2025
Few-shot Personalized Scanpath Prediction.
CoRR, April, 2025
2024
Driver Attention Tracking and Analysis.
CoRR, 2024
Detecting Omissions in Geographic Maps through Computer Vision.
Proceedings of the International Conference on Multimedia Analysis and Pattern Recognition, 2024
Characterizing Learners' Complex Attentional States During Online Multimedia Learning Using Eye-tracking, Egocentric Camera, Webcam, and Retrospective recalls.
Proceedings of the 2024 Symposium on Eye Tracking Research and Applications, 2024
Look Hear: Gaze Prediction for Speech-Directed Human Attention.
Proceedings of the Computer Vision - ECCV 2024, 2024
Diffusion-Refined VQA Annotations for Semi-supervised Gaze Following.
Proceedings of the Computer Vision - ECCV 2024, 2024
Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
HOIST-Former: Hand-Held Objects Identification, Segmentation, and Tracking in the Wild.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
HanDiffuser: Text-to-Image Generation with Realistic Hand Appearances.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Error Detection in Egocentric Procedural Task Videos.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Unifying Top-Down and Bottom-Up Scanpath Prediction Using Transformers.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
2023
Predicting Human Attention using Computational Attention.
CoRR, 2023
Patch-level Gaze Distribution Prediction for Gaze Following.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
Interactive Class-Agnostic Object Counting.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation.
Proceedings of the Findings of the Association for Computational Linguistics: EACL 2023, 2023
Object Detection with Self-Supervised Scene Adaptation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
2022
Distilling Knowledge from Language Models for Video-based Action Anticipation.
CoRR, 2022
Target-Absent Human Attention.
Proceedings of the Computer Vision - ECCV 2022, 2022
Few-Shot Object Counting and Detection.
Proceedings of the Computer Vision - ECCV 2022, 2022
Vicinal Counting Networks.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022
Whose Hands are These? Hand Detection and Hand-Body Association in the Wild.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Forward Propagation, Backward Regression, and Pose Association for Hand Tracking in the Wild.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Characterizing Target-absent Human Attention.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022
Self-supervised Learning with Multi-view Rendering for 3D Point Cloud Analysis.
Proceedings of the Computer Vision - ACCV 2022, 2022
From Within to Between: Knowledge Distillation for Cross Modality Retrieval.
Proceedings of the Computer Vision - ACCV 2022, 2022
Exemplar Free Class Agnostic Counting.
Proceedings of the Computer Vision - ACCV 2022, 2022
2021
Interactive Visual Study of Multiple Attributes Learning Model of X-Ray Scattering Images.
IEEE Trans. Vis. Comput. Graph., 2021
Sequence-to-Segments Networks for Detecting Segments in Videos.
IEEE Trans. Pattern Anal. Mach. Intell., 2021
Large Scale Shadow Annotation and Detection Using Lazy Annotation and Stacked CNNs.
IEEE Trans. Pattern Anal. Mach. Intell., 2021
Explore Image Deblurring via Blur Kernel Space.
CoRR, 2021
FineNet: Frame Interpolation and Enhancement for Face Video Deblurring.
CoRR, 2021
Supervoxel Attention Graphs for Long-Range Video Modeling.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2021
Adaptive Streaming of 360-Degree Videos with Reinforcement Learning.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2021
Progressive Knowledge Distillation For Early Action Recognition.
Proceedings of the 2021 IEEE International Conference on Image Processing, 2021
Knowledge Distillation for Human Action Anticipation.
Proceedings of the 2021 IEEE International Conference on Image Processing, 2021
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021
Explore Image Deblurring via Encoded Blur Kernel Space.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Learning To Count Everything.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Lipstick Ain't Enough: Beyond Color Matching for In-the-Wild Makeup Transfer.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Dictionary-Guided Scene Text Recognition.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Progressive Semantic Segmentation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Exemplar-Based Early Event Prediction in Video.
Proceedings of the 32nd British Machine Vision Conference 2021, 2021
Localization in the Crowd with Topological Constraints.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021
2020
A Study of Human Gaze Behavior During Visual Crowd Counting.
CoRR, 2020
Predicting Goal-directed Attention Control Using Inverse-Reinforcement Learning.
CoRR, 2020
Detecting Hands and Recognizing Physical Contact in the Wild.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Distribution Matching for Crowd Counting.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Structural and Functional Decomposition for Personality Image Captioning in a Communication Game.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020
Predicting Goal-Directed Human Attention Using Inverse Reinforcement Learning.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Learning Visual Emotion Representations From Web Data.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Active Vision for Early Recognition of Human Actions.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Attentive Action and Context Factorization.
Proceedings of the 31st British Machine Vision Conference 2020, 2020
Uncertainty Estimation and Sample Selection for Crowd Counting.
Proceedings of the Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30, 2020
2019
Visual Understanding of Multiple Attributes Learning Model of X-Ray Scattering Images.
CoRR, 2019
Back to the Future: Knowledge Distillation for Human Action Anticipation.
CoRR, 2019
Crowd Transformer Network.
CoRR, 2019
BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation.
CoRR, 2019
Contextual Attention for Hand Detection in the Wild.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019
Benchmarking Gaze Prediction for Categorical Visual Search.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019
GIF2Video: Color Dequantization and Temporal Interpolation of GIF Images.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
WorkingHands: A Hand-Tool Assembly Dataset for Image Segmentation and Activity Mining.
Proceedings of the 30th British Machine Vision Conference 2019, 2019
2018
Latent Bi-Constraint SVM for Video-Based Object Recognition.
IEEE Trans. Circuits Syst. Video Technol., 2018
Leave-One-Out Kernel Optimization for Shadow Detection and Removal.
IEEE Trans. Pattern Anal. Mach. Intell., 2018
Back to the beginning: Starting point detection for early recognition of ongoing human actions.
Comput. Vis. Image Underst., 2018
Fake Sentence Detection as a Training Task for Sentence Encoding.
CoRR, 2018
Sequence-to-Segment Networks for Segment Detection.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
Eigen-Evolution Dense Trajectory Descriptors.
Proceedings of the 13th IEEE International Conference on Automatic Face & Gesture Recognition, 2018
Predicting Body Movement and Recognizing Actions: An Integrated Framework for Mutual Benefits.
Proceedings of the 13th IEEE International Conference on Automatic Face & Gesture Recognition, 2018
Iterative Crowd Counting.
Proceedings of the Computer Vision - ECCV 2018, 2018
A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation.
Proceedings of the Computer Vision - ECCV 2018, 2018
Good View Hunting: Learning Photo Composition From Dense View Pairs.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018
Pulling Actions out of Context: Explicit Separation for Effective Combination.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018
2017
A+D-Net: Shadow Detection with Adversarial Shadow Attenuation.
CoRR, 2017
Eigen Evolution Pooling for Human Action Recognition.
CoRR, 2017
Evolution-Preserving Dense Trajectory Descriptors.
CoRR, 2017
X-Ray Scattering Image Classification Using Deep Learning.
Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision, 2017
Shadow Detection with Conditional Generative Adversarial Networks.
Proceedings of the IEEE International Conference on Computer Vision, 2017
Large-scale Continual Road Inspection: Visual Infrastructure Assessment in the Wild.
Proceedings of the British Machine Vision Conference 2017, 2017
2016
Learned Region Sparsity and Diversity Also Predicts Visual Attention.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016
Large-Scale Training of Shadow Detectors with Noisily-Annotated Shadow Examples.
Proceedings of the Computer Vision - ECCV 2016, 2016
Region Ranking SVM for Image Classification.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
Improving Human Action Recognition by Non-action Classification.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
Noisy Label Recovery for Shadow Detection in Unfamiliar Domains.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
2015
Leave-One-Out Kernel Optimization for Shadow Detection.
Proceedings of the 2015 IEEE International Conference on Computer Vision, 2015
Recognizing cultural events in images: A study of image categorization models.
Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2015
2014
Learning discriminative localization from weakly labeled data.
Pattern Recognit., 2014
Max-Margin Early Event Detectors.
Int. J. Comput. Vis., 2014
Talking Heads: Detecting Humans and Recognizing Their Interactions.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014
Action Recognition From Weak Alignment of Body Parts.
Proceedings of the British Machine Vision Conference, 2014
Regularized Max Pooling for Image Categorization.
Proceedings of the British Machine Vision Conference, 2014
Improving Human Action Recognition Using Score Distribution and Ranking.
Proceedings of the Computer Vision - ACCV 2014, 2014
Thread-Safe: Towards Recognizing Human Actions Across Shot Boundaries.
Proceedings of the Computer Vision - ACCV 2014, 2014
2013
Discriminative Sub-categorization.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013
2012
Segment-based SVMs for Time Series Analysis.
PhD thesis, 2012
Maximum Margin Temporal Clustering.
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012
2011
Joint segmentation and classification of human actions in video.
Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, 2011
2010
Optimal feature selection for support vector machines.
Pattern Recognit., 2010
Metric Learning for Image Alignment.
Int. J. Comput. Vis., 2010
Action unit detection with segment-based SVMs.
Proceedings of the Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, 2010
2009
Weakly supervised discriminative localization and classification: a joint learning process.
Proceedings of the IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27, 2009
Detecting depression from facial actions and vocal prosody.
Proceedings of the Affective Computing and Intelligent Interaction, 2009
2008
Comput. Graph. Forum, 2008
Robust Kernel Principal Component Analysis.
Proceedings of the Advances in Neural Information Processing Systems 21, 2008
Learning image alignment without local minima for face detection and tracking.
Proceedings of the 8th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2008), 2008
Facial feature detection with optimal pixel reduction SVM.
Proceedings of the 8th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2008), 2008
Parameterized Kernel Principal Component Analysis: Theory and applications to supervised and unsupervised image alignment.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008
Local minima free Parameterized Appearance Models.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008
2006
A Flexible Framework for SharedPlans.
Proceedings of the AI 2006: Advances in Artificial Intelligence, 2006
2003
DRT: A Tool for Design Recovery of Interactive Graphical Applications.
Proceedings of the 25th International Conference on Software Engineering, 2003