Too Many Frames, not all Useful:Efficient Strategies for Long-Form Video QA
- URL: http://arxiv.org/abs/2406.09396v2
- Date: Mon, 17 Jun 2024 17:50:22 GMT
- Title: Too Many Frames, not all Useful:Efficient Strategies for Long-Form Video QA
- Authors: Jongwoo Park, Kanchana Ranasinghe, Kumara Kahatapitiya, Wonjeong Ryoo, Donghyun Kim, Michael S. Ryoo,
- Abstract summary: Long-form videos that span across wide temporal intervals are highly information redundant.
When performing long-form video question answering (LVQA),all information necessary to generate a correct response can often be contained within a small subset of frames.
Recent literature explore the use of large language models (LLMs) in LVQA benchmarks, achieving exceptional performance.
- Score: 40.54207548074378
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Long-form videos that span across wide temporal intervals are highly information redundant and contain multiple distinct events or entities that are often loosely-related. Therefore, when performing long-form video question answering (LVQA),all information necessary to generate a correct response can often be contained within a small subset of frames. Recent literature explore the use of large language models (LLMs) in LVQA benchmarks, achieving exceptional performance, while relying on vision language models (VLMs) to convert all visual content within videos into natural language. Such VLMs often independently caption a large number of frames uniformly sampled from long videos, which is not efficient and can mostly be redundant. Questioning these decision choices, we explore optimal strategies for key-frame selection and sequence-aware captioning, that can significantly reduce these redundancies. We propose two novel approaches that improve each of aspects, namely Hierarchical Keyframe Selector and Sequential Visual LLM. Our resulting framework termed LVNet achieves state-of-the-art performance across three benchmark LVQA datasets. Our code will be released publicly.
Related papers
- Encoding and Controlling Global Semantics for Long-form Video Question Answering [40.129800076300434]
We introduce a state space layer (SSL) into multi-modal Transformer to efficiently integrate global semantics of the video.
Our SSL includes a gating unit to enable controllability over the flow of global semantics into visual representations.
To rigorously evaluate long-form videoQA capacity, we construct two new benchmarks Ego-QA and MAD-QA featuring videos of considerably long length.
arXiv Detail & Related papers (2024-05-30T06:10:10Z) - VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos [67.78336281317347]
VideoTree is a queryadaptive and hierarchical framework for long-video understanding with Large Language Models.
VideoTree adaptively selects frames for captioning by iteratively clustering frames based on their visual features.
It organizes visual clusters into a query-adaptive and hierarchical tree structure.
arXiv Detail & Related papers (2024-05-29T15:49:09Z) - Streaming Long Video Understanding with Large Language Models [83.11094441893435]
VideoStreaming is an advanced vision-language large model (VLLM) for video understanding.
It capably understands arbitrary-length video with a constant number of video streaming tokens encoded and propagatedly selected.
Our model achieves superior performance and higher efficiency on long video benchmarks.
arXiv Detail & Related papers (2024-05-25T02:22:09Z) - LongVLM: Efficient Long Video Understanding via Large Language Models [55.813206751150716]
LongVLM is a simple yet powerful VideoLLM for long video understanding.
We encode video representations that incorporate both local and global information.
Our model produces more precise responses for long video understanding.
arXiv Detail & Related papers (2024-04-04T11:33:29Z) - VidLA: Video-Language Alignment at Scale [48.665918882615195]
We propose VidLA, an approach for video-language alignment at scale.
Our proposed approach surpasses state-of-the-art methods on multiple retrieval benchmarks.
arXiv Detail & Related papers (2024-03-21T22:36:24Z) - A Simple LLM Framework for Long-Range Video Question-Answering [66.68887077133355]
We present LLoVi, a language-based framework for long-range video question-answering (LVQA)
Our approach uses a frame/clip-level visual captioner coupled with a Large Language Model (GPT-3.5, GPT-4)
Our method achieves 50.3% accuracy, outperforming the previous best-performing approach by 18.1% (absolute gain)
arXiv Detail & Related papers (2023-12-28T18:58:01Z) - Self-Chained Image-Language Model for Video Localization and Question
Answering [66.86740990630433]
We propose Self-Chained Video-Answering (SeViLA) framework to tackle both temporal localization and QA on videos.
SeViLA framework consists of two modules: Localizer and Answerer, where both are parameter-efficiently fine-tuned from BLIP-2.
arXiv Detail & Related papers (2023-05-11T17:23:00Z)
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.