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 2650 of 147 papers

TitleStatusHype
Towards Robust Video Object Segmentation with Adaptive Object CalibrationCode1
Recurrent Dynamic Embedding for Video Object SegmentationCode1
Reliable Propagation-Correction Modulation for Video Object SegmentationCode1
FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical FlowCode1
Dense Unsupervised Learning for Video SegmentationCode1
Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic PerspectiveCode1
Pixel-Level Bijective Matching for Video Object SegmentationCode1
Hierarchical Memory Matching Network for Video Object SegmentationCode1
Joint Inductive and Transductive Learning for Video Object SegmentationCode1
Self-Supervised Video Object Segmentation by Motion-Aware Mask PropagationCode1
Accelerating Video Object Segmentation with Compressed VideoCode1
Do Different Tracking Tasks Require Different Appearance Models?Code1
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object SegmentationCode1
Associating Objects with Transformers for Video Object SegmentationCode1
TransVOS: Video Object Segmentation with TransformersCode1
Efficient Regional Memory Network for Video Object SegmentationCode1
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware FusionCode1
SwiftNet: Real-time Video Object SegmentationCode1
SSTVOS: Sparse Spatiotemporal Transformers for Video Object SegmentationCode1
Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object SegmentationCode1
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box EstimationCode1
Make One-Shot Video Object Segmentation Efficient AgainCode1
TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency LossCode1
Delving into the Cyclic Mechanism in Semi-supervised Video Object SegmentationCode1
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region RefinementCode1
Show:102550
← PrevPage 2 of 6Next →

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
8Cutie+ (base, MEGA)J&F88.1Unverified
9JIMDJ&F88.1Unverified
10Cutie (base)J&F87.9Unverified
#ModelMetricClaimedVerifiedStatus
1SwinB-AOST (L'=3, MS)J&F93Unverified
2SwinB-AOTv2-L (MS)J&F93Unverified
3SwinB-DeAOT-LJ&F92.9Unverified
4XMem (MS)J&F92.7Unverified
5SwinB-AOTv2-LJ&F92.4Unverified
6SwinB-AOST (L'=3)J&F92.4Unverified
7R50-DeAOT-LJ&F92.3Unverified
8R50-AOST (L'=3)J&F92.1Unverified
9QDMNJ&F92Unverified
10DeAOT-LJ&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