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.
Zero-Shot 4D Lidar Panoptic Segmentation
ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025
Online Reasoning Video Segmentation with Just-in-Time Digital Twins
Comparative Analysis of Image, Video, and Audio Classifiers for Automated News Video Segmentation
Exploiting Temporal State Space Sharing for Video Semantic Segmentation
CamSAM2: Segment Anything Accurately in Camouflaged Videos
Reducing Annotation Burden: Exploiting Image Knowledge for Few-Shot Medical Video Object Segmentation via Spatiotemporal Consistency Relearning
One-Shot Medical Video Object Segmentation via Temporal Contrastive Memory Networks
High Temporal Consistency through Semantic Similarity Propagation in Semi-Supervised Video Semantic Segmentation for Autonomous Flight
Leveraging Vision-Language Models for Open-Vocabulary Instance Segmentation and Tracking
SAM2 for Image and Video Segmentation: A Comprehensive Survey
AUTV: Creating Underwater Video Datasets with Pixel-wise Annotations
Leveraging Motion Information for Better Self-Supervised Video Correspondence Learning
Investigation of Frame Differences as Motion Cues for Video Object Segmentation
Open-World Skill Discovery from Unsegmented Demonstrations
OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation
Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matching
Parameter-free Video Segmentation for Vision and Language Understanding
BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports
An Analysis of Data Transformation Effects on Segment Anything 2
Deep learning approaches to surgical video segmentation and object detection: A Scoping Review
Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field
Role of the Pretraining and the Adaptation data sizes for low-resource real-time MRI video segmentation
SASVi - Segment Any Surgical Video
Wandering around: A bioinspired approach to visual attention through object motion sensitivity
HD-EPIC: A Highly-Detailed Egocentric Video Dataset
Efficient Portrait Matte Creation With Layer Diffusion and Connectivity Priors
ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations
MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation
Efficient Frame Extraction: A Novel Approach Through Frame Similarity and Surgical Tool Tracking for Video Segmentation
Few-shot Structure-Informed Machinery Part Segmentation with Foundation Models and Graph Neural Networks
Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation
EdgeTAM: On-Device Track Anything Model
Static Segmentation by Tracking: A Frustratingly Label-Efficient Approach to Fine-Grained Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.