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 26–48 of 48 papers

TitleStatusHype
Video Salient Object Detection via Contrastive Features and Attention Modules—0
Guidance and Teaching Network for Video Salient Object Detection—0
Confidence-guided Adaptive Gate and Dual Differential Enhancement for Video Salient Object Detection—0
Video Salient Object Detection via Adaptive Local-Global RefinementCode0
Fast Video Salient Object Detection via Spatiotemporal Knowledge Distillation—0
A Novel Video Salient Object Detection Method via Semi-supervised Motion Quality PerceptionCode0
TENet: Triple Excitation Network for Video Salient Object Detection—0
Motion Guided Attention for Video Salient Object DetectionCode0
Semi-Supervised Video Salient Object Detection Using Pseudo-LabelsCode0
Time Masking: Leveraging Temporal Information in Spoken Dialogue Systems—0
Shifting More Attention to Video Salient Object DetectionCode0
Salient Object Detection in Video using Deep Non-Local Neural Networks—0
Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation—0
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection—0
Sequential Clique Optimization for Video Object Segmentation—0
Unsupervised Video Object Segmentation with Motion-based Bilateral Networks—0
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection—0
Video Salient Object Detection Using Spatiotemporal Deep Features—0
Video Salient Object Detection via Fully Convolutional Networks—0
Real-Time Salient Object Detection With a Minimum Spanning TreeCode0
Minimum Barrier Salient Object Detection at 80 FPS—0
Saliency-Aware Geodesic Video Object Segmentation—0
Time-Mapping Using Space-Time Saliency—0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.