{"ID":2868557,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.15546","arxiv_id":"2509.15546","title":"Enhancing Sa2VA for Referent Video Object Segmentation: 2nd Solution for 7th LSVOS RVOS Track","abstract":"Referential Video Object Segmentation (RVOS) aims to segment all objects in a video that match a given natural language description, bridging the gap between vision and language understanding. Recent work, such as Sa2VA, combines Large Language Models (LLMs) with SAM~2, leveraging the strong video reasoning capability of LLMs to guide video segmentation. In this work, we present a training-free framework that substantially improves Sa2VA's performance on the RVOS task. Our method introduces two key components: (1) a Video-Language Checker that explicitly verifies whether the subject and action described in the query actually appear in the video, thereby reducing false positives; and (2) a Key-Frame Sampler that adaptively selects informative frames to better capture both early object appearances and long-range temporal context. Without any additional training, our approach achieves a J\u0026F score of 64.14% on the MeViS test set, ranking 2nd place in the RVOS track of the 7th LSVOS Challenge at ICCV 2025.","short_abstract":"Referential Video Object Segmentation (RVOS) aims to segment all objects in a video that match a given natural language description, bridging the gap between vision and language understanding. Recent work, such as Sa2VA, combines Large Language Models (LLMs) with SAM~2, leveraging the strong video reasoning capability...","url_abs":"https://arxiv.org/abs/2509.15546","url_pdf":"https://arxiv.org/pdf/2509.15546v1","authors":"[\"Ran Hong\",\"Feng Lu\",\"Leilei Cao\",\"An Yan\",\"Youhai Jiang\",\"Fengjie Zhu\"]","published":"2025-09-19T03:01:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}