SOTAVerified

Video Semantic Segmentation

The goal of video semantic segmentation is to assign a predefined class to each pixel in all frames of a video. This requires the model not only to predict accurate segmentation masks but also to ensure that these masks remain temporally consistent across frames. This task has broad applications in areas such as autonomous driving, medical video analysis, and AR/VR.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 895 papers

TitleStatusHype
Decoupling Static and Hierarchical Motion Perception for Referring Video SegmentationCode2
Decoupling Features in Hierarchical Propagation for Video Object SegmentationCode2
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System CollaborationCode2
Scalable Video Object Segmentation with Identification MechanismCode2
MOSE: A New Dataset for Video Object Segmentation in Complex ScenesCode2
One Token to Seg Them All: Language Instructed Reasoning Segmentation in VideosCode2
Mask2Former for Video Instance SegmentationCode2
LVOS: A Benchmark for Large-scale Long-term Video Object SegmentationCode2
MemSAM: Taming Segment Anything Model for Echocardiography Video SegmentationCode2
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet VideosCode2
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any GranularityCode2
Efficient Video Object Segmentation via Modulated Cross-Attention MemoryCode2
HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual PerceiverCode2
InstMove: Instance Motion for Object-centric Video SegmentationCode2
MeViS: A Large-scale Benchmark for Video Segmentation with Motion ExpressionsCode2
In Defense of Online Models for Video Instance SegmentationCode2
Global Spectral Filter Memory Network for Video Object SegmentationCode1
1st Place Solution for YouTubeVOS Challenge 2022: Referring Video Object SegmentationCode1
Clockwork Convnets for Video Semantic SegmentationCode1
Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2Code1
Global Knowledge Calibration for Fast Open-Vocabulary SegmentationCode1
GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video SegmentationCode1
Full-Duplex Strategy for Video Object SegmentationCode1
Flow-based Video Segmentation for Human Head and ShouldersCode1
General and Task-Oriented Video SegmentationCode1
Few-shot Structure-Informed Machinery Part Segmentation with Foundation Models and Graph Neural NetworksCode1
Generic Event Boundary Detection: A Benchmark for Event SegmentationCode1
Guided Interactive Video Object Segmentation Using Reliability-Based Attention MapsCode1
Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic PerspectiveCode1
Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object SegmentationCode1
FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical FlowCode1
Event-assisted Low-Light Video Object SegmentationCode1
CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video SegmentationCode1
Exploiting Temporal State Space Sharing for Video Semantic SegmentationCode1
Fast Template Matching and Update for Video Object Tracking and SegmentationCode1
End-to-End Semi-Supervised Learning for Video Action DetectionCode1
End-to-End Referring Video Object Segmentation with Multimodal TransformersCode1
End-to-End Video Matting With Trimap PropagationCode1
Adversarial Pixel Restoration as a Pretext Task for Transferable PerturbationsCode1
Learning Local and Global Temporal Contexts for Video Semantic SegmentationCode1
Accelerating Video Object Segmentation with Compressed VideoCode1
EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object RelationsCode1
Fast Video Object Segmentation using the Global Context ModuleCode1
Guided Slot Attention for Unsupervised Video Object SegmentationCode1
Efficient Multimodal Semantic Segmentation via Dual-Prompt LearningCode1
CamSAM2: Segment Anything Accurately in Camouflaged VideosCode1
Boosting Video Object Segmentation via Space-time Correspondence LearningCode1
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual GroupingCode1
Efficient Regional Memory Network for Video Object SegmentationCode1
3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPWCode1
Show:102550
← PrevPage 2 of 18Next →
All datasetsCityscapes valCamVidVSPWLaRSMultispectral Video Semantic Segmentation

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TMANet-50mIoU80.3—Unverified
2TDNet-50 [9]mIoU79.9—Unverified
3DeltaDist-DDRNet-39mIoU79.9—Unverified
4PSPNet-101 [20]mIoU79.7—Unverified
5PSPNet-50 [20]mIoU78.1—Unverified
6LVS [12]mIoU76.8—Unverified
7GRFP [15]mIoU73.6—Unverified
8FCN-50 [14]mIoU70.1—Unverified
9DFF [22]mIoU69.2—Unverified
#ModelMetricClaimedVerifiedStatus
1TMANet-50Mean IoU76.5—Unverified
2ETC-MobileNetMean IoU76.3—Unverified
3TDNet-50Mean IoU76.2—Unverified
4PSPNet-50Mean IoU76—Unverified
5NetwarpMean IoU74.7—Unverified
6GRFPMean IoU67.1—Unverified
#ModelMetricClaimedVerifiedStatus
1DVIS++(VIT-L)mIoU63.8—Unverified
2UniVS(Swin-L)mIoU59.8—Unverified
3Tube-Link(Swin-large)mIoU59.6—Unverified
4MRCFA(MiT-B5)mIoU49.9—Unverified
5CFFM(MiT-B5)mIoU49.3—Unverified
#ModelMetricClaimedVerifiedStatus
1WaSR-T (ResNet-101)Q60.1—Unverified
2TMANet (ResNet-50)Q57.5—Unverified
3CSANet (ResNet-101)Q49.1—Unverified
#ModelMetricClaimedVerifiedStatus
1MVNet(DeepLabV3)mIoU54.52—Unverified
2MVNet(PSPNet)mIoU54.36—Unverified
3MVNet(FCN)mIoU53.9—Unverified