Vision & Intelligence Group
Vision & Intelligence Group
News
Events
Projects
People
Research Direction
Publications
Contact
2
Integrating part-object relationship and contrast for camouflaged object detection
Object detectors that solely rely on image contrast are struggling to detect camouflaged objects in images because of the high …
Yi Liu
,
Dingwen Zhang
PDF
Cite
Structured Attention Composition for Temporal Action Localization
Temporal action localization aims at localizing action instances from untrimmed videos. Existing works have designed various effective …
Le Yang
,
Dingwen Zhang
,
Junwei Han
PDF
Cite
Onfocus detection: identifying individual-camera eye contact from unconstrained images
Onfocus detection aims at identifying whether the focus of the individual captured by a camera is on the camera or not. Based on the …
Dingwen Zhang
,
Bo Wang
,
Gerong Wang
,
Qiang Zhang
PDF
Cite
Learning Self-supervised Low-Rank Network for Single-Stage Weakly and Semi-supervised Semantic Segmentation
Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic …
Junwen Pan
,
Dingwen Zhang
,
Junwei Han
PDF
Cite
Exploring rich intermediate representations for reconstructing 3D shapes from 2D images
Recovering 3D voxelized shapes with fine details from single-view 2D images is an extremely challenging and ill-conditioned problem. …
Yang Yang
,
Junwei Han
,
Dingwen Zhang
PDF
Cite
Htd: Heterogeneous task decoupling for two-stage object detection
Decoupling the sibling head has recently shown great potential in relieving the inherent task-misalignment problem in two-stage object …
Wuyang Li
,
Zhen Chen
,
Baopu Li
,
Dingwen Zhang
PDF
Cite
CLRNet: Component-Level Refinement Network for Deep Face Parsing
Face parsing aims to assign pixel-wise semantic labels to different facial components (e.g., hair, brows, and lips) in given face …
Peiliang Huang
,
Dingwen Zhang
,
Junwei Han
PDF
Cite
Scribble-Supervised Video Object Segmentation
Recently, video object segmentation has received great attention in the computer vision community. Most of the existing methods heavily …
Peiliang Huang
,
Dingwen Zhang
,
Junwei Han
PDF
Cite
Equivalent classification mapping for weakly supervised temporal action localization
Weakly supervised temporal action localization is a newly emerging yet widely studied topic in recent years. The existing methods can …
Le Yang
,
Dingwen Zhang
,
Junwei Han
PDF
Cite
Learning Object Detectors with Semi-Annotated Weak Labels
For alleviating the human labor associated with annotating the training data for learning object detectors, recent research has focused …
Guoyu Guang
,
Dingwen Zhang
,
Junwei Han
PDF
Cite
»
Cite
×