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 201–250 of 895 papers

TitleStatusHype
Moving Object Segmentation: All You Need Is SAM (and Flow)Code3
arcjetCV: an open-source software to analyze material ablationCode0
Spatial-Temporal Multi-level Association for Video Object Segmentation—0
Decoupling Static and Hierarchical Motion Perception for Referring Video SegmentationCode2
Event-assisted Low-Light Video Object SegmentationCode1
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor QueriesCode2
Temporally Consistent Referring Video Object Segmentation with Hybrid MemoryCode1
Annolid: Annotate, Segment, and Track Anything You NeedCode0
Efficient Video Object Segmentation via Modulated Cross-Attention MemoryCode2
Triple Component Matrix Factorization: Untangling Global, Local, and Noisy Components—0
PSALM: Pixelwise SegmentAtion with Large Multi-Modal ModelCode3
Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object SegmentationCode1
Video Object Segmentation with Dynamic Query ModulationCode1
OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework—0
Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment AnythingCode1
ClickVOS: Click Video Object SegmentationCode0
Depth-aware Test-Time Training for Zero-shot Video Object SegmentationCode1
Deep Common Feature Mining for Efficient Video Semantic SegmentationCode0
Motion-Corrected Moving Average: Including Post-Hoc Temporal Information for Improved Video Segmentation—0
VideoMAC: Video Masked Autoencoders Meet ConvNetsCode1
UniVS: Unified and Universal Video Segmentation with Prompts as QueriesCode3
PolypNextLSTM: A lightweight and fast polyp video segmentation network using ConvNext and ConvLSTMCode0
Lester: rotoscope animation through video object segmentation and trackingCode1
Moving Object Proposals with Deep Learned Optical Flow for Video Object Segmentation—0
Point-VOS: Pointing Up Video Object Segmentation—0
Is Two-shot All You Need? A Label-efficient Approach for Video Segmentation in Breast Ultrasound—0
We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation BaselineCode1
Vanishing-Point-Guided Video Semantic Segmentation of Driving ScenesCode0
Self-supervised Video Object Segmentation with Distillation Learning of Deformable Attention—0
Vivim: a Video Vision Mamba for Medical Video SegmentationCode2
Explore Synergistic Interaction Across Frames for Interactive Video Object Segmentation—0
Understanding Video Transformers via Universal Concept Discovery—0
OMG-Seg: Is One Model Good Enough For All Segmentation?Code5
RAP-SAM: Towards Real-Time All-Purpose Segment AnythingCode3
Learning to Segment Referred Objects from Narrated Egocentric Videos—0
MemSAM: Taming Segment Anything Model for Echocardiography Video SegmentationCode2
Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video SegmentationCode0
1st Place Solution for 5th LSVOS Challenge: Referring Video Object SegmentationCode1
Tracking with Human-Intent ReasoningCode1
UniRef++: Segment Every Reference Object in Spatial and Temporal SpacesCode2
DVIS++: Improved Decoupled Framework for Universal Video SegmentationCode1
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision—0
Appearance-Based Refinement for Object-Centric Motion Segmentation—0
AutoVisual Fusion Suite: A Comprehensive Evaluation of Image Segmentation and Voice Conversion Tools on HuggingFace PlatformCode1
Artificial intelligence optical hardware empowers high-resolution hyperspectral video understanding at 1.2 Tb/s—0
Hierarchical Graph Pattern Understanding for Zero-Shot VOSCode0
TAM-VT: Transformation-Aware Multi-scale Video Transformer for Segmentation and Tracking—0
Semi-supervised Active Learning for Video Action DetectionCode0
Flexible visual prompts for in-context learning in computer visionCode0
GenDeF: Learning Generative Deformation Field for Video Generation—0
Show:102550
← PrevPage 5 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