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 1–50 of 895 papers

TitleStatusHype
SAM 2: Segment Anything in Images and VideosCode11
Efficient Track AnythingCode7
Segment Anything in Medical Images and Videos: Benchmark and DeploymentCode7
The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video SegmentationCode5
4th PVUW MeViS 3rd Place Report: Sa2VACode5
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and VideosCode5
Underwater Camouflaged Object Tracking Meets Vision-Language SAM2Code5
Unleashing the Potential of SAM2 for Biomedical Images and Videos: A SurveyCode5
OMG-Seg: Is One Model Good Enough For All Segmentation?Code5
MedSAM2: Segment Anything in 3D Medical Images and VideosCode4
EdgeTAM: On-Device Track Anything ModelCode4
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory TreeCode4
PVUW 2024 Challenge on Complex Video Understanding: Methods and ResultsCode4
SegGPT: Segmenting Everything In ContextCode4
SiamMask: A Framework for Fast Online Object Tracking and SegmentationCode4
Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different ScenesCode3
SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video SegmentationCode3
SMITE: Segment Me In TimECode3
Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2Code3
VISA: Reasoning Video Object Segmentation via Large Language ModelsCode3
Moving Object Segmentation: All You Need Is SAM (and Flow)Code3
PSALM: Pixelwise SegmentAtion with Large Multi-Modal ModelCode3
UniVS: Unified and Universal Video Segmentation with Prompts as QueriesCode3
RAP-SAM: Towards Real-Time All-Purpose Segment AnythingCode3
Putting the Object Back into Video Object SegmentationCode3
Tracking Anything with Decoupled Video SegmentationCode3
VideoCutLER: Surprisingly Simple Unsupervised Video Instance SegmentationCode3
Personalize Segment Anything Model with One ShotCode3
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory ModelCode3
Min-Max Similarity: A Contrastive Semi-Supervised Deep Learning Network for Surgical Tools SegmentationCode3
VideoMolmo: Spatio-Temporal Grounding Meets PointingCode2
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System CollaborationCode2
GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video SegmentationCode2
Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object SegmentationCode2
HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual PerceiverCode2
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language ModelsCode2
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any GranularityCode2
Det-SAM2:Technical Report on the Self-Prompting Segmentation Framework Based on Segment Anything Model 2Code2
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet VideosCode2
One Token to Seg Them All: Language Instructed Reasoning Segmentation in VideosCode2
Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 ModelCode2
Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object SegmentationCode2
Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame PruningCode2
Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion ModelsCode2
LVOS: A Benchmark for Large-scale Long-term Video Object SegmentationCode2
Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object SegmentationCode2
Decoupling Static and Hierarchical Motion Perception for Referring Video SegmentationCode2
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor QueriesCode2
Efficient Video Object Segmentation via Modulated Cross-Attention MemoryCode2
Vivim: a Video Vision Mamba for Medical Video SegmentationCode2
Show:102550
← PrevPage 1 of 18Next →
All datasetsCityscapes valCamVidVSPWLaRSMultispectral Video Semantic Segmentation

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TMANet-50mIoU80.3—Unverified
2DeltaDist-DDRNet-39mIoU79.9—Unverified
3TDNet-50 [9]mIoU79.9—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