TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models

• URL: http://arxiv.org/abs/2411.11066v1
• Date: Sun, 17 Nov 2024 13:08:29 GMT
• Title: TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
• Authors: Tingyu Qu, Mingxiao Li, Tinne Tuytelaars, Marie-Francine Moens,
• Abstract summary: Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents. For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality, curated video-text paired data. In this work, we explore the limitations of the existing compression strategies for building a training-free video LLM.
• Score: 52.590072198551944
• License:
• Abstract: Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents. For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality, curated video-text paired data. In contrast, paired image-text data are much easier to obtain, and there is substantial similarity between images and videos. Consequently, extending image LLMs for video understanding tasks presents an appealing alternative. Developing effective strategies for compressing visual tokens from multiple frames is a promising way to leverage the powerful pre-trained image LLM. In this work, we explore the limitations of the existing compression strategies for building a training-free video LLM. The findings lead to our method TS-LLaVA, which constructs visual tokens through a Thumbnail-and-Sampling strategy. Given a video, we select few equidistant frames from all input frames to construct a Thumbnail image as a detailed visual cue, complemented by Sampled visual tokens from all input frames. Our method establishes the new state-of-the-art performance among training-free video LLMs on various benchmarks. Notably, our 34B model outperforms GPT-4V on the MVBench benchmark, and achieves performance comparable to the 72B training-based video LLM, Video-LLaMA2, on the challenging MLVU benchmark. Code is available at https://github.com/tingyu215/TS-LLaVA.

Related papers

• Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs [56.040198387038025]
  We present a novel prompt-guided visual perception framework (abbreviated as Free Video-LLM) for efficient inference of training-free video LLMs. Our method effectively reduces the number of visual tokens while maintaining high performance across multiple video question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T12:35:12Z)
• Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models [29.825619120260164]
  This paper addresses the challenge by leveraging the visual commonalities between images and videos to evolve image-LVLMs into video-LVLMs. We present a cost-effective video-LVLM that enhances model architecture, introduces innovative training strategies, and identifies the most effective types of video instruction data.
  arXiv  Detail & Related papers  (2024-06-12T09:22:45Z)
• ST-LLM: Large Language Models Are Effective Temporal Learners [58.79456373423189]
  Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation. How to effectively encode and understand videos in video-based dialogue systems remains to be solved. We propose ST-LLM, an effective video-LLM baseline with spatial-temporal sequence modeling inside LLM.
  arXiv  Detail & Related papers  (2024-03-30T10:11:26Z)
• Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback [38.708690624594794]
  Video and text multimodal alignment remains challenging, primarily due to the deficient volume and quality of multimodal instruction-tune data. We present a novel alignment strategy that employs multimodal AI system to oversee itself called Reinforcement Learning from AI Feedback (RLAIF) In specific, we propose context-aware reward modeling by providing detailed video descriptions as context during the generation of preference feedback.
  arXiv  Detail & Related papers  (2024-02-06T06:27:40Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding [63.075626670943116]
  We introduce a cutting-edge framework, VaQuitA, designed to refine the synergy between video and textual information. At the data level, instead of sampling frames uniformly, we implement a sampling method guided by CLIP-score rankings. At the feature level, we integrate a trainable Video Perceiver alongside a Visual-Query Transformer.
  arXiv  Detail & Related papers  (2023-12-04T19:48:02Z)
• Video-LLaVA: Learning United Visual Representation by Alignment Before Projection [27.04277811443469]
  Video-LLaVA learns from a mixed dataset of images and videos, mutually enhancing each other. Video-LLaVA superior performances on a broad range of 9 image benchmarks across 5 image question-answering datasets and 4 image benchmark toolkits.
  arXiv  Detail & Related papers  (2023-11-16T10:59:44Z)
• VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending [78.1399386935455]
  Large-scale image-text contrastive pre-training models, such as CLIP, have been demonstrated to effectively learn high-quality multimodal representations. We propose a novel video-text pre-training method dubbed VLAB: Video Language pre-training by feature generativearity and Blending. VLAB transfers CLIP representations to video pre-training tasks and develops unified video multimodal models for a wide range of video-text tasks.
  arXiv  Detail & Related papers  (2023-05-22T15:54:22Z)

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.