Vision & Intelligence Group
Vision & Intelligence Group
News
Events
Projects
People
Research Direction
Publications
Contact
2
Revisiting anchor mechanisms for temporal action localization
Most of the current action localization methods follow an anchor-based pipeline depicting action instances by pre-defined anchors, …
Le Yang
,
Dingwen Zhang
,
Junwei Han
PDF
Cite
Revisiting anchor mechanisms for temporal action localization
Most of the current action localization methods follow an anchor-based pipeline depicting action instances by pre-defined anchors, …
Le Yang
,
Dingwen Zhang
,
Junwei Han
PDF
Cite
Salient Object Detection via Integrity Learning
Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the …
Mingchen Zhuge
,
Deng-Ping Fan
,
Nian Liu
,
Dingwen Zhang
PDF
Cite
Segmentation in weakly labeled videos via a semantic ranking and optical warping network.
Weakly supervised video object segmentation (WSVOS) focuses on generating pixel-level object masks for videos only tagged with class …
Dingwen Zhang
,
Le Yang
,
Junwei Han
PDF
Cite
Background-click supervision for temporal action localization
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a …
Le Yang
,
Junwei Han
,
Dingwen Zhang
PDF
Cite
«
Cite
×