Zero-Shot Automatic Annotation and Instance Segmentation using LLM-Generated Datasets: Eliminating Field Imaging and Manual Annotation…
SAM Decoding: Speculative Decoding via Suffix Automatonby Yuxuan Hu, Ke Wang, Xiaokang Zhang, Fanjin Zhang,…
Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Levelby Andong Deng, Tongjia Chen, Shoubin…
Region-Guided Attack on the Segment Anything Model (SAM)by Xiaoliang Liu, Furao Shen, Jian ZhaoFirst submitted…
A SAM based Tool for Semi-Automatic Food Annotationby Lubnaa Abdur Rahman, Ioannis Papathanail, Lorenzo Brigato,…
Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Imagesby Virmarie…
Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcareby Zhikai Li, Jing Zhang, Qingyi GuFirst…
DarkSAM: Fooling Segment Anything Model to Segment Nothingby Ziqi Zhou, Yufei Song, Minghui Li, Shengshan…
Global-Local Medical SAM Adaptor Based on Full Adaptionby Meng Wang, Yarong Feng, Yongwei Tang, Tian…
Towards Underwater Camouflaged Object Tracking: Benchmark and Baselinesby Chunhui Zhang, Li Liu, Guanjie Huang, Hao…