paper-with-me

홈 › Papers

The Instance-centric Transformer for the RVOS Track of LSVOS Challenge: 3rd Place Solution

2024-08-20 · Bin Cao, Yisi Zhang, Hanyi Wang, Xingjian He, Jing Liu

Referring Video Object Segmentation is an emerging multi-modal task that aims to segment objects in the video given a natural language expression. In this work, we build two instance-centric models and fuse predicted results from frame-level and instance-level. First, we introduce instance mask into the DETR-based model for query initialization to achieve temporal enhancement and employ SAM for spatial refinement. Secondly, we build an instance retrieval model conducting binary instance mask classification whether the instance is referred. Finally, we fuse predicted results and our method achieved a score of 52.67 J&F in the validation phase and 60.36 J&F in the test phase, securing the final ranking of 3rd place in the 6-th LSVOS Challenge RVOS Track.

📄 PDF Abstract BibTeX arXiv:2408.10541

Code (0)

등록된 구현이 없습니다.

Tasks

Referring Video Object SegmentationRetrievalSemantic SegmentationVideo Object SegmentationVideo Semantic Segmentation

Methods 이 논문이 사용한 방법론

SAM 설명 없음

Similar Papers 제목 키워드 기반

UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track

2024-08-19 · Hao Fang, Feiyu Pan, Xiankai Lu, Wei zhang 외

Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video. In this year, LSVOS Challenge RVOS Track replaced the origin YouTube-RVOS benchmark with MeViS. MeViS …

Referring Video Object SegmentationSemantic SegmentationVideo Object SegmentationVideo Semantic Segmentation

1st Place Solution for 5th LSVOS Challenge: Referring Video Object Segmentation

2024-01-01 · Zhuoyan Luo, Yicheng Xiao, Yong liu, Yitong Wang 외

The recent transformer-based models have dominated the Referring Video Object Segmentation (RVOS) task due to the superior performance. Most prior works adopt unified DETR framework to generate segmentation masks in quer…

ObjectReferring Video Object SegmentationSegmentationSemantic Segmentation+2

The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA

2025-09-21 · Quanzhu Niu, Dengxian Gong, Shihao Chen, Tao Zhang 외 arxiv

Referring video object segmentation (RVOS) requires segmenting and tracking objects in videos conditioned on natural-language expressions, demanding fine-grained understanding of both appearance and motion. Building on S…

Referring Video Object SegmentationVideo Segmentation

The 2nd Solution for LSVOS Challenge RVOS Track: Spatial-temporal Refinement for Consistent Semantic Segmentation

2024-08-22 · Tuyen Tran

Referring Video Object Segmentation (RVOS) is a challenging task due to its requirement for temporal understanding. Due to the obstacle of computational complexity, many state-of-the-art models are trained on short time …

Referring Video Object SegmentationSegmentationSemantic SegmentationVideo Object Segmentation+1

Enhancing Sa2VA for Referent Video Object Segmentation: 2nd Solution for 7th LSVOS RVOS Track

2025-09-19 · Ran Hong, Feng Lu, Leilei Cao, An Yan 외 arxiv

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,…

Video Object SegmentationVideo Segmentation