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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 147 papers

TitleStatusHype
THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation—0
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 Segmentation—0
SAM 2: Segment Anything in Images and VideosCode11
Global Motion Understanding in Large-Scale Video Object Segmentation—0
Spatial-Temporal Multi-level Association for Video Object Segmentation—0
Efficient Video Object Segmentation via Modulated Cross-Attention MemoryCode2
Video Object Segmentation with Dynamic Query ModulationCode1
Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment AnythingCode1
Lester: rotoscope animation through video object segmentation and trackingCode1
ODTrack: Online Dense Temporal Token Learning for Visual TrackingCode2
SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolution—0
Putting the Object Back into Video Object SegmentationCode3
Sub-token ViT Embedding via Stochastic Resonance TransformersCode0
Memory-Efficient Continual Learning Object Segmentation for Long Video—0
Tracking Anything with Decoupled Video SegmentationCode3
XMem++: Production-level Video Segmentation From Few Annotated FramesCode2
Tracking Anything in High QualityCode2
Hierarchical Spatiotemporal Transformers for Video Object Segmentation—0
ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: Semi-Supervised Video Object Segmentation—0
TrickVOS: A Bag of Tricks for Video Object Segmentation—0
READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object SegmentationCode0
Video Object Segmentation in Panoptic Wild ScenesCode2
Robust and Efficient Memory Network for Video Object Segmentation—0
CLVOS23: A Long Video Object Segmentation Dataset for Continual LearningCode0
MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation—0
Flow-guided Semi-supervised Video Object Segmentation—0
Alignment Before Aggregation: Trajectory Memory Retrieval Network for Video Object Segmentation—0
Look Before You Match: Instance Understanding Matters in Video Object Segmentation—0
Learning to Learn Better for Video Object SegmentationCode1
Decoupling Features in Hierarchical Propagation for Video Object SegmentationCode2
Global Spectral Filter Memory Network for Video Object SegmentationCode1
Pixel-Level Equalized Matching for Video Object Segmentation—0
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationCode1
Per-Clip Video Object SegmentationCode1
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation—0
Region Aware Video Object Segmentation with Deep Motion Modeling—0
Learning Quality-aware Dynamic Memory for Video Object SegmentationCode1
Tackling Background Distraction in Video Object SegmentationCode1
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory ModelCode3
Towards Robust Video Object Segmentation with Adaptive Object CalibrationCode1
The Second Place Solution for The 4th Large-scale Video Object Segmentation Challenge--Track 3: Referring Video Object Segmentation—0
Collaborative Attention Memory Network for Video Object Segmentation—0
Recurrent Dynamic Embedding for Video Object SegmentationCode1
Boosting Video Object Segmentation based on Scale InconsistencyCode0
Adaptive Memory Management for Video Object SegmentationCode0
Scalable Video Object Segmentation with Identification MechanismCode2
MixFormer: End-to-End Tracking with Iterative Mixed AttentionCode2
Show:102550
← PrevPage 1 of 3Next →
All datasetsDAVIS 2017 (val)DAVIS 2016DAVIS-2017 (test-dev)YouTube-VOS 2018DAVIS (no YouTube-VOS training)YouTube-VOS 2019VOT2020MOSELong Video DatasetYouTubeDAVIS 2017BURST-test

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SAM2J&F90.7—Unverified
2Cutie+ (base)J&F90.5—Unverified
3ISVOS (BL30K, MS)J&F89.8—Unverified
4XMem (BL30K, MS)J&F89.5—Unverified
5ISVOS (MS)J&F88.6—Unverified
6ISVOS (BL30K)J&F88.2—Unverified
7XMem (MS)J&F88.2—Unverified
8Cutie+ (base, MEGA)J&F88.1—Unverified
9JIMDJ&F88.1—Unverified
10Cutie (base)J&F87.9—Unverified
#ModelMetricClaimedVerifiedStatus
1SwinB-AOST (L'=3, MS)J&F93—Unverified
2SwinB-AOTv2-L (MS)J&F93—Unverified
3SwinB-DeAOT-LJ&F92.9—Unverified
4XMem (MS)J&F92.7—Unverified
5SwinB-AOTv2-LJ&F92.4—Unverified
6SwinB-AOST (L'=3)J&F92.4—Unverified
7R50-DeAOT-LJ&F92.3—Unverified
8R50-AOST (L'=3)J&F92.1—Unverified
9QDMNJ&F92—Unverified
10DeAOT-LJ&F92—Unverified
#ModelMetricClaimedVerifiedStatus
1Cutie+ (base, MEGA)J&F88.1—Unverified
2Cutie (base, MEGA)J&F86.1—Unverified
3Cutie+ (base)J&F85.9—Unverified
4SwinB-AOST (L'=3, MS)J&F84.7—Unverified
5SwinB-AOTv2-LJ&F84.5—Unverified
6JIMD-R50J&F83.9—Unverified
7XMem (BL30K, MS)J&F83.7—Unverified
8DEVAJ&F83.2—Unverified
9XMem (MS)J&F83.1—Unverified
10SwinB-DeAOT-LJ&F82.8—Unverified