VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Ji Soo, Kim, Jongha, Na, Jeehye, Park, Jinyoung, Kim, Hyunwoo J.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916563013074944
author Lee, Ji Soo
Kim, Jongha
Na, Jeehye
Park, Jinyoung
Kim, Hyunwoo J.
author_facet Lee, Ji Soo
Kim, Jongha
Na, Jeehye
Park, Jinyoung
Kim, Hyunwoo J.
contents Despite the advancements of Video Large Language Models (VideoLLMs) in various tasks, they struggle with fine-grained temporal understanding, such as Dense Video Captioning (DVC). DVC is a complicated task of describing all events within a video while also temporally localizing them, which integrates multiple fine-grained tasks, including video segmentation, video captioning, and temporal video grounding. Previous VideoLLMs attempt to solve DVC in a single step, failing to utilize their reasoning capability. Moreover, previous training objectives for VideoLLMs do not fully reflect the evaluation metrics, therefore not providing supervision directly aligned to target tasks. To address such a problem, we propose a novel framework named VidChain comprised of Chain-of-Tasks (CoTasks) and Metric-based Direct Preference Optimization (M-DPO). CoTasks decompose a complex task into a sequence of sub-tasks, allowing VideoLLMs to leverage their reasoning capabilities more effectively. M-DPO aligns a VideoLLM with evaluation metrics, providing fine-grained supervision to each task that is well-aligned with metrics. Applied to two different VideoLLMs, VidChain consistently improves their fine-grained video understanding, thereby outperforming previous VideoLLMs on two different DVC benchmarks and also on the temporal video grounding task. Code is available at \url{https://github.com/mlvlab/VidChain}.
format Preprint
id arxiv_https___arxiv_org_abs_2501_06761
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
Lee, Ji Soo
Kim, Jongha
Na, Jeehye
Park, Jinyoung
Kim, Hyunwoo J.
Computer Vision and Pattern Recognition
Despite the advancements of Video Large Language Models (VideoLLMs) in various tasks, they struggle with fine-grained temporal understanding, such as Dense Video Captioning (DVC). DVC is a complicated task of describing all events within a video while also temporally localizing them, which integrates multiple fine-grained tasks, including video segmentation, video captioning, and temporal video grounding. Previous VideoLLMs attempt to solve DVC in a single step, failing to utilize their reasoning capability. Moreover, previous training objectives for VideoLLMs do not fully reflect the evaluation metrics, therefore not providing supervision directly aligned to target tasks. To address such a problem, we propose a novel framework named VidChain comprised of Chain-of-Tasks (CoTasks) and Metric-based Direct Preference Optimization (M-DPO). CoTasks decompose a complex task into a sequence of sub-tasks, allowing VideoLLMs to leverage their reasoning capabilities more effectively. M-DPO aligns a VideoLLM with evaluation metrics, providing fine-grained supervision to each task that is well-aligned with metrics. Applied to two different VideoLLMs, VidChain consistently improves their fine-grained video understanding, thereby outperforming previous VideoLLMs on two different DVC benchmarks and also on the temporal video grounding task. Code is available at \url{https://github.com/mlvlab/VidChain}.
title VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.06761