SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree Paper โข 2410.16268 โข Published Oct 21 โข 65
Llama-3.1-Nemotron-70B Collection SOTA models on Arena Hard and RewardBench as of 1 Oct 2024. โข 6 items โข Updated Oct 15 โข 146
UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces Paper โข 2312.15715 โข Published Dec 25, 2023 โข 19