CoS: Chain-of-Shot Prompting for Long Video Understanding

• URL: http://arxiv.org/abs/2502.06428v2
• Date: Tue, 11 Feb 2025 14:59:25 GMT
• Title: CoS: Chain-of-Shot Prompting for Long Video Understanding
• Authors: Jian Hu, Zixu Cheng, Chenyang Si, Wei Li, Shaogang Gong,
• Abstract summary: 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.
• Score: 35.36760289077085
• License:
• Abstract: Multi-modal Large Language Models (MLLMs) struggle with long videos due to the need for excessive visual tokens. These tokens exceed massively the context length of MLLMs, resulting in filled by redundant task-irrelevant shots. How to select shots is an unsolved critical problem: sparse sampling risks missing key details, while exhaustive sampling overwhelms the model with irrelevant content, leading to video misunderstanding. To solve this problem, we propose Chain-of-Shot prompting (CoS). The key idea is to frame shot selection as test-time visual prompt optimisation, choosing shots adaptive to video understanding 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. It embeds the optimised shot selections into the original video, facilitating a focus on relevant context to optimize long video understanding. Experiments across three baselines and five datasets demonstrate the effectiveness and adaptability of CoS. Code given in https://lwpyh.github.io/CoS.

Related papers

• VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning [17.820597831536322]
  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.
  arXiv  Detail & Related papers  (2025-01-12T10:08:26Z)
• 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)
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency [62.38914747727636]
  We study self-supervised video representation learning, which is a challenging task due to 1) a lack of labels for explicit supervision and 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminating instances from each other. In this paper, we observe that the consistency between positive samples is the key to learn robust video representations.
  arXiv  Detail & Related papers  (2021-06-04T08:44:50Z)
• Video Corpus Moment Retrieval with Contrastive Learning [56.249924768243375]
  Video corpus moment retrieval (VCMR) is to retrieve a temporal moment that semantically corresponds to a given text query. We propose a Retrieval and Localization Network with Contrastive Learning (ReLoCLNet) for VCMR. Experimental results show that ReLoCLNet encodes text and video separately for efficiency, its retrieval accuracy is comparable with baselines adopting cross-modal interaction learning.
  arXiv  Detail & Related papers  (2021-05-13T12:54:39Z)
• Fill-in-the-blank as a Challenging Video Understanding Evaluation Framework [19.031957183047048]
  We introduce a novel dataset consisting of 28,000 videos and fill-in-the-blank tests. We show that both a multimodal model and a strong language model have a large gap with human performance.
  arXiv  Detail & Related papers  (2021-04-09T04:00:10Z)
• Few-Shot Action Recognition with Compromised Metric via Optimal Transport [31.834843714684343]
  Few-shot action recognition is still not mature despite the wide research of few-shot image classification. One main obstacle to applying these algorithms in action recognition is the complex structure of videos. We propose Compromised Metric via Optimal Transport (CMOT) to combine the advantages of these two solutions.
  arXiv  Detail & Related papers  (2021-04-08T12:42:05Z)
• Video Understanding as Machine Translation [53.59298393079866]
  We tackle a wide variety of downstream video understanding tasks by means of a single unified framework. We report performance gains over the state-of-the-art on several downstream tasks including video classification (EPIC-Kitchens), question answering (TVQA), captioning (TVC, YouCook2, and MSR-VTT)
  arXiv  Detail & Related papers  (2020-06-12T14:07:04Z)
• Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA [96.10612095576333]
  We propose a video question answering model which effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions. Our model is also comprised of dual-level attention (word/object and frame level), multi-head self-cross-integration for different sources (video and dense captions), and which pass more relevant information to gates. We evaluate our model on the challenging TVQA dataset, where each of our model components provides significant gains, and our overall model outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2020-05-13T16:35:27Z)

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.