SOTAVerified

Video Salient Object Detection

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 )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 48 papers

TitleStatusHype
Transforming Static Images Using Generative Models for Video Salient Object Detection—0
UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection—0
Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation—0
Unsupervised Video Object Segmentation with Motion-based Bilateral Networks—0
Video Salient Object Detection Using Spatiotemporal Deep Features—0
Video Salient Object Detection via Contrastive Features and Attention Modules—0
Video Salient Object Detection via Fully Convolutional Networks—0
A Novel Long-term Iterative Mining Scheme for Video Salient Object Detection—0
Panoramic Video Salient Object Detection with Ambisonic Audio Guidance—0
PSNet: Parallel Symmetric Network for Video Salient Object Detection—0
Show:102550
← PrevPage 3 of 5Next →

No leaderboard results yet.