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 150 of 147 papers

TitleStatusHype
SAM 2: Segment Anything in Images and VideosCode11
A Distractor-Aware Memory for Visual Object Tracking with SAM2Code3
Putting the Object Back into Video Object SegmentationCode3
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory ModelCode3
Tracking Anything with Decoupled Video SegmentationCode3
Fast Online Object Tracking and Segmentation: A Unifying ApproachCode2
XMem++: Production-level Video Segmentation From Few Annotated FramesCode2
Decoupling Features in Hierarchical Propagation for Video Object SegmentationCode2
MixFormer: End-to-End Tracking with Iterative Mixed AttentionCode2
Tracking Anything in High QualityCode2
ODTrack: Online Dense Temporal Token Learning for Visual TrackingCode2
Efficient Video Object Segmentation via Modulated Cross-Attention MemoryCode2
Scalable Video Object Segmentation with Identification MechanismCode2
Exploring Enhanced Contextual Information for Video-Level Object TrackingCode2
Video Object Segmentation in Panoptic Wild ScenesCode2
A Transductive Approach for Video Object SegmentationCode1
Associating Objects with Transformers for Video Object SegmentationCode1
Learning to Learn Better for Video Object SegmentationCode1
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object SegmentationCode1
Reliable Propagation-Correction Modulation for Video Object SegmentationCode1
Self-Supervised Video Object Segmentation by Motion-Aware Mask PropagationCode1
SSTVOS: Sparse Spatiotemporal Transformers for Video Object SegmentationCode1
Learning Quality-aware Dynamic Memory for Video Object SegmentationCode1
Recurrent Dynamic Embedding for Video Object SegmentationCode1
Per-Clip Video Object SegmentationCode1
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background IntegrationCode1
Fast Template Matching and Update for Video Object Tracking and SegmentationCode1
Pixel-Level Bijective Matching for Video Object SegmentationCode1
Delving into the Cyclic Mechanism in Semi-supervised Video Object SegmentationCode1
Dense Unsupervised Learning for Video SegmentationCode1
MAST: A Memory-Augmented Self-supervised TrackerCode1
FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical FlowCode1
Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic PerspectiveCode1
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box EstimationCode1
Accelerating Video Object Segmentation with Compressed VideoCode1
Lester: rotoscope animation through video object segmentation and trackingCode1
Hierarchical Memory Matching Network for Video Object SegmentationCode1
Learning What to Learn for Video Object SegmentationCode1
LiVOS: Light Video Object Segmentation with Gated Linear MatchingCode1
Efficient Regional Memory Network for Video Object SegmentationCode1
Kernelized Memory Network for Video Object SegmentationCode1
Do Different Tracking Tasks Require Different Appearance Models?Code1
Joint Inductive and Transductive Learning for Video Object SegmentationCode1
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware FusionCode1
Fast Video Object Segmentation using the Global Context ModuleCode1
One-Shot Video Object SegmentationCode1
Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object SegmentationCode1
Learning Fast and Robust Target Models for Video Object SegmentationCode1
Collaborative Video Object Segmentation by Foreground-Background IntegrationCode1
Directional Deep Embedding and Appearance Learning for Fast Video Object SegmentationCode1
Show:102550
← PrevPage 1 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SAM2J&F90.7Unverified
2Cutie+ (base)J&F90.5Unverified
3ISVOS (BL30K, MS)J&F89.8Unverified
4XMem (BL30K, MS)J&F89.5Unverified
5ISVOS (MS)J&F88.6Unverified
6ISVOS (BL30K)J&F88.2Unverified
7XMem (MS)J&F88.2Unverified
8JIMDJ&F88.1Unverified
9Cutie+ (base, MEGA)J&F88.1Unverified
10Cutie (base)J&F87.9Unverified
#ModelMetricClaimedVerifiedStatus
1SwinB-AOTv2-L (MS)J&F93Unverified
2SwinB-AOST (L'=3, MS)J&F93Unverified
3SwinB-DeAOT-LJ&F92.9Unverified
4XMem (MS)J&F92.7Unverified
5SwinB-AOST (L'=3)J&F92.4Unverified
6SwinB-AOTv2-LJ&F92.4Unverified
7R50-DeAOT-LJ&F92.3Unverified
8R50-AOST (L'=3)J&F92.1Unverified
9SwinB-AOT-LJ&F92Unverified
10XMem (BL30K)J&F92Unverified
#ModelMetricClaimedVerifiedStatus
1Cutie+ (base, MEGA)J&F88.1Unverified
2Cutie (base, MEGA)J&F86.1Unverified
3Cutie+ (base)J&F85.9Unverified
4SwinB-AOST (L'=3, MS)J&F84.7Unverified
5SwinB-AOTv2-LJ&F84.5Unverified
6JIMD-R50J&F83.9Unverified
7XMem (BL30K, MS)J&F83.7Unverified
8DEVAJ&F83.2Unverified
9XMem (MS)J&F83.1Unverified
10SwinB-DeAOT-LJ&F82.8Unverified