Vision & Intelligence Group
Vision & Intelligence Group
News
Events
Projects
People
Publications
Contact
Dingwen Zhang
Latest
A Memory-based Robust region feature synthesizer for zero-shot object detection
Uncertainty Modeling for Gaze Estimation
Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching
Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching
GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding
Integrating part-object relationship and contrast for camouflaged object detection
Cross-Modality High-Frequency Transformer for MR Image Super-Resolution.
Colar: Effective and efficient online action detection by consulting exemplars
Structured Attention Composition for Temporal Action Localization
Onfocus detection: identifying individual-camera eye contact from unconstrained images
Learning Self-supervised Low-Rank Network for Single-Stage Weakly and Semi-supervised Semantic Segmentation
Exploring rich intermediate representations for reconstructing 3D shapes from 2D images
Incremental Cross-View Mutual Distillation for Self-Supervised Medical CT Synthesis
Robust Region Feature Synthesizer for Zero-Shot Object Detection
Htd: Heterogeneous task decoupling for two-stage object detection
HUMA21: 2nd International Workshop on Human-centric Multimedia Analysis
CLRNet: Component-Level Refinement Network for Deep Face Parsing
Scribble-Supervised Video Object Segmentation
Equivalent classification mapping for weakly supervised temporal action localization
Strengthen Learning Tolerance for Weakly Supervised Object Localization
Learning Object Detectors with Semi-Annotated Weak Labels
Revisiting anchor mechanisms for temporal action localization
Revisiting anchor mechanisms for temporal action localization
Salient Object Detection via Integrity Learning
Segmentation in weakly labeled videos via a semantic ranking and optical warping network.
Background-click supervision for temporal action localization
Reinforcement cutting-agent learning for video object segmentation
PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos
Spftn: A self-paced fine-tuning network for segmenting objects in weakly labelled videos
Cite
×