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

Showing 51100 of 895 papers

TitleStatusHype
Decoupling Static and Hierarchical Motion Perception for Referring Video SegmentationCode2
Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object SegmentationCode2
One Token to Seg Them All: Language Instructed Reasoning Segmentation in VideosCode2
MOSE: A New Dataset for Video Object Segmentation in Complex ScenesCode2
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor QueriesCode2
Scalable Video Object Segmentation with Identification MechanismCode2
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
Decoupling Features in Hierarchical Propagation for Video Object SegmentationCode2
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
Learning Spatio-Appearance Memory Network for High-Performance Visual TrackingCode1
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
Differentiable Soft-Masked AttentionCode1
General and Task-Oriented Video SegmentationCode1
Directional Deep Embedding and Appearance Learning for Fast Video Object SegmentationCode1
Flow-based Video Segmentation for Human Head and ShouldersCode1
Generic Event Boundary Detection: A Benchmark for Event SegmentationCode1
Guided Interactive Video Object Segmentation Using Reliability-Based Attention MapsCode1
Delving into the Cyclic Mechanism in Semi-supervised Video Object SegmentationCode1
Delving Deep Into Many-to-Many Attention for Few-Shot Video Object SegmentationCode1
Dense Unsupervised Learning for Video SegmentationCode1
Fast Template Matching and Update for Video Object Tracking and SegmentationCode1
Depth-aware Test-Time Training for Zero-shot Video Object SegmentationCode1
Fast Video Object Segmentation using the Global Context ModuleCode1
Few-shot Structure-Informed Machinery Part Segmentation with Foundation Models and Graph Neural NetworksCode1
Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object SegmentationCode1
Deep Feature Flow for Video RecognitionCode1
Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic PerspectiveCode1
Boosting Video Object Segmentation via Space-time Correspondence LearningCode1
Adversarial Pixel Restoration as a Pretext Task for Transferable PerturbationsCode1
Domain Adaptive Video Segmentation via Temporal Consistency RegularizationCode1
FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical FlowCode1
Guided Slot Attention for Unsupervised Video Object SegmentationCode1
End-to-End Referring Video Object Segmentation with Multimodal TransformersCode1
Unified Domain Adaptive Semantic SegmentationCode1
End-to-End Semi-Supervised Learning for Video Action DetectionCode1
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual GroupingCode1
3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPWCode1
Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object SegmentationCode1
Show:102550
← PrevPage 2 of 18Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TMANet-50mIoU80.3Unverified
2DeltaDist-DDRNet-39mIoU79.9Unverified
3TDNet-50 [9]mIoU79.9Unverified
4PSPNet-101 [20]mIoU79.7Unverified
5PSPNet-50 [20]mIoU78.1Unverified
6LVS [12]mIoU76.8Unverified
7GRFP [15]mIoU73.6Unverified
8FCN-50 [14]mIoU70.1Unverified
9DFF [22]mIoU69.2Unverified
#ModelMetricClaimedVerifiedStatus
1TMANet-50Mean IoU76.5Unverified
2ETC-MobileNetMean IoU76.3Unverified
3TDNet-50Mean IoU76.2Unverified
4PSPNet-50Mean IoU76Unverified
5NetwarpMean IoU74.7Unverified
6GRFPMean IoU67.1Unverified
#ModelMetricClaimedVerifiedStatus
1DVIS++(VIT-L)mIoU63.8Unverified
2UniVS(Swin-L)mIoU59.8Unverified
3Tube-Link(Swin-large)mIoU59.6Unverified
4MRCFA(MiT-B5)mIoU49.9Unverified
5CFFM(MiT-B5)mIoU49.3Unverified
#ModelMetricClaimedVerifiedStatus
1WaSR-T (ResNet-101)Q60.1Unverified
2TMANet (ResNet-50)Q57.5Unverified
3CSANet (ResNet-101)Q49.1Unverified
#ModelMetricClaimedVerifiedStatus
1MVNet(DeepLabV3)mIoU54.52Unverified
2MVNet(PSPNet)mIoU54.36Unverified
3MVNet(FCN)mIoU53.9Unverified