| SAM 2: Segment Anything in Images and Videos | Aug 1, 2024 | Image SegmentationRobot Manipulation Generalization | CodeCode Available | 11 |
| Efficient Track Anything | Nov 28, 2024 | ObjectSegmentation | CodeCode Available | 7 |
| Segment Anything in Medical Images and Videos: Benchmark and Deployment | Aug 6, 2024 | BenchmarkingSegmentation | CodeCode Available | 7 |
| The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation | Apr 7, 2025 | Inference OptimizationReferring Video Object Segmentation | CodeCode Available | 5 |
| Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos | Jan 7, 2025 | 2kLanguage Modeling | CodeCode Available | 5 |
| Underwater Camouflaged Object Tracking Meets Vision-Language SAM2 | Sep 25, 2024 | ObjectObject Tracking | CodeCode Available | 5 |
| Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey | Aug 23, 2024 | Image SegmentationSegmentation | CodeCode Available | 5 |
| MedSAM2: Segment Anything in 3D Medical Images and Videos | Apr 4, 2025 | SegmentationVideo Segmentation | CodeCode Available | 4 |
| EdgeTAM: On-Device Track Anything Model | Jan 13, 2025 | modelVideo Segmentation | CodeCode Available | 4 |
| SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree | Oct 21, 2024 | Heuristic SearchObject | CodeCode Available | 4 |
| PVUW 2024 Challenge on Complex Video Understanding: Methods and Results | Jun 24, 2024 | SegmentationSemantic Segmentation | CodeCode Available | 4 |
| Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes | Dec 2, 2024 | In-Context LearningVideo Segmentation | CodeCode Available | 3 |
| SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation | Nov 26, 2024 | Natural Language UnderstandingReferring Video Object Segmentation | CodeCode Available | 3 |
| SMITE: Segment Me In TimE | Oct 24, 2024 | SegmentationSemantic Segmentation | CodeCode Available | 3 |
| Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2 | Aug 3, 2024 | DiversitySegmentation | CodeCode Available | 3 |
| VISA: Reasoning Video Object Segmentation via Large Language Models | Jul 16, 2024 | DecoderObject | CodeCode Available | 3 |
| UniVS: Unified and Universal Video Segmentation with Prompts as Queries | Feb 28, 2024 | DecoderReferring Expression Segmentation | CodeCode Available | 3 |
| RAP-SAM: Towards Real-Time All-Purpose Segment Anything | Jan 18, 2024 | AllDecoder | CodeCode Available | 3 |
| Tracking Anything with Decoupled Video Segmentation | Sep 7, 2023 | Open-Vocabulary Video SegmentationOpen-World Video Segmentation | CodeCode Available | 3 |
| VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation | Aug 28, 2023 | Instance SegmentationOptical Flow Estimation | CodeCode Available | 3 |
| Segment Anything Meets Point Tracking | Jul 3, 2023 | Interactive Video Object SegmentationObject | CodeCode Available | 3 |
| Min-Max Similarity: A Contrastive Semi-Supervised Deep Learning Network for Surgical Tools Segmentation | Mar 29, 2022 | Contrastive LearningSegmentation | CodeCode Available | 3 |
| GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation | Apr 10, 2025 | Contrastive LearningLanguage Modeling | CodeCode Available | 2 |
| HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver | Jan 1, 2025 | Reasoning SegmentationSegmentation | CodeCode Available | 2 |
| InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models | Dec 18, 2024 | Reasoning SegmentationSegmentation | CodeCode Available | 2 |
