VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
- URL: http://arxiv.org/abs/2501.06761v1
- Date: Sun, 12 Jan 2025 10:08:26 GMT
- Title: VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
- Authors: Ji Soo Lee, Jongha Kim, Jeehye Na, Jinyoung Park, Hyunwoo J. Kim,
- Abstract summary: Video is complicated task describing all events within a video while also temporally localizing them.
Previous VideoLLMs attempt to solve the task in a single step, failing to utilize their reasoning capability.
We propose VidChain of Chain-of-Tasks and Dense-based Direct Preference (-DPO)
M-DPO aligns a VideoLLM with evaluation metrics, providing fine-grained supervision to each task that is well-aligned with metrics.
- Score: 17.820597831536322
- License:
- Abstract: 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}.
Related papers
- CoS: Chain-of-Shot Prompting for Long Video Understanding [35.36760289077085]
Chain-of-Shot prompting (CoS) aims to frame shot selection as test-time visual prompt optimisation, choosing shots adaptive to video semantic task by optimising shots-task alignment.
CoS has two key parts: (1) a binary video summary mechanism that performs pseudo temporal grounding, discovering a binary coding to identify task-relevant shots, and (2) a video co-reasoning module that deploys the binary coding to pair (learning to align) task-relevant positive shots with irrelevant negative shots.
arXiv Detail & Related papers (2025-02-10T13:03:05Z) - VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection [61.54044967253421]
We introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essential spatial details and temporal coherence.
Our construction pipeline employs a semantic-aware method to reduce redundancy, followed by generating QA pairs using GPT-4o.
We propose a Hybrid LVLMs Collaboration framework, featuring a Frame Selector and a two-stage instruction fine-tuned reasoning LVLM.
arXiv Detail & Related papers (2024-11-22T08:33:36Z) - Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models [53.235170710385006]
We introduce Grounded-VideoLLM, a novel Video-LLM adept at perceiving and reasoning over specific video moments in a fine-grained manner.
We sharpen our model by incorporating (1) an additional temporal stream to encode the relationships between frames and (2) discrete temporal tokens enriched with specific time knowledge.
In experiments, Grounded-VideoLLM excels in fine-grained grounding tasks such as temporal sentence grounding, dense video captioning, and grounded VideoQA.
arXiv Detail & Related papers (2024-10-04T10:04:37Z) - Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs [20.168429351519055]
Video understanding is a crucial next step for multimodal large language models (LMLMs)
We propose VideoNIAH (Video Needle In A Haystack), a benchmark construction framework through synthetic video generation.
We conduct a comprehensive evaluation of both proprietary and open-source models, uncovering significant differences in their video understanding capabilities.
arXiv Detail & Related papers (2024-06-13T17:50:05Z) - TempCompass: Do Video LLMs Really Understand Videos? [36.28973015469766]
Existing benchmarks fail to provide a comprehensive feedback on the temporal perception ability of Video LLMs.
We propose the textbfTemp benchmark, which introduces a diversity of high-quality temporal aspects and task formats.
arXiv Detail & Related papers (2024-03-01T12:02:19Z) - Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement [72.7576395034068]
Video Corpus Moment Retrieval (VCMR) is a new video retrieval task aimed at retrieving a relevant moment from a large corpus of untrimmed videos using a text query.
We argue that effectively capturing the partial relevance between the query and video is essential for the VCMR task.
For video retrieval, we introduce a multi-modal collaborative video retriever, generating different query representations for the two modalities.
For moment localization, we propose the focus-then-fuse moment localizer, utilizing modality-specific gates to capture essential content.
arXiv Detail & Related papers (2024-02-21T07:16:06Z) - Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning [102.54669633984278]
We propose Momentor, a Video-LLM capable of accomplishing fine-grained temporal understanding tasks.
We train Momentor on Moment-10M, enabling it to perform segment-level reasoning and localization.
arXiv Detail & Related papers (2024-02-18T03:04:38Z) - Dense Video Object Captioning from Disjoint Supervision [77.47084982558101]
We propose a new task and model for dense video object captioning.
This task unifies spatial and temporal localization in video.
We show how our model improves upon a number of strong baselines for this new task.
arXiv Detail & Related papers (2023-06-20T17:57:23Z) - VALUE: A Multi-Task Benchmark for Video-and-Language Understanding
Evaluation [124.02278735049235]
VALUE benchmark aims to cover a broad range of video genres, video lengths, data volumes, and task difficulty levels.
We evaluate various baseline methods with and without large-scale VidL pre-training.
The significant gap between our best model and human performance calls for future study for advanced VidL models.
arXiv Detail & Related papers (2021-06-08T18:34:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.