Papers with Code 아카이브
Video Semantic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 5
- 보존된 평가 기록
- 26
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Segment Anything Model for Zero-shot Single Particle Tracking in Liquid Phase Transmission Electron Microscopy
Is Segment Anything Model 2 All You Need for Surgery Video Segmentation? A Systematic Evaluation
Generative Video Propagation
When SAM2 Meets Video Shadow and Mirror Detection
M$^3$-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
Towards Open-Vocabulary Video Semantic Segmentation
Static-Dynamic Class-level Perception Consistency in Video Semantic Segmentation
Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentation
Stable Mean Teacher for Semi-supervised Video Action Detection
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
Video Decomposition Prior: A Methodology to Decompose Videos into Layers
Referring Video Object Segmentation via Language-aligned Track Selection
Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
Multi-Granularity Video Object Segmentation
Efficient Track Anything
Det-SAM2:Technical Report on the Self-Prompting Segmentation Framework Based on Segment Anything Model 2
Track Anything Behind Everything: Zero-Shot Amodal Video Object Segmentation
RoMo: Robust Motion Segmentation Improves Structure from Motion
SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation
ClickTrack: Towards Real-time Interactive Single Object Tracking
Geometric Algebra Planes: Convex Implicit Neural Volumes
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level
Zero-shot capability of SAM-family models for bone segmentation in CT scans
MSEG-VCUQ: Multimodal SEGmentation with Enhanced Vision Foundation Models, Convolutional Neural Networks, and Uncertainty Quantification for High-Speed Video Phase Detection Data
GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting
VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
Breaking The Ice: Video Segmentation for Close-Range Ice-Covered Waters
LiVOS: Light Video Object Segmentation with Gated Linear Matching
Event-guided Low-light Video Semantic Segmentation
Continuous Spatio-Temporal Memory Networks for 4D Cardiac Cine MRI Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.