Advancing Complex Video Object Segmentation via Progressive Concept Construction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911474949029888 |
|---|---|
| author | Zhang, Zhixiong Ding, Shuangrui Dong, Xiaoyi He, Songxin Lin, Jianfan Tang, Junsong Zang, Yuhang Cao, Yuhang Lin, Dahua Wang, Jiaqi |
| author_facet | Zhang, Zhixiong Ding, Shuangrui Dong, Xiaoyi He, Songxin Lin, Jianfan Tang, Junsong Zang, Yuhang Cao, Yuhang Lin, Dahua Wang, Jiaqi |
| contents | We propose Segment Concept (SeC), a concept-driven video object segmentation (VOS) framework that shifts from conventional feature matching to the progressive construction and utilization of high-level, object-centric representations. SeC employs Large Vision-Language Models (LVLMs) to integrate visual cues across diverse frames, constructing robust conceptual priors. To balance semantic reasoning with computational overhead, SeC forwards the LVLMs only when a new scene appears, injecting concept-level features at those points. To rigorously assess VOS methods in scenarios demanding high-level conceptual reasoning and robust semantic understanding, we introduce the Semantic Complex Scenarios Video Object Segmentation benchmark (SeCVOS). SeCVOS comprises 160 manually annotated multi-scenario videos designed to challenge models with substantial appearance variations and dynamic scene transformations. Empirical evaluations demonstrate that SeC substantially outperforms state-of-the-art approaches, including SAM 2 and its advanced variants, on both SeCVOS and standard VOS benchmarks. In particular, SeC achieves an 11.8-point improvement over SAM 2.1 on SeCVOS, establishing a new state-of-the-art in concept-aware VOS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15852 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advancing Complex Video Object Segmentation via Progressive Concept Construction Zhang, Zhixiong Ding, Shuangrui Dong, Xiaoyi He, Songxin Lin, Jianfan Tang, Junsong Zang, Yuhang Cao, Yuhang Lin, Dahua Wang, Jiaqi Computer Vision and Pattern Recognition Artificial Intelligence We propose Segment Concept (SeC), a concept-driven video object segmentation (VOS) framework that shifts from conventional feature matching to the progressive construction and utilization of high-level, object-centric representations. SeC employs Large Vision-Language Models (LVLMs) to integrate visual cues across diverse frames, constructing robust conceptual priors. To balance semantic reasoning with computational overhead, SeC forwards the LVLMs only when a new scene appears, injecting concept-level features at those points. To rigorously assess VOS methods in scenarios demanding high-level conceptual reasoning and robust semantic understanding, we introduce the Semantic Complex Scenarios Video Object Segmentation benchmark (SeCVOS). SeCVOS comprises 160 manually annotated multi-scenario videos designed to challenge models with substantial appearance variations and dynamic scene transformations. Empirical evaluations demonstrate that SeC substantially outperforms state-of-the-art approaches, including SAM 2 and its advanced variants, on both SeCVOS and standard VOS benchmarks. In particular, SeC achieves an 11.8-point improvement over SAM 2.1 on SeCVOS, establishing a new state-of-the-art in concept-aware VOS. |
| title | Advancing Complex Video Object Segmentation via Progressive Concept Construction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.15852 |