ORCID Profile
0000-0001-7790-6423
Current Organisation
University of Adelaide
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)
Artificial Intelligence and Image Processing | Computer Vision | Adaptive Agents and Intelligent Robotics | Pattern Recognition and Data Mining | Mining Engineering | Neural, Evolutionary and Fuzzy Computation |
ANZSRC Socio-Economic Objective (SEO)
Expanding Knowledge in the Information and Computing Sciences | Application Software Packages (excl. Computer Games) | Computer Software and Services not elsewhere classified | Plant Production and Plant Primary Products not elsewhere classified | Information Processing Services (incl. Data Entry and Capture) | Coal Mining and Extraction | Understanding Australia's Past | Emerging Defence Technologies | Mineral Exploration not elsewhere classified | Manufacturing not elsewhere classified
Related Links
Publications
Hidden view synthesis using real-time visual SLAM for simplifying video surveillance analysis
Publisher: IEEE
Date: 05-2011
Dense 3D Face Correspondence
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2018
Training medical image analysis systems like radiologists
Publisher: Springer International Publishing
Date: 2018
Measuring the performance of single image depth estimation methods
Publisher: IEEE
Date: 10-2016
Estimating gaze direction from low-resolution faces in video
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11744047_31
Active tracking of foveated feature clusters using affine structure
Publisher: Springer Science and Business Media LLC
Date: 04-1996
DOI: 10.1007/BF00126139
Automated alignment of Robotic pan-tilt camera units using vision
Publisher: Springer Science and Business Media LLC
Date: 05-2006
Efficient 3D scene labeling using fields of trees
Publisher: IEEE
Date: 12-2013
Deep regression tracking with shrinkage loss
Publisher: Springer International Publishing
Date: 2018
Geometrically consistent plane extraction for dense indoor 3D maps segmentation
Publisher: IEEE
Date: 10-2016
Approximate Fisher Information Matrix to Characterize the Training of Deep Neural Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Reconstruct locally, localize globally: A model free method for object pose estimation
Publisher: IEEE
Date: 06-2020
Dense monocular reconstruction using surface normals
Publisher: IEEE
Date: 05-2017
Video synchronization from human motion using rank constraints
Publisher: Elsevier BV
Date: 08-2009
Model-based recognition and range imaging for a guided vehicle
Publisher: Elsevier BV
Date: 04-1992
Structured binary neural networks for accurate image classification and semantic segmentation
Publisher: IEEE
Date: 06-2019
Structure Aware SLAM Using Quadrics and Planes
Publisher: Springer International Publishing
Date: 2019
Global stereo reconstruction under second order smoothness priors
Publisher: IEEE
Date: 06-2008
12th Asian conference on computer vision
Publisher: Elsevier BV
Date: 05-2016
Meaningful Maps With Object-Oriented Semantic Mapping
Publisher: IEEE
Date: 09-2017
Binary constrained deep hashing network for image retrieval without manual annotation
Publisher: IEEE
Date: 2019
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2016
Deep learning for 2D scan matching and loop closure
Publisher: IEEE
Date: 09-2017
Topnet: Structural point cloud decoder
Publisher: IEEE
Date: 06-2019
Single view metrology
Publisher: Springer Science and Business Media LLC
Date: 2000
Exploring Context with Deep Structured Models for Semantic Segmentation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2018
Goal-directed video metrology
Publisher: Springer Berlin Heidelberg
Date: 1996
On combining visual SLAM and visual odometry
Publisher: IEEE
Date: 05-2010
Latent data association: Bayesian model selection for multi-target tracking
Publisher: IEEE
Date: 12-2013
HM$^4$: Hidden Markov Model With Memory Management for Visual Place Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
A probabilistic framework for recognizing similar actions using spatio-temporal features
Publisher: British Machine Vision Association
Date: 2007
DOI: 10.5244/C.21.8
Regressing local to global shape properties for online segmentation and tracking
Publisher: Springer Science and Business Media LLC
Date: 11-06-2014
Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression.
Publisher: IEEE
Date: 06-2019
Simultaneous monocular 2D segmentation, 3D pose recovery and 3D reconstruction
Publisher: Springer Berlin Heidelberg
Date: 2013
Self-alignment of a binocular robot
Publisher: Elsevier BV
Date: 08-1996
Are you talking to me? Reasoned visual dialog generation through adversarial learning
Publisher: IEEE
Date: 06-2018
RRD-SLAM: Radial-distorted rolling-shutter direct SLAM
Publisher: IEEE
Date: 05-2017
Improving Global Multi-target Tracking with Local Updates
Publisher: Springer International Publishing
Date: 2015
Object Captioning and Retrieval with Natural Language
Publisher: IEEE
Date: 10-2019
Computer Vision-ACCV 2014:12th Asian Conference on Computer Vision Singapore, Singapore, November 1–5, 2014 Revised Selected Papers, Part I
Publisher: Springer International Publishing
Date: 2014
SC-DepthV3: Robust Self-Supervised Monocular Depth Estimation for Dynamic Scenes
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Scalable deep k-subspace clustering
Publisher: Springer International Publishing
Date: 2019
Simultaneous 3D tracking and reconstruction on a mobile phone
Publisher: IEEE
Date: 10-2013
A constant-time efficient stereo SLAM system
Publisher: British Machine Vision Association
Date: 2009
DOI: 10.5244/C.23.54
Learning deeply supervised good features to match for dense monocular reconstruction
Publisher: Springer International Publishing
Date: 2019
A dynamic programming approach to reconstructing building interiors
Publisher: Springer Berlin Heidelberg
Date: 2010
Attention-guided network for ghost-free high dynamic range imaging
Publisher: IEEE
Date: 06-2019
Visual Odometry Revisited: What Should Be Learnt?
Publisher: IEEE
Date: 05-2020
PWP3D: Real-time segmentation and tracking of 3D objects
Publisher: British Machine Vision Association
Date: 2009
DOI: 10.5244/C.23.47
Modelling pedestrian trajectory patterns with Gaussian processes
Publisher: IEEE
Date: 09-2009
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking
Publisher: Springer Science and Business Media LLC
Date: 23-12-2020
DOI: 10.1007/S11263-020-01393-0
Abstract: Standardized benchmarks have been crucial in pushing the performance of computer vision algorithms, especially since the advent of deep learning. Although leaderboards should not be over-claimed, they often provide the most objective measure of performance and are therefore important guides for research. We present MOTChallenge , a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data and create a framework for the standardized evaluation of multiple object tracking methods. The benchmark is focused on multiple people tracking, since pedestrians are by far the most studied object in the tracking community, with applications ranging from robot navigation to self-driving cars. This paper collects the first three releases of the benchmark: (i) MOT15 , along with numerous state-of-the-art results that were submitted in the last years, (ii) MOT16 , which contains new challenging videos, and (iii) MOT17 , that extends MOT16 sequences with more precise labels and evaluates tracking performance on three different object detectors. The second and third release not only offers a significant increase in the number of labeled boxes, but also provide labels for multiple object classes beside pedestrians, as well as the level of visibility for every single object of interest. We finally provide a categorization of state-of-the-art trackers and a broad error analysis. This will help newcomers understand the related work and research trends in the MOT community, and hopefully shed some light into potential future research directions.
SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
Publisher: IEEE
Date: 05-2018
Unsupervised CNN for single view depth estimation: Geometry to the rescue
Publisher: Springer International Publishing
Date: 2016
Pre and post-hoc diagnosis and interpretation of malignancy from breast DCE-MRI
Publisher: Elsevier BV
Date: 12-2019
DOI: 10.1016/J.MEDIA.2019.101562
Abstract: We propose a new method for breast cancer screening from DCE-MRI based on a post-hoc approach that is trained using weakly annotated data (i.e., labels are available only at the image level without any lesion delineation). Our proposed post-hoc method automatically diagnosis the whole volume and, for positive cases, it localizes the malignant lesions that led to such diagnosis. Conversely, traditional approaches follow a pre-hoc approach that initially localises suspicious areas that are subsequently classified to establish the breast malignancy - this approach is trained using strongly annotated data (i.e., it needs a delineation and classification of all lesions in an image). We also aim to establish the advantages and disadvantages of both approaches when applied to breast screening from DCE-MRI. Relying on experiments on a breast DCE-MRI dataset that contains scans of 117 patients, our results show that the post-hoc method is more accurate for diagnosing the whole volume per patient, achieving an AUC of 0.91, while the pre-hoc method achieves an AUC of 0.81. However, the performance for localising the malignant lesions remains challenging for the post-hoc method due to the weakly labelled dataset employed during training.
Parallel attention: a unified framework for visual object discovery through dialogs and queries
Publisher: IEEE
Date: 06-2018
Gaze directed camera control for face image acquisition
Publisher: IEEE
Date: 05-2011
A theoretically sound upper bound on the triplet loss for improving the efficiency of deep distance metric learning
Publisher: IEEE
Date: 06-2019
Model agnostic saliency for weakly supervised lesion detection from breast DCE-MRI
Publisher: IEEE
Date: 04-2019
Real-time tracking of multiple occluding objects using level sets
Publisher: IEEE
Date: 06-2010
Nonlinear shape manifolds as shape priors in level set segmentation and tracking
Publisher: IEEE
Date: 06-2011
Integrating object detection with 3D tracking towards a better driver assistance system
Publisher: IEEE
Date: 08-2010
Message from the 3DV 2016 program chairs
Publisher: IEEE
Date: 10-2016
DOI: 10.1109/3DV.2016.6
Visual SLAM: Why bundle adjust?
Publisher: IEEE
Date: 05-2019
FroDO: From Detections to 3D Objects
Publisher: IEEE
Date: 06-2020
From motion blur to motion flow: A deep learning solution for removing heterogeneous motion blur
Publisher: IEEE
Date: 07-2017
Camera calibration from human motion
Publisher: Elsevier BV
Date: 06-2008
Articulated structure from motion by factorization
Publisher: IEEE
Date: 2005
DOI: 10.1109/CVPR.2005.75
Self-supervised learning for single view depth and surface normal estimation
Publisher: IEEE
Date: 05-2019
A unified energy minimization framework for model fitting in depth
Publisher: Springer Berlin Heidelberg
Date: 2012
Vast-scale outdoor navigation using adaptive relative bundle adjustment
Publisher: SAGE Publications
Date: 04-05-2010
Abstract: In this paper we describe a relative approach to simultaneous localization and mapping, based on the insight that a continuous relative representation can make the problem tractable at large scales. First, it is well known that bundle adjustment is the optimal non-linear least-squares formulation for this problem, in that its maximum-likelihood form matches the definition of the Cramer—Rao lower bound. Unfortunately, computing the maximum-likelihood solution is often prohibitively expensive: this is especially true during loop closures, which often necessitate adjusting all parameters in a loop. In this paper we note that it is precisely the choice of a single privileged coordinate frame that makes bundle adjustment costly, and that this expense can be avoided by adopting a completely relative approach. We derive a new relative bundle adjustment which, instead of optimizing in a single Euclidean space, works in a metric space defined by a manifold. Using an adaptive optimization strategy, we show experimentally that it is possible to solve for the full maximum-likelihood solution incrementally in constant time, even at loop closure. Our approach is, by definition, everywhere locally Euclidean, and we show that the local Euclidean estimate matches that of traditional bundle adjustment. Our system operates online in realtime using stereo data, with fast appearance-based loop closure detection. We show results on over 850,000 images that indicate the accuracy and scalability of the approach, and process over 330 GB of image data into a relative map covering 142 km of Southern England. To demonstrate a baseline sufficiency for navigation, we show that it is possible to find shortest paths in the relative maps we build, in terms of both time and distance. Query images from the web of popular landmarks around London, such as the London Eye or Trafalgar Square, are matched to the relative map to provide route planning goals.
Cognitive visual tracking and camera control
Publisher: Elsevier BV
Date: 03-2012
Saccade and pursuit on an active head/eye platform
Publisher: Elsevier BV
Date: 04-1994
Providing synthetic views for teleoperation using visual pose tracking in multiple cameras
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2001
DOI: 10.1109/3468.903865
Joint tracking and segmentation of multiple targets
Publisher: IEEE
Date: 06-2015
Structured learning of human interactions in TV shows
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2012
High Five: Recognising human interactions in TV shows
Publisher: British Machine Vision Association
Date: 2010
DOI: 10.5244/C.24.50
Attend in groups: A weakly-supervised deep learning framework for learning from web data
Publisher: IEEE
Date: 07-2017
The active recovery of 3D motion trajectories and their use in prediction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-1997
DOI: 10.1109/34.584099
Recognition of parameterized objects from 3D data: a parallel implementation
Publisher: Elsevier BV
Date: 11-1994
Stable multi-target tracking in real-time surveillance video
Publisher: IEEE
Date: 06-2011
PWP3D: Real-time segmentation and tracking of 3D objects
Publisher: Springer Science and Business Media LLC
Date: 10-01-2012
Automatic reasoning about causal events in surveillance video
Publisher: Springer Science and Business Media LLC
Date: 2011
DOI: 10.1155/2011/530325
Smart Mining for Deep Metric Learning
Publisher: IEEE
Date: 10-2017
Hierarchical higher-order regression forest fields: An application to 3D indoor scene labelling
Publisher: IEEE
Date: 12-2015
Visual Localization under Appearance Change: A Filtering Approach.
Publisher: IEEE
Date: 12-2019
Real-time monocular object-model aware sparse SLAM
Publisher: IEEE
Date: 05-2019
RefineNet: Multi-path refinement networks for high-resolution semantic segmentation
Publisher: IEEE
Date: 07-2017
RGBD based dimensional decomposition residual network for 3D semantic scene completion
Publisher: IEEE
Date: 06-2019
Automatic relocalization and loop closing for real-time monocular SLAM
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2011
Deep learning features at scale for visual place recognition
Publisher: IEEE
Date: 05-2017
A fast, modular scene understanding system using context-aware object detection
Publisher: IEEE
Date: 05-2015
From visual query to visual portrayal
Publisher: British Machine Vision Association
Date: 2008
DOI: 10.5244/C.22.117
Influence of zoom selection on a Kalman filter
Publisher: IEEE
Date: 09-2200
Robust 3D hand tracking for human computer interaction
Publisher: IEEE
Date: 03-2011
Navigating, recognizing and describing urban spaces with vision and lasers
Publisher: SAGE Publications
Date: 21-07-2009
Abstract: In this paper we describe a body of work aimed at extending the reach of mobile navigation and mapping. We describe how running topological and metric mapping and pose estimation processes concurrently, using vision and laser ranging, has produced a full six-degree-of-freedom outdoor navigation system. It is capable of producing intricate three-dimensional maps over many kilometers and in real time. We consider issues concerning the intrinsic quality of the built maps and describe our progress towards adding semantic labels to maps via scene de-construction and labeling. We show how our choices of representation, inference methods and use of both topological and metric techniques naturally allow us to fuse maps built from multiple sessions with no need for manual frame alignment or data association.
Semantic segmentation from limited training data
Publisher: IEEE
Date: 05-2018
Globally Optimal Event-Based Divergence Estimation for Ventral Landing
Publisher: Springer Nature Switzerland
Date: 2023
Addressing challenging place recognition tasks using generative adversarial networks
Publisher: IEEE
Date: 05-2018
Global stereo reconstruction under second-order smoothness priors
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2009
Projective calibration of a laser-stripe range finder
Publisher: Elsevier BV
Date: 10-1996
Multi-Task Structure-Aware Context Modeling for Robust Keypoint-Based Object Tracking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Temporally-coherent novel video synthesis using texture-based priors
Publisher: Information Processing Society of Japan
Date: 2009
Understanding interactions and guiding visual surveillance by tracking attention
Publisher: Springer Berlin Heidelberg
Date: 2011
Just-in-time reconstruction: Inpainting sparse maps using single view depth predictors as priors
Publisher: IEEE
Date: 05-2018
DeepSetNet: Predicting Sets with Deep Neural Networks
Publisher: IEEE
Date: 10-2017
Recognition of object classes from range data
Publisher: Elsevier BV
Date: 10-1995
Image interpolation for virtual sports scenarios
Publisher: Springer Science and Business Media LLC
Date: 10-06-2005
Online unsupervised feature learning for visual tracking
Publisher: Elsevier BV
Date: 07-2016
Dense reconstruction using 3D object shape priors
Publisher: IEEE
Date: 06-2013
Real-time human gaze estimation
Publisher: IEEE
Date: 12-2019
Efficient Dense Point Cloud Object Reconstruction Using Deformation Vector Fields
Publisher: Springer International Publishing
Date: 2018
Driving saccade to pursuit using image motion
Publisher: Springer Science and Business Media LLC
Date: 11-1995
DOI: 10.1007/BF01539627
Erratum: Self-calibration of rotating and zooming cameras (International Journal of Computer Vision (November 2001) 45:2)
Publisher: Springer Science and Business Media LLC
Date: 2002
Exploiting temporal information for DCNN-based fine-grained object classification
Publisher: IEEE
Date: 11-2016
Behaviour understanding in video: A combined method
Publisher: IEEE
Date: 2005
DOI: 10.1109/ICCV.2005.47
Multiview segmentation and tracking of dynamic occluding layers
Publisher: British Machine Vision Association
Date: 2005
DOI: 10.5244/C.19.91
Deep Reinforcement Learning for Detecting Breast Lesions from DCE-MRI
Publisher: Springer International Publishing
Date: 2019
Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Self-calibration of rotating and zooming cameras
Publisher: Springer Science and Business Media LLC
Date: 2001
Unsupervised learning of a scene-specific coarse gaze estimator
Publisher: IEEE
Date: 11-2011
3D tracking of multiple objects with identical appearance using RGB-D input
Publisher: IEEE
Date: 12-2015
DOI: 10.1109/3DV.2014.39
Steering without representation with the use of active fixation
Publisher: SAGE Publications
Date: 12-1997
DOI: 10.1068/P261519
Abstract: This paper demonstrates the use of active fixation on both fixed and moving fixation points to guide a robot vehicle by means of a steering rule which, at large distances, sets the steering angle directly proportional to the deviation of gaze direction from translation direction. Steering a motor vehicle around a winding but otherwise uncluttered road has been observed by Land and Lee to involve repeated periods of visual fixation upon the tangent point of the inside of each bend. We suggest that proportional rule devised for steering in the robotic ex le appears applicable to the observed human performance data, providing an alternative explanation to the quadratic rule proposed by Land and Lee.
The pathfinder image-guided surgical robot
Publisher: SAGE Publications
Date: 25-09-2010
Abstract: This paper first describes the workflow of the Pathfinder image-guided surgical robot that has been designed to replace the stereotactic frame in neurosurgery, and then details the calibration stages employed in order to achieve submillimetre positioning accuracy of a tool tip. The process uses non-linear parameter identification techniques in conjunction with some procedures for camera calibration, which exploit the fact that the camera is mounted to a calibrated robot arm that executes precise motions.
Planes, trains and automobiles - Autonomy for the modern robot
Publisher: IEEE
Date: 05-2010
GMS: Grid-Based Motion Statistics for Fast, Ultra-robust Feature Correspondence
Publisher: Springer Science and Business Media LLC
Date: 17-12-2019
DOI: 10.1007/S11263-019-01280-3
Abstract: Feature matching aims at generating correspondences across images, which is widely used in many computer vision tasks. Although considerable progress has been made on feature descriptors and fast matching for initial correspondence hypotheses, selecting good ones from them is still challenging and critical to the overall performance. More importantly, existing methods often take a long computational time, limiting their use in real-time applications. This paper attempts to separate true correspondences from false ones at high speed. We term the proposed method (GMS) grid-based motion Statistics, which incorporates the smoothness constraint into a statistic framework for separation and uses a grid-based implementation for fast calculation. GMS is robust to various challenging image changes, involving in viewpoint, scale, and rotation. It is also fast, e.g., take only 1 or 2 ms in a single CPU thread, even when 50 K correspondences are processed. This has important implications for real-time applications. What’s more, we show that incorporating GMS into the classic feature matching and epipolar geometry estimation pipeline can significantly boost the overall performance. Finally, we integrate GMS into the well-known ORB-SLAM system for monocular initialization, resulting in a significant improvement.
'Maximizing Rigidity' Revisited: A Convex Programming Approach for Generic 3D Shape Reconstruction from Multiple Perspective Views
Publisher: IEEE
Date: 10-2017
Model-Free Tracker for Multiple Objects Using Joint Appearance and Motion Inference
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Towards Context-Aware Interaction Recognition for Visual Relationship Detection
Publisher: IEEE
Date: 10-2017
DOI: 10.1109/ICCV.2017.71
On new view synthesis using multiview stereo
Publisher: British Machine Vision Association
Date: 2007
DOI: 10.5244/C.21.110
Visual localization under appearance change: filtering approaches
Publisher: Springer Science and Business Media LLC
Date: 17-09-2020
RSLAM: A system for large-scale mapping in constant-time using stereo
Publisher: Springer Science and Business Media LLC
Date: 11-06-2011
Erratum: Vast-scale outdoor navigation using adaptive relative bundle adjustment (International Journal of Robotics Research (2010) 29:8 (958-980))
Publisher: SAGE Publications
Date: 2011
STAR3D: Simultaneous tracking and reconstruction of 3D objects using RGB-D data
Publisher: IEEE
Date: 12-2013
Manhattan scene understanding using monocular, stereo, and 3D features
Publisher: IEEE
Date: 11-2011
Computer Vision – ACCV 2014: 12th Asian Conference on Computer Vision Singapore, Singapore, November 1–5, 2014 Revised Selected Papers, Part II
Publisher: Springer International Publishing
Date: 2015
Real-time joint semantic segmentation and depth estimation using asymmetric annotations
Publisher: IEEE
Date: 05-2019
Scalable Place Recognition Under Appearance Change for Autonomous Driving
Publisher: IEEE
Date: 10-2019
Deep Reinforcement Learning for Active Breast Lesion Detection from DCE-MRI
Publisher: Springer International Publishing
Date: 2017
Training quantized neural networks with a full-precision auxiliary module
Publisher: IEEE
Date: 06-2020
SG-VAE: Scene Grammar Variational Autoencoder to Generate New Indoor Scenes
Publisher: Springer International Publishing
Date: 2020
Depth based semantic scene completion with position importance aware loss
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Visual Question Answering with memory-augmented network
Publisher: IEEE
Date: 06-2018
Information-theoretic active scene exploration
Publisher: IEEE
Date: 06-2008
On the comparison of uncertainty criteria for active SLAM
Publisher: IEEE
Date: 05-2012
Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2016
Fast neural architecture search of compact semantic segmentation models via auxiliary cells
Publisher: IEEE
Date: 06-2019
Mean-shift visual tracking with NP-windows density estimates
Publisher: British Machine Vision Association
Date: 2010
DOI: 10.5244/C.24.103
Auto-Rectify Network for Unsupervised Indoor Depth Estimation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Transfer of Fixation Using Affine Structure: Extending the Analysis to Stereo
Publisher: Springer Science and Business Media LLC
Date: 1998
Plane measuring device
Publisher: Elsevier BV
Date: 06-1999
An image-to-map loop closing method for monocular SLAM
Publisher: IEEE
Date: 10-2011
Guiding visual surveillance by tracking human attention
Publisher: British Machine Vision Association
Date: 2009
DOI: 10.5244/C.23.14
Colour invariant head pose classification in low resolution video
Publisher: British Machine Vision Association
Date: 2008
DOI: 10.5244/C.22.49
AffordanceNet: an end-to-end deep learning approach for object affordance detection
Publisher: IEEE
Date: 05-2018
Scaling CNNs for High Resolution Volumetric Reconstruction from a Single Image
Publisher: IEEE
Date: 10-2018
Multiview segmentation and tracking of dynamic occluding layers
Publisher: Elsevier BV
Date: 06-2010
Articulated body motion capture by stochastic search
Publisher: Springer Science and Business Media LLC
Date: 02-2005
A hybrid SLAM representation for dynamic marine environments
Publisher: IEEE
Date: 05-2010
Direct semi-dense SLAM for rolling shutter cameras
Publisher: IEEE
Date: 05-2016
Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction
Publisher: IEEE
Date: 02-2018
Learn to Predict Sets Using Feed-Forward Neural Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
A comparison of loop closing techniques in monocular SLAM
Publisher: Elsevier BV
Date: 12-2009
Real-Time 3D Tracking and Reconstruction on Mobile Phones
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2015
A discrete-time attitude observer on SO(3) for vision and GPS fusion
Publisher: IEEE
Date: 05-2017
Hybrid Inference Optimization for robust pose graph estimation
Publisher: IEEE
Date: 09-2014
Cartman: The low-cost Cartesian manipulator that won the Amazon Robotics Challenge
Publisher: IEEE
Date: 05-2018
Real-time Image Smoothing via Iterative Least Squares
Publisher: Association for Computing Machinery (ACM)
Date: 06-06-2020
DOI: 10.1145/3388887
Abstract: Edge-preserving image smoothing is a fundamental procedure for many computer vision and graphic applications. There is a tradeoff between the smoothing quality and the processing speed: the high smoothing quality usually requires a high computational cost, which leads to the low processing speed. In this article, we propose a new global optimization based method, named iterative least squares (ILS), for efficient edge-preserving image smoothing. Our approach can produce high-quality results but at a much lower computational cost. Comprehensive experiments demonstrate that the proposed method can produce results with little visible artifacts. Moreover, the computation of ILS can be highly parallel, which can be easily accelerated through either multi-thread computing or the GPU hardware. With the acceleration of a GTX 1080 GPU, it is able to process images of 1080p resolution (1920 × 1080) at the rate of 20fps for color images and 47fps for gray images. In addition, the ILS is flexible and can be modified to handle more applications that require different smoothing properties. Experimental results of several applications show the effectiveness and efficiency of the proposed method. The code is available at liusjtu/Real-time-Image-Smoothing-via-Iterative-Least-Squares.
Deep Object Tracking with Shrinkage Loss
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Drones count wildlife more accurately and precisely than humans
Publisher: Wiley
Date: 13-02-2018
Architecture search of dynamic cells for semantic video segmentation
Publisher: IEEE
Date: 03-2020
Bayesian semantic instance segmentation in open set world
Publisher: Springer International Publishing
Date: 2018
Duality, rigidity and planar parallax
Publisher: Springer Berlin Heidelberg
Date: 1998
DOI: 10.1007/BFB0054783
Towards effective low-bitwidth convolutional neural networks
Publisher: IEEE
Date: 06-2018
Efficient new-view synthesis using pairwise dictionary priors
Publisher: IEEE
Date: 06-2007
Camera relocalization by exploiting multi-view constraints for scene coordinates regression
Publisher: IEEE
Date: 10-2019
Socially and Contextually Aware Human Motion and Pose Forecasting
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2020
Automatic relocalisation for a single-camera simultaneous localisation and mapping system
Publisher: IEEE
Date: 04-2007
Probabilistic parameter selection for learning scene structure from video
Publisher: British Machine Vision Association
Date: 2008
DOI: 10.5244/C.22.32
RefineNet: multi-path refinement networks for dense prediction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Template-Based Automatic Search of Compact Semantic Segmentation Architectures.
Publisher: IEEE
Date: 03-2019
Multi-modal cycle-consistent generalized zero-shot learning
Publisher: Springer International Publishing
Date: 2018
MonoSLAM: Real-time single camera SLAM
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2007
Bootstrapping the performance of webly supervised semantic segmentation
Publisher: IEEE
Date: 06-2018
Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments
Publisher: IEEE
Date: 06-2018
Seeing behind Things: Extending Semantic Segmentation to Occluded Regions
Publisher: IEEE
Date: 11-2019
Cognitive active vision for human identification
Publisher: IEEE
Date: 05-2012
A branch-and-bound algorithm for checkerboard extraction in camera-laser calibration
Publisher: IEEE
Date: 05-2017
Real-Time Tracking of Single and Multiple Objects from Depth-Colour Imagery Using 3D Signed Distance Functions
Publisher: Springer Science and Business Media LLC
Date: 11-01-2017
Effective Training of Convolutional Neural Networks With Low-Bitwidth Weights and Activations
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2022
3D hand tracking for human computer interaction
Publisher: Elsevier BV
Date: 03-2012
How Trustworthy are Performance Evaluations for Basic Vision Tasks?
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
NeuRoRA: Neural Robust Rotation Averaging
Publisher: Springer International Publishing
Date: 2020
Multi-scale dense networks for deep high dynamic range imaging
Publisher: IEEE
Date: 2019
Probabilistic surveillance with multiple active cameras
Publisher: IEEE
Date: 05-2010
A general method for human activity recognition in video
Publisher: Elsevier BV
Date: 11-2006
An evaluation of shape descriptors for image retrieval in Human Pose Estimation
Publisher: British Machine Vision Association
Date: 2007
DOI: 10.5244/C.21.65
Augmentation Network for Generalised Zero-Shot Learning
Publisher: Springer International Publishing
Date: 2021
A modular head/eye platform for real-time reactive vision
Publisher: Elsevier BV
Date: 08-1993
SPRINT: Subgraph Place Recognition for INtelligent Transportation
Publisher: IEEE
Date: 05-2020
Multi-Object Model-Free Tracking with Joint Appearance and Motion Inference
Publisher: IEEE
Date: 11-2017
Modeling and generating complex motion blur for real-time tracking
Publisher: IEEE
Date: 06-2008
Growing semantically meaningful models for visual SLAM
Publisher: IEEE
Date: 06-2010
Related Organisations
University Of Oxford
Location: United Kingdom of Great Britain and Northern Ireland
Related Funding Activities
Linkage Projects - Grant ID: LP130101064
Start Date: 07-2013
End Date: 12-2017
Amount: $150,000.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP220102398
Start Date: 10-2022
End Date: 09-2025
Amount: $515,000.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP200102427
Start Date: 08-2020
End Date: 12-2024
Amount: $450,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP200200881
Start Date: 08-2021
End Date: 02-2025
Amount: $643,565.00
Funder: Australian Research Council
View Funded ActivityAustralian Laureate Fellowships - Grant ID: FL130100102
Start Date: 10-2013
End Date: 03-2020
Amount: $3,179,946.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP130104413
Start Date: 2013
End Date: 12-2016
Amount: $358,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Infrastructure, Equipment And Facilities - Grant ID: LE160100090
Start Date: 04-2016
End Date: 12-2017
Amount: $250,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Infrastructure, Equipment And Facilities - Grant ID: LE190100080
Start Date: 2019
End Date: 12-2019
Amount: $726,921.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP130100154
Start Date: 01-2014
End Date: 12-2017
Amount: $345,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Infrastructure, Equipment And Facilities - Grant ID: LE130100156
Start Date: 2013
End Date: 12-2013
Amount: $210,000.00
Funder: Australian Research Council
View Funded ActivityARC Centres Of Excellence - Grant ID: CE140100016
Start Date: 07-2014
End Date: 03-2021
Amount: $19,000,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP140100946
Start Date: 2015
End Date: 06-2018
Amount: $240,000.00
Funder: Australian Research Council
View Funded Activity