computer-vision-5
Video Salient Object Detection
3260 papers • 126 benchmarks • 313 datasets
Video salient object detection (VSOD) is significantly essential for understanding the underlying mechanism behind HVS during free-viewing in general and instrumental to a wide range of real-world applications, e.g., video segmentation, video captioning, video compression, autonomous driving, robotic interaction, weakly supervised attention. Besides its academic value and practical significance, VSOD presents great difficulties due to the challenges carried by video data (diverse motion patterns, occlusions, blur, large object deformations, etc.) and the inherent complexity of human visual attention behavior (i.e., selective attention allocation, attention shift) during dynamic scenes. Online benchmark: http://dpfan.net/davsod. ( Image credit: Shifting More Attention to Video Salient Object Detection, CVPR2019-Best Paper Finalist )
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in video-salient-object-detection-10
Trend
Dataset
Best Model
Actions
FBMS-59
FBMS-59
DAVIS-2016
DAVIS-2016
Libraries
iUse these libraries to find video-salient-object-detection-10 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
Motion Guided Attention for Video Salient Object Detection
Yizhou Yu, Guanbin Li, Haofeng Li, Guanqi Chen•Sun Sep 15 2019
A multi-task motion guided video salient object detection network, which learns to accomplish two sub-tasks using twoSub-networks, one sub-network for salient object Detection in still images and the other for motion saliency detection in optical flow images, which significantly outperforms existing state-of-the-art algorithms on a wide range of benchmarks.
198
