https://github.com/claudiacuttano/samwise
공식 코드SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of Thoughts
Temporal Aggregate Representations for Long-Range Video Understanding
Coarse to Fine Multi-Resolution Temporal Convolutional Network
EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation
DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields
Meta Learning Deep Visual Words for Fast Video Object Segmentation
Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations
PVUW 2024 Challenge on Complex Video Understanding: Methods and Results
MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions
Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
An Image Processing Pipeline for Camera Trap Time-Lapse Recordings
Towards Robust Video Object Segmentation with Adaptive Object Calibration
Video Semantic Segmentation with Distortion-Aware Feature Correction
Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning
MediViSTA: Medical Video Segmentation via Temporal Fusion SAM Adaptation for Echocardiography
Local-Global Context Aware Transformer for Language-Guided Video Segmentation
Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation
Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.