SOTAVerified

Semi-Supervised Video Object Segmentation

The semi-supervised scenario assumes the user inputs a full mask of the object(s) of interest in the first frame of a video sequence. Methods have to produce the segmentation mask for that object(s) in the subsequent frames.

Papers

Showing 110 of 147 papers

TitleStatusHype
THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation0
Exploring Enhanced Contextual Information for Video-Level Object TrackingCode2
A Distractor-Aware Memory for Visual Object Tracking with SAM2Code3
LiVOS: Light Video Object Segmentation with Gated Linear MatchingCode1
Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation0
SAM 2: Segment Anything in Images and VideosCode11
Global Motion Understanding in Large-Scale Video Object Segmentation0
Spatial-Temporal Multi-level Association for Video Object Segmentation0
Efficient Video Object Segmentation via Modulated Cross-Attention MemoryCode2
Video Object Segmentation with Dynamic Query ModulationCode1
Show:102550
← PrevPage 1 of 15Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Cutie+ (base, MEGA)Overall87.5Unverified
2XMem (BL30K, MS)Overall86.9Unverified
3XMem (MS)Overall86.7Unverified
4SwinB-AOTv2-L (all frames, MS)Overall86.5Unverified
5SwinB-DeAOT-LOverall86.2Unverified
6XMem (BL30K)Overall86.1Unverified
7R50-DeAOT-LOverall86Unverified
8SwinB-AOTv2-L (all frames)Overall85.8Unverified
9XMemOverall85.7Unverified
10R50-AOT-L (all frames)Overall85.5Unverified