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.
SMITE: Segment Me In TimE
VideoSAM: A Large Vision Foundation Model for High-Speed Video Segmentation
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation
Configurable Embodied Data Generation for Class-Agnostic RGB-D Video Segmentation
VideoSAM: Open-World Video Segmentation
Shift and matching queries for video semantic segmentation
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation
Underwater Camouflaged Object Tracking Meets Vision-Language SAM2
Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation
Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervision
Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model
LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation
Discriminative Spatial-Semantic VOS Solution: 1st Place Solution for 6th LSVOS
Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation
CSS-Segment: 2nd Place Report of LSVOS Challenge VOS Track
Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey
The 2nd Solution for LSVOS Challenge RVOS Track: Spatial-temporal Refinement for Consistent Semantic Segmentation
LSVOS Challenge 3rd Place Report: SAM2 and Cutie based VOS
The Instance-centric Transformer for the RVOS Track of LSVOS Challenge: 3rd Place Solution
Rethinking Video Segmentation with Masked Video Consistency: Did the Model Learn as Intended?
3D-Aware Instance Segmentation and Tracking in Egocentric Videos
Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track
UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track
Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning
Is SAM 2 Better than SAM in Medical Image Segmentation?
Saliency Detection in Educational Videos: Analyzing the Performance of Current Models, Identifying Limitations and Advancement Directions
SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation
Novel adaptation of video segmentation to 3D MRI: efficient zero-shot knee segmentation with SAM2
Fast Sprite Decomposition from Animated Graphics
Performance and Non-adversarial Robustness of the Segment Anything Model 2 in Surgical Video Segmentation
Biomedical SAM 2: Segment Anything in Biomedical Images and Videos
Segment Anything in Medical Images and Videos: Benchmark and Deployment
Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.