paper-with-me

Video Semantic Segmentation

5개 벤치마크 · 논문 905편 · 이 태스크의 논문 보기 →

Benchmarks

Cityscapes val

결과 36개

CamVid

결과 24개

VSPW

결과 20개

LaRS

결과 12개

Most implemented

Pyramid Scene Parsing Network

2016-12-04 · 구현 67개

Papers

Surgical Anatomy Recognition with Context Learning using Foundation Representations

2026-06-20 · Ronald L. P. D. de Jong, Tim J. M. Jaspers, Raf A. H. Vervoort, Aron F. H. A. Bakker 외 arxiv

Accurate recognition of anatomical structures is essential for safe and effective minimally invasive surgery (MIS), yet it remains underexplored in surgical computer vision due to limited annotated data and methods tailo…

Video Semantic SegmentationScene UnderstandingObject Tracking

Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation

2026-06-08 · Jingpu Yang, Fengxian Ji, Zhengzhao Lai, Juanfan Wu 외 arxiv

Video semantic segmentation for low-altitude UAVs requires temporal consistency, yet dense optical flow introduces spatially structured noise in the planar regions that dominate aerial imagery. We propose a zero-paramete…

Video Semantic SegmentationSemantic Similarity

Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation

2026-05-04 · Chenyu Hui, Xiaodi Huang, Siyu Xu, Yunke Wang 외 arxiv

Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parallelizable to collect, often suffers from a substantial visual domain …

Video Semantic SegmentationData AugmentationVideo Captioning

Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation

2026-04-13 · Jihun Kim, Hoyong Kwon, Hyeokjun Kweon, Kuk-Jin Yoon arxiv

Fully supervised Video Semantic Segmentation (VSS) relies heavily on densely annotated video data, limiting practical applicability. Alternatively, applying pre-trained Image Semantic Segmentation (ISS) models frame-by-f…

Video Semantic SegmentationTest-time Adaptation

Can Unsupervised Segmentation Reduce Annotation Costs for Video Semantic Segmentation?

2026-03-29 · Samik Some, Vinay P. Namboodiri arxiv

Present-day deep neural networks for video semantic segmentation require a large number of fine-grained pixel-level annotations to achieve the best possible results. Obtaining such annotations, however, is very expensive…

Video Semantic SegmentationVideo Segmentation

RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation

2026-03-25 · Kai Zhu, Zhenyu Cui, Zehua Zang, Jiahuan Zhou arxiv

Recently, state space models have demonstrated efficient video segmentation through linear-complexity state space compression. However, Video Semantic Segmentation (VSS) requires pixel-level spatiotemporal modeling capab…

Video Semantic SegmentationComputational EfficiencyVideo Segmentation

전체 905편 보기 →