| Online Reasoning Video Segmentation with Just-in-Time Digital Twins | Mar 27, 2025 | Reasoning SegmentationVideo Segmentation | —Unverified | 0 |
| CamSAM2: Segment Anything Accurately in Camouflaged Videos | Mar 25, 2025 | Camouflaged Object SegmentationObject | CodeCode Available | 1 |
| Reducing Annotation Burden: Exploiting Image Knowledge for Few-Shot Medical Video Object Segmentation via Spatiotemporal Consistency Relearning | Mar 19, 2025 | SegmentationSemantic Segmentation | CodeCode Available | 0 |
| Leveraging Vision-Language Models for Open-Vocabulary Instance Segmentation and Tracking | Mar 18, 2025 | DescriptiveInstance Segmentation | CodeCode Available | 0 |
| SAM2 for Image and Video Segmentation: A Comprehensive Survey | Mar 17, 2025 | Autonomous DrivingImage Segmentation | —Unverified | 0 |
| Open-World Skill Discovery from Unsegmented Demonstrations | Mar 11, 2025 | Boundary DetectionEvent Segmentation | —Unverified | 0 |
| OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation | Mar 10, 2025 | Pseudo LabelSemantic Segmentation | —Unverified | 0 |
| Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matching | Mar 5, 2025 | Data AugmentationFew-Shot Learning | —Unverified | 0 |
| Parameter-free Video Segmentation for Vision and Language Understanding | Mar 3, 2025 | Question AnsweringVideo Question Answering | —Unverified | 0 |
| BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports | Feb 28, 2025 | Action RecognitionLine Detection | CodeCode Available | 1 |
