine design, drug testing, and discovery science.
Rich Embedding Features for One-Shot Semantic Segmentation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2022
Cross-modal Data Augmentation for Tasks of Different Modalities
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Fast and Accurate Content-based Semantic Search in 100M Internet Videos
Publisher: ACM
Date: 13-10-2015
Divide and Retain: A Dual-Phase Modeling for Long-Tailed Visual Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
CamStyle: A Novel Data Augmentation Method for Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2019
Progressive Transfer Learning for Face Anti-Spoofing
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Generalizing a Person Retrieval Model Hetero- and Homogeneously
Publisher: Springer International Publishing
Date: 2018
Person Reidentification via Multi-Feature Fusion With Adaptive Graph Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2020
Action Keypoint Network for Efficient Video Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Twitter100k: A Real-World Dataset for Weakly Supervised Cross-Media Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2018
Interactive Video Indexing With Statistical Active Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2012
A Multimedia Retrieval Framework Based on Semi-Supervised Ranking and Relevance Feedback
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2012
Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Discriminative Nonnegative Spectral Clustering with Out-of-Sample Extension
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2013
Human Activity Analysis for Geriatric Care in Nursing Homes
Publisher: Springer New York
Date: 03-08-2012
Robust Hashing With Local Models for Approximate Similarity Search
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2014
Regularized Deep Belief Network for Image Attribute Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2017
AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion
Publisher: ACM
Date: 26-10-2023
Clustering-Guided Sparse Structural Learning for Unsupervised Feature Selection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2014
DOI: 10.1109/TKDE.2013.65
Adaptive Structure Discovery for Multimedia Analysis Using Multiple Features
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2018
Weakly Supervised Photo Cropping
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2014
Recognizing an Action Using Its Name: A Knowledge-Based Approach
Publisher: Springer Science and Business Media LLC
Date: 02-03-2016
Multimedia Event Detection Using A Classifier-Specific Intermediate Representation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2013
Learning Distilled Graph for Large-Scale Social Network Data Clustering
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2020
Harnessing Lab Knowledge for Real-World Action Recognition
Publisher: Springer Science and Business Media LLC
Date: 16-04-2014
Few-Shot Common-Object Reasoning Using Common-Centric Localization Network
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation
Publisher: ACM
Date: 26-10-2023
Complex Event Detection by Identifying Reliable Shots from Untrimmed Videos
Publisher: IEEE
Date: 10-2017
DOI: 10.1109/ICCV.2017.86
Searching persuasively: Joint event detection and evidence recounting with limited supervision
Publisher: ACM
Date: 13-10-2015
Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization
Publisher: Springer Science and Business Media LLC
Date: 13-11-2015
Learning to Anticipate Egocentric Actions by Imagination
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Dynamic background learning through deep auto-encoder networks
Publisher: ACM
Date: 03-11-2014
Macro-Micro Adversarial Network for Human Parsing
Publisher: Springer International Publishing
Date: 2018
Show Me a Video: A Large-Scale Narrated Video Dataset for Coherent Story Illustration
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Multiple Features But Few Labels?
Publisher: ACM
Date: 03-11-2014
Exploiting detected visual objects for frame-level video filtering
Publisher: Springer Science and Business Media LLC
Date: 27-10-2017
Unsupervised Video Adaptation for Parsing Human Motion
Publisher: Springer International Publishing
Date: 2014
Discriminative Orthogonal Nonnegative matrix factorization with flexibility for data representation
Publisher: Elsevier BV
Date: 03-2014
Parameter-Efficient Person Re-Identification in the 3D Space
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Special section on learning from multiple evidences for large scale multimedia analysis
Publisher: Elsevier BV
Date: 2014
Resource Constrained Multimedia Event Detection
Publisher: Springer International Publishing
Date: 2014
Multitask Spectral Clustering by Exploring Intertask Correlation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2015
An Adaptive Semisupervised Feature Analysis for Video Semantic Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2018
FRC-Net: A Simple Yet Effective Architecture for Low-Light Image Enhancement
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Guest editorial: Adaptation methods for multimedia analysis
Publisher: Elsevier BV
Date: 2016
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
Publisher: Springer Science and Business Media LLC
Date: 06-01-2021
Early Active Learning with Pairwise Constraint for Person Re-identification
Publisher: Springer International Publishing
Date: 2017
Web and Personal Image Annotation by Mining Label Correlation With Relaxed Visual Graph Embedding
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2012
Beyond trace ratio: Weighted harmonic mean of trace ratios for multiclass discriminant analysis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2017
Co-Learning Meets Stitch-Up for Noisy Multi-Label Visual Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Using Detected Visual Objects to Index Video Database
Publisher: Springer International Publishing
Date: 2016
Training Robust Object Detectors From Noisy Category Labels and Imprecise Bounding Boxes
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)
Publisher: Springer International Publishing
Date: 2018
Data-Driven Answer Selection in Community QA Systems
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2017
On the Large-Scale Transferability of Convolutional Neural Networks
Publisher: Springer International Publishing
Date: 2018
Progressive Local Filter Pruning for Image Retrieval Acceleration
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Cyclic Self-Training With Proposal Weight Modulation for Cross-Supervised Object Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Local-Global Context Aware Transformer for Language-Guided Video Segmentation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2023
Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Supervision by Registration and Triangulation for Landmark Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2021
Unsupervised Person Re-identification
Publisher: Association for Computing Machinery (ACM)
Date: 10-10-2018
DOI: 10.1145/3243316
Abstract: The superiority of deeply learned pedestrian representations has been reported in very recent literature of person re-identification (re-ID). In this article, we consider the more pragmatic issue of learning a deep feature with no or only a few labels. We propose a progressive unsupervised learning (PUL) method to transfer pretrained deep representations to unseen domains. Our method is easy to implement and can be viewed as an effective baseline for unsupervised re-ID feature learning. Specifically, PUL iterates between (1) pedestrian clustering and (2) fine-tuning of the convolutional neural network (CNN) to improve the initialization model trained on the irrelevant labeled dataset. Since the clustering results can be very noisy, we add a selection operation between the clustering and fine-tuning. At the beginning, when the model is weak, CNN is fine-tuned on a small amount of reliable ex les that locate near to cluster centroids in the feature space. As the model becomes stronger, in subsequent iterations, more images are being adaptively selected as CNN training s les. Progressively, pedestrian clustering and the CNN model are improved simultaneously until algorithm convergence. This process is naturally formulated as self-paced learning. We then point out promising directions that may lead to further improvement. Extensive experiments on three large-scale re-ID datasets demonstrate that PUL outputs discriminative features that improve the re-ID accuracy. Our code has been released at ehefan/Unsupervised-Person-Re-identification-Clustering-and-Fine-tuning.
Weakly supervised sparse coding with geometric consistency pooling
Publisher: IEEE
Date: 06-2012
Feature Interaction Augmented Sparse Learning for Fast Kinect Motion Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2017
Feature Selection for Multimedia Analysis by Sharing Information Among Multiple Tasks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2013
Active Learning for Deep Visual Tracking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Hierarchical Memory Decoder for Visual Narrating
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2021
Dual-path Convolutional Image-Text Embeddings with Instance Loss
Publisher: Association for Computing Machinery (ACM)
Date: 22-05-2020
DOI: 10.1145/3383184
Abstract: Matching images and sentences demands a fine understanding of both modalities. In this article, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply the ranking loss to pull the positive image/text pairs close and push the negative pairs apart from each other. However, directly deploying the ranking loss on heterogeneous features (i.e., text and image features) is less effective, because it is hard to find appropriate triplets at the beginning. So the naive way of using the ranking loss may compromise the network from learning inter-modal relationship. To address this problem, we propose the instance loss, which explicitly considers the intra-modal data distribution. It is based on an unsupervised assumption that each image/text group can be viewed as a class. So the network can learn the fine granularity from every image/text group. The experiment shows that the instance loss offers better weight initialization for the ranking loss, so that more discriminative embeddings can be learned. Besides, existing works usually apply the off-the-shelf features, i.e., word2vec and fixed visual feature. So in a minor contribution, this article constructs an end-to-end dual-path convolutional network to learn the image and text representations. End-to-end learning allows the system to directly learn from the data and fully utilize the supervision. On two generic retrieval datasets (Flickr30k and MSCOCO), experiments demonstrate that our method yields competitive accuracy compared to state-of-the-art methods. Moreover, in language-based person retrieval, we improve the state of the art by a large margin. The code has been made publicly available.
Interactive Surveillance Event Detection through Mid-level Discriminative Representation
Publisher: ACM
Date: 04-2014
Point Adversarial Self-Mining: A Simple Method for Facial Expression Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Temporal Pixel-Level Semantic Understanding Through the VSPW Dataset
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2023
Harmonizing Hierarchical Manifolds for Multimedia Document Semantics Understanding and Cross-Media Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2008
Knowledge adaptation for ad hoc multimedia event detection with few exemplars
Publisher: ACM
Date: 29-10-2012
Discriminative coupled dictionary hashing for fast cross-media retrieval
Publisher: ACM
Date: 03-07-2014
Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: The Benefit of Target Expectation Maximization
Publisher: Springer International Publishing
Date: 2018
Bilaterally Normalized Scale-Consistent Sinkhorn Distance for Few-Shot Image Classification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Inter-media hashing for large-scale retrieval from heterogeneous data sources
Publisher: ACM
Date: 22-06-2013
Action recognition by exploring data distribution and feature correlation
Publisher: IEEE
Date: 06-2012
Exploiting Combination Effect for Unsupervised Feature Selection by <inline-formula> <tex-math notation=LaTeX>$\ell_{2,0}$ </tex-math> </
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Discriminating Joint Feature Analysis for Multimedia Data Understanding
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2012
Saying the Unseen: Video Descriptions via Dialog Agents
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2022
Aspect Learning for Multimedia Summarization via Nonparametric Bayesian
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2016
Overcoming Semantic drift in information extraction
Publisher: No publisher found
Date: 2014
Fall detection in multi-camera surveillance videos
Publisher: ACM
Date: 22-10-2013
Modality-Invariant Image-Text Embedding for Image-Sentence Matching
Publisher: Association for Computing Machinery (ACM)
Date: 07-02-2019
DOI: 10.1145/3300939
Abstract: Performing direct matching among different modalities (like image and text) can benefit many tasks in computer vision, multimedia, information retrieval, and information fusion. Most of existing works focus on class-level image-text matching, called cross-modal retrieval , which attempts to propose a uniform model for matching images with all types of texts, for ex le, tags, sentences, and articles (long texts). Although cross-model retrieval alleviates the heterogeneous gap among visual and textual information, it can provide only a rough correspondence between two modalities. In this article, we propose a more precise image-text embedding method, image-sentence matching, which can provide heterogeneous matching in the instance level. The key issue for image-text embedding is how to make the distributions of the two modalities consistent in the embedding space. To address this problem, some previous works on the cross-model retrieval task have attempted to pull close their distributions by employing adversarial learning. However, the effectiveness of adversarial learning on image-sentence matching has not been proved and there is still not an effective method. Inspired by previous works, we propose to learn a modality-invariant image-text embedding for image-sentence matching by involving adversarial learning. On top of the triplet loss--based baseline, we design a modality classification network with an adversarial loss, which classifies an embedding into either the image or text modality. In addition, the multi-stage training procedure is carefully designed so that the proposed network not only imposes the image-text similarity constraints by ground-truth labels, but also enforces the image and text embedding distributions to be similar by adversarial learning. Experiments on two public datasets (Flickr30k and MSCOCO) demonstrate that our method yields stable accuracy improvement over the baseline model and that our results compare favorably to the state-of-the-art methods.
Bidirectional Multirate Reconstruction for Temporal Modeling in Videos
Publisher: IEEE
Date: 07-2017
A cognitive assistive system for monitoring the use of home medical devices
Publisher: ACM
Date: 22-10-2013
Effective transfer tagging from image to video
Publisher: Association for Computing Machinery (ACM)
Date: 05-2013
Abstract: Recent years have witnessed a great explosion of user-generated videos on the Web. In order to achieve an effective and efficient video search, it is critical for modern video search engines to associate videos with semantic keywords automatically. Most of the existing video tagging methods can hardly achieve reliable performance due to deficiency of training data. It is noticed that abundant well-tagged data are available in other relevant types of media (e.g., images). In this article, we propose a novel video tagging framework, termed as Cross-Media Tag Transfer (CMTT), which utilizes the abundance of well-tagged images to facilitate video tagging. Specifically, we build a “cross-media tunnel” to transfer knowledge from images to videos. To this end, an optimal kernel space, in which distribution distance between images and video is minimized, is found to tackle the domain-shift problem. A novel cross-media video tagging model is proposed to infer tags by exploring the intrinsic local structures of both labeled and unlabeled data, and learn reliable video classifiers. An efficient algorithm is designed to optimize the proposed model in an iterative and alternative way. Extensive experiments illustrate the superiority of our proposal compared to the state-of-the-art algorithms.
Guest editors' introduction: Perception, Aesthetics, and Emotion in Multimedia Quality Modeling
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2016
DOI: 10.1109/MMUL.2016.42
Personalized Video Recommendation Using Rich Contents from Videos
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2020
Related Organisations
Related Funding Activities
Discovery Early Career Researcher Award - Grant ID: DE130101311
Start Date: 05-2013
End Date: 12-2016
Amount: $375,000.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP200100938
Start Date: 05-2020
End Date: 03-2025
Amount: $486,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP160100630
Start Date: 07-2016
End Date: 07-2020
Amount: $520,000.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP180100106
Start Date: 2018
End Date: 12-2021
Amount: $392,884.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP150103008
Start Date: 2015
End Date: 12-2018
Amount: $494,300.00
Funder: Australian Research Council
View Funded Activity