SOTAVerified

Video Segmentation

Papers

Showing 3140 of 388 papers

TitleStatusHype
MeViS: A Large-scale Benchmark for Video Segmentation with Motion ExpressionsCode2
Mask2Former for Video Instance SegmentationCode2
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language ModelsCode2
HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual PerceiverCode2
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor QueriesCode2
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any GranularityCode2
InstMove: Instance Motion for Object-centric Video SegmentationCode2
MemSAM: Taming Segment Anything Model for Echocardiography Video SegmentationCode2
A Survey on Deep Learning Technique for Video SegmentationCode1
Differentiable Soft-Masked AttentionCode1
Show:102550
← PrevPage 4 of 39Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GDHFAccuracy86.86Unverified