{"ID":2877874,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.18634","arxiv_id":"2508.18634","title":"OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward","abstract":"Video captioning aims to generate comprehensive and coherent descriptions of the video content, contributing to the advancement of both video understanding and generation. However, existing methods often suffer from motion-detail imbalance, as models tend to overemphasize one aspect while neglecting the other. This imbalance results in incomplete captions, which in turn leads to a lack of consistency in video understanding and generation. To address this issue, we propose solutions from two aspects: 1) Data aspect: We constructed the Harmonizing Motion-Detail 270K (HMD-270K) dataset through a two-stage pipeline: Motion-Detail Fusion (MDF) and Fine-Grained Examination (FGE). 2) Optimization aspect: We introduce the Caption Set Equivalence Reward (CSER) based on Group Relative Policy Optimization (GRPO). CSER enhances completeness and accuracy in capturing both motion and details through unit-to-set matching and bidirectional validation. Based on the HMD-270K supervised fine-tuning and GRPO post-training with CSER, we developed OwlCap, a powerful video captioning multi-modal large language model (MLLM) with motion-detail balance. Experimental results demonstrate that OwlCap achieves significant improvements compared to baseline models on two benchmarks: the detail-focused VDC (+4.2 Acc) and the motion-focused DREAM-1K (+4.6 F1). The HMD-270K dataset and OwlCap model will be publicly released to facilitate video captioning research community advancements.","short_abstract":"Video captioning aims to generate comprehensive and coherent descriptions of the video content, contributing to the advancement of both video understanding and generation. However, existing methods often suffer from motion-detail imbalance, as models tend to overemphasize one aspect while neglecting the other. This imb...","url_abs":"https://arxiv.org/abs/2508.18634","url_pdf":"https://arxiv.org/pdf/2508.18634v2","authors":"[\"Chunlin Zhong\",\"Qiuxia Hou\",\"Zhangjun Zhou\",\"Shuang Hao\",\"Haonan Lu\",\"Yanhao Zhang\",\"He Tang\",\"Xiang Bai\"]","published":"2025-08-26T03:18:34Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}