Koala: Key frame-conditioned long video-LLM

• URL: http://arxiv.org/abs/2404.04346v3
• Date: Fri, 3 May 2024 19:43:55 GMT
• Title: Koala: Key frame-conditioned long video-LLM
• Authors: Reuben Tan, Ximeng Sun, Ping Hu, Jui-hsien Wang, Hanieh Deilamsalehy, Bryan A. Plummer, Bryan Russell, Kate Saenko,
• Abstract summary: We propose a lightweight and self-supervised long video-LLM (Koala) to adapt pretrained vLLMs for generalizing to longer videos. Our approach outperforms state-of-the-art large models by 3 - 6% in absolute accuracy across all tasks. Surprisingly, we also empirically show that our approach not only helps a pretrained vLLM to understand long videos but also improves its accuracy on short-term action recognition.
• Score: 70.52369588364992
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long video question answering is a challenging task that involves recognizing short-term activities and reasoning about their fine-grained relationships. State-of-the-art video Large Language Models (vLLMs) hold promise as a viable solution due to their demonstrated emergent capabilities on new tasks. However, despite being trained on millions of short seconds-long videos, vLLMs are unable to understand minutes-long videos and accurately answer questions about them. To address this limitation, we propose a lightweight and self-supervised approach, Key frame-conditioned long video-LLM (Koala), that introduces learnable spatiotemporal queries to adapt pretrained vLLMs for generalizing to longer videos. Our approach introduces two new tokenizers that condition on visual tokens computed from sparse video key frames for understanding short and long video moments. We train our proposed approach on HowTo100M and demonstrate its effectiveness on zero-shot long video understanding benchmarks, where it outperforms state-of-the-art large models by 3 - 6% in absolute accuracy across all tasks. Surprisingly, we also empirically show that our approach not only helps a pretrained vLLM to understand long videos but also improves its accuracy on short-term action recognition.

Related papers

• Goldfish: Vision-Language Understanding of Arbitrarily Long Videos [51.547065479762715]
  We present a methodology tailored for comprehending videos of arbitrary lengths. We also introduce the TVQA-long benchmark, designed to evaluate models' capabilities in understanding long videos with questions in both vision and text content. Our results indicate that our models have significant improvements in both long and short-video understanding.
  arXiv  Detail & Related papers  (2024-07-17T15:59:32Z)
• DrVideo: Document Retrieval Based Long Video Understanding [44.34473173458403]
  DrVideo is a document-retrieval-based system designed for long video understanding. It transforms a long video into a text-based long document to retrieve key frames and augment the information of these frames. It then employs an agent-based iterative loop to continuously search for missing information, augment relevant data, and provide final predictions.
  arXiv  Detail & Related papers  (2024-06-18T17:59:03Z)
• 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)
• Understanding Long Videos in One Multimodal Language Model Pass [44.78900245769057]
  Large Language Models (LLMs) are known to contain a strong awareness of world knowledge. We propose Likelihood Selection, a technique that unlocks faster inference in autoregressive LLMs. Our resulting Multimodal Video Understanding framework demonstrates state-of-the-art performance across long-video and fine-grained action recognition benchmarks.
  arXiv  Detail & Related papers  (2024-03-25T17:59:09Z)
• LVCHAT: Facilitating Long Video Comprehension [25.395689904747965]
  We propose Long Video Chat (LVChat) to enable multimodal large language models (LLMs) to read videos. LV significantly outperforms existing methods by up to 27% in accuracy on long-video QA datasets and long-video captioning benchmarks.
  arXiv  Detail & Related papers  (2024-02-19T11:59:14Z)
• A Simple LLM Framework for Long-Range Video Question-Answering [63.50439701867275]
  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)
• Locate before Answering: Answer Guided Question Localization for Video Question Answering [70.38700123685143]
  LocAns integrates a question locator and an answer predictor into an end-to-end model. It achieves state-of-the-art performance on two modern long-term VideoQA datasets.
  arXiv  Detail & Related papers  (2022-10-05T08:19:16Z)
• Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories [56.91664227337115]
  We introduce a collaborative memory mechanism that encodes information across multiple sampled clips of a video at each training iteration. This enables the learning of long-range dependencies beyond a single clip. Our proposed framework is end-to-end trainable and significantly improves the accuracy of video classification at a negligible computational overhead.
  arXiv  Detail & Related papers  (2021-04-02T18:59:09Z)

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.