SOTAVerified

Video Object Segmentation

Video object segmentation is a binary labeling problem aiming to separate foreground object(s) from the background region of a video.

For leaderboards please refer to the different subtasks.

Papers

Showing 26–50 of 551 papers

TitleStatusHype
Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object SegmentationCode2
VideoMolmo: Spatio-Temporal Grounding Meets PointingCode2
UniRef++: Segment Every Reference Object in Spatial and Temporal SpacesCode2
VLT: Vision-Language Transformer and Query Generation for Referring SegmentationCode2
Efficient Video Object Segmentation via Modulated Cross-Attention MemoryCode2
Tracking Anything in High QualityCode2
Video Object Segmentation in Panoptic Wild ScenesCode2
Scalable Video Object Segmentation with Identification MechanismCode2
One Token to Seg Them All: Language Instructed Reasoning Segmentation in VideosCode2
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System CollaborationCode2
Language as Queries for Referring Video Object SegmentationCode2
In Defense of Online Models for Video Instance SegmentationCode2
LVOS: A Benchmark for Large-scale Long-term Video Object SegmentationCode2
HyperSeg: Towards Universal Visual Segmentation with Large Language ModelCode2
GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video SegmentationCode2
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet VideosCode2
MeViS: A Large-scale Benchmark for Video Segmentation with Motion ExpressionsCode2
Fast Online Object Tracking and Segmentation: A Unifying ApproachCode2
Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object SegmentationCode2
Decoupling Features in Hierarchical Propagation for Video Object SegmentationCode2
Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object SegmentationCode2
MOSE: A New Dataset for Video Object Segmentation in Complex ScenesCode2
A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic InformationCode1
Contrastive Transformation for Self-supervised Correspondence LearningCode1
Emerging Properties in Self-Supervised Vision TransformersCode1
Show:102550
← PrevPage 2 of 23Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AOC-MF (val)F-Score94.7—Unverified
2ISVOS (BL30K, MS)J&F93.4—Unverified
3XMem (BL30K, MS)J&F93.3—Unverified
4BATMAN (val)J&F92.5—Unverified
5STCN (val)J&F91.6—Unverified
6XMemJ&F91.5—Unverified
7MobileVOS (val)J&F91.4—Unverified
8AOT (val)J&F91.1—Unverified
9LCM (val)J&F90.7—Unverified
10RPCMVOS (val)J&F90.6—Unverified
#ModelMetricClaimedVerifiedStatus
1XMem (BLK30K, MS)Mean Jaccard & F-Measure89.5—Unverified
2LCMF-measure86.5—Unverified
3XMemMean Jaccard & F-Measure86.2—Unverified
4BATMANMean Jaccard & F-Measure86.2—Unverified
5STCNMean Jaccard & F-Measure85.4—Unverified
6AOTMean Jaccard & F-Measure84.9—Unverified
7STMF-measure84.3—Unverified
8TransVOSMean Jaccard & F-Measure83.9—Unverified
9RPCMVOSMean Jaccard & F-Measure83.7—Unverified
10RMNMean Jaccard & F-Measure83.5—Unverified
#ModelMetricClaimedVerifiedStatus
1XMem (BL30K, MS)Mean Jaccard & F-Measure86.9—Unverified
2AOTMean Jaccard & F-Measure84.1—Unverified
3RPCMVOSMean Jaccard & F-Measure84—Unverified
4STCNMean Jaccard & F-Measure83—Unverified
5CFBI+Mean Jaccard & F-Measure82.8—Unverified
6RMNJaccard (Seen)82.1—Unverified
7LCMMean Jaccard & F-Measure82—Unverified
8TransVOSMean Jaccard & F-Measure81.8—Unverified
9SSTMean Jaccard & F-Measure81.7—Unverified
10LWLMean Jaccard & F-Measure81.5—Unverified
#ModelMetricClaimedVerifiedStatus
1XMem (BL30K, MS)Mean Jaccard & F-Measure83.7—Unverified
2XMemMean Jaccard & F-Measure81—Unverified
3BATMANJaccard78.4—Unverified
4AOTJaccard75.9—Unverified
5RPCMVOSJaccard75.8—Unverified
6LCMJaccard74.4—Unverified
7KMNJaccard74.1—Unverified
8TransVOSJaccard73—Unverified
9STCNJaccard72.7—Unverified
10RMNJaccard71.9—Unverified
#ModelMetricClaimedVerifiedStatus
1XMem (BL30K,MS)Mean Jaccard & F-Measure86.8—Unverified
2XMemMean Jaccard & F-Measure85.5—Unverified
3BATMANMean Jaccard & F-Measure85—Unverified
4AOTMean Jaccard & F-Measure84.1—Unverified
5RPCMVOSMean Jaccard & F-Measure83.9—Unverified
6MobileVOSMean Jaccard & F-Measure83.3—Unverified
7STCNMean Jaccard & F-Measure82.7—Unverified
8CFBI+Mean Jaccard & F-Measure82.6—Unverified
9SSTMean Jaccard & F-Measure81.8—Unverified
10CFBIMean Jaccard & F-Measure81—Unverified
#ModelMetricClaimedVerifiedStatus
1AOC-MF (val)Jaccard (Mean)81.7—Unverified
2ViTAE-T-StageJaccard (Mean)79.4—Unverified
3DINO (ViT-B/8, ImageNet retrain)J&F71.4—Unverified
4VOSwL (Mask+Language)mIoU59—Unverified
5UniTrackmIoU58.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ReVOSAverage IOU75.6—Unverified
2Cutie-baseAverage IOU74.6—Unverified
3XMemAverage IOU70.4—Unverified
4SAM 2Average IOU69.5—Unverified
#ModelMetricClaimedVerifiedStatus
1DFNetF-Score82.3—Unverified
2oursJaccard (Mean)76.7—Unverified
#ModelMetricClaimedVerifiedStatus
1OursAverage74.9—Unverified
2FEELVOSmIoU0.82—Unverified
#ModelMetricClaimedVerifiedStatus
1LOCATEmIoU68.8—Unverified
#ModelMetricClaimedVerifiedStatus
1CutieJ&F68.3—Unverified
#ModelMetricClaimedVerifiedStatus
1LOCATEmIoU79.9—Unverified