paper-with-me

Papers

MotionAtlas: Detailed Region Captioning for Motion-Centric Videos

2026-06-28 · Weisong Liu, Haochen Wang, Kuan Gao, Yuhao Wang, Yikang Zhou, Zhongwei Ren, Jacky Mai, Anna Wang, Yanwei Li, Jason Li, Zhaoxiang Zhang arxiv

We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs. Unlike conventional global motion captioning datasets, we focus on region-aware motion captioning: given a video and a spatiotemporal mask, the model generates precise descriptions of motion within the target region, thereby alleviating visual clutter and motion entanglement and enabling reliable, quantifiable evaluation. Concretely, we first build MotionAtlas-Bench, a comprehensive benchmark comprising 2,073 multiple-choice questions, meticulously annotated for a curated set of high-quality, motion-centric videos, to evaluate fine-grained motion understanding of the objects in question. Second, we design a rigorous and scalable data pipeline that leverages self-bootstrap refinement to suppress fine-grained hallucinations, yielding 159k high-quality motion captioning data. Third, we design a tailored training data composition strategy, which achieves consistent and substantial performance gains across diverse baseline Video-MLLMs, including Molmo2 and Qwen3-VL. For instance, MotionAtlas-4B surpasses Qwen3-VL-4B by an average of 5.2 percentage points across general motion benchmarks. The benchmark, dataset, and code have been released.

📄 PDF Abstract BibTeX arXiv:2606.29531

Code (0)

등록된 구현이 없습니다.

Tasks

Motion Captioning

Similar Papers 제목 키워드 기반

Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention

2021-09-07 · Katsuyuki Nakamura, Hiroki Ohashi, Mitsuhiro Okada

Automatically describing video, or video captioning, has been widely studied in the multimedia field. This paper proposes a new task of sensor-augmented egocentric-video captioning, a newly constructed dataset for it cal…

Sensor FusionVideo Captioning

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

2025-04-07 · Yunlong Tang, Jing Bi, Chao Huang, Susan Liang 외

We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three ke…

Boundary DetectionObjectSemantic SegmentationVideo Captioning

KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding

2026-02-19 · Boda Lin, Yongjie Zhu, Xiaocheng Gong, Wenyu Qin 외 arxiv

Despite recent advancements, video captioning models still face significant limitations in accurately describing fine-grained motion details and suffer from severe hallucination issues. These challenges become particular…

Video Captioning

One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

2025-10-03 · Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara, Nicola Messina 외 arxiv

Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without relying on paired image-text data. To caption an image, they proceed by textually deco…

Dense Captioning

AVC-DPO: Aligned Video Captioning via Direct Preference Optimization

2025-07-02 · Jiyang Tang, Hengyi Li, Yifan Du, Wayne Xin Zhao arxiv

Although video multimodal large language models (video MLLMs) have achieved substantial progress in video captioning tasks, it remains challenging to adjust the focal emphasis of video captions according to human prefere…

Video Captioning