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 601650 of 895 papers

TitleStatusHype
Learning Spatio-Appearance Memory Network for High-Performance Visual TrackingCode1
PMVOS: Pixel-Level Matching-Based Video Object Segmentation0
Ground-truth or DAER: Selective Re-query of Secondary InformationCode0
LSMVOS: Long-Short-Term Similarity Matching for Video ObjectCode0
Making a Case for 3D Convolutions for Object Segmentation in VideosCode1
ScribbleBox: Interactive Annotation Framework for Video Object Segmentation0
MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object SegmentationCode1
DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping0
Monocular Instance Motion Segmentation for Autonomous Driving: KITTI InstanceMotSeg Dataset and Multi-task Baseline0
Curriculum Learning for Recurrent Video Object SegmentationCode0
Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation0
Self-supervised Object Tracking with Cycle-consistent Siamese NetworksCode1
Unsupervised Video Object Segmentation with Joint Hotspot Tracking0
Self-supervised Motion Representation via Scattering Local Motion Cues0
URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale BenchmarkCode1
Memory Selection Network for Video Propagation0
Interactive Video Object Segmentation Using Global and Local Transfer ModulesCode1
Kernelized Memory Network for Video Object SegmentationCode1
Video Object Segmentation with Episodic Graph Memory NetworksCode1
DeU-Net: Deformable U-Net for 3D Cardiac MRI Video Segmentation0
Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching0
Learning Object Depth from Camera Motion and Video Object SegmentationCode1
Motion Prediction in Visual Object Tracking0
Robust Semantic Segmentation in Adverse Weather Conditions by means of Fast Video-Sequence SegmentationCode1
Self-supervised Video Object SegmentationCode0
Video Panoptic SegmentationCode1
Video Semantic Segmentation with Distortion-Aware Feature CorrectionCode1
Real-Time Video Inference on Edge Devices via Adaptive Model StreamingCode1
Video Instance Segmentation Tracking With a Modified VAE Architecture0
D3S - A Discriminative Single Shot Segmentation Tracker0
Visual-Textual Capsule Routing for Text-Based Video Segmentation0
Temporal Aggregate Representations for Long-Range Video UnderstandingCode1
ALBA : Reinforcement Learning for Video Object SegmentationCode0
Tamed Warping Network for High-Resolution Semantic Video Segmentation0
MEDIAPI-SKEL - A 2D-Skeleton Video Database of French Sign Language With Aligned French Subtitles0
Physarum Powered Differentiable Linear Programming Layers and ApplicationsCode1
Revisiting Sequence-to-Sequence Video Object Segmentation with Multi-Task Loss and Skip-MemoryCode0
LSM: Learning Subspace Minimization for Low-level Vision0
Fast Template Matching and Update for Video Object Tracking and SegmentationCode1
A Transductive Approach for Video Object SegmentationCode1
Real-Time Segmentation Networks should be Latency Aware0
Context Modulated Dynamic Networks for Actor and Action Video Segmentation with Language Queries0
Temporally Distributed Networks for Fast Video Semantic SegmentationCode1
Memory Aggregation Networks for Efficient Interactive Video Object Segmentation0
TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain KnowledgeCode1
Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection0
Coronary Artery Segmentation in Angiographic Videos Using A 3D-2D CE-Net0
Learning What to Learn for Video Object SegmentationCode1
Collaborative Video Object Segmentation by Foreground-Background IntegrationCode1
Dual Temporal Memory Network for Efficient Video Object Segmentation0
Show:102550
← PrevPage 13 of 18Next →

Benchmark Results

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