SAM3RL introduces a reinforcement‑learning based memory controller for the Segment Anything Model 3 (SAM 3) visual object tracker, deciding which past frames to store in a memory bank to improve tracking performance. This data‑driven approach replaces hand‑crafted memory update rules and achieves state‑of‑the‑art results on 10 of 12 tracking and video object segmentation benchmarks, with no runtime overhead. The same method applied to SAM 2 (SAM2RL) also outperforms hand‑crafted rules on 9 of 12 benchmarks, demonstrating its generality across model generations.
Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking. Its tracker, inherited from SAM 2, stores information...
SAM3Dual is a training‑free inference extension of pretrained SAM 3 that won third place in the MOSEv2 track of the 8th Large‑scale Video Object Segmentation Challenge. It separates temporal memory into short‑term and long‑term branches, fuses their responses deterministically, and modulates them with previous‑frame confidence, all while keeping SAM 3 parameters frozen. The approach achieved an official J&F score of 64.37, demonstrating competitive long‑term VOS performance without task‑specific training.
arXiv:2608.22064v1 Announce Type: new Abstract: We present our solution for the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. The challenge evaluates r...
arXiv:2602. 14771v5 Announce Type: replace-cross Abstract: The human visual system tracks objects by integrating current observations with previously observed information, adapting to target and scene changes, and reasoning about occlusion at fine granularity.
arXiv:2610.01022v1 Announce Type: new Abstract: Memory-attention-based Video Instance Segmentation (VIS) methods have demonstrated strong zero-shot tracking capability, yet their substantial memory r...
arXiv:2609.37339v1 Announce Type: new Abstract: General multi-object tracking (GMOT) tracks all instances of a user-specified category from a single first-frame exemplar. Prior work relies on boundin...
arXiv:2608.22869v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models have leveraged internet-scale pretraining and task-focused finetuning to achieve strong performance on long...
arXiv:2608.22869v2 Announce Type: replace-cross Abstract: While Vision-Language-Action (VLA) models have leveraged internet-scale pretraining and task-specific finetuning to achieve strong performanc...
LiAM‑SAM is a lifecycle‑aware memory framework designed to improve segmentation‑based multi‑object tracking (MOT) with the SAM2 foundation video model. It addresses three common failure modes—faulty track initiation, memory drift during close interactions, and unreliable re‑identification after occlusion—by introducing contrastive track initiation, motion‑ and geometry‑grounded memory correction, and adaptive context memory. The system achieves state‑of‑the‑art HOTA and IDF1 scores, with ablations showing significant gains in association metrics and a 96% reduction in identity switches.
Segmentation-based multi-object tracking (MOT) with foundation video models such as SAM2 offers strong localization quality, yet remains fragile in crowded, real-world scenes. In detector-prompted SAM...
VideoTIR introduces a reinforcement‑learning approach to improve long‑video understanding by encouraging multimodal large language models to use comprehensive multi‑level toolkits efficiently. It combines Zero‑RL and SFT cold‑starting strategies to help models retrieve and focus on meaningful video segments, images, and regions, thereby reducing hallucinations. The method includes Toolkit Action Grouped Policy Optimization (TAGPO) to streamline tool‑calling and a sandbox‑based trajectory synthesis framework for high‑quality data, achieving strong results on three long‑video QA benchmarks.
arXiv:2609.05533v1 Announce Type: cross Abstract: Long-horizon manipulation is partially observable: the information needed to choose the next action may appear only in observations from minutes earl...