LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding

• URL: http://arxiv.org/abs/2504.06835v1
• Date: Wed, 09 Apr 2025 12:51:10 GMT
• Title: LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding
• Authors: Ziyi Wang, Haoran Wu, Yiming Rong, Deyang Jiang, Yixin Zhang, Yunlong Zhao, Shuang Xu, Bo XU,
• Abstract summary: Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input.<n>Video Large Language Models (Video-LLMs) capture temporal relationships within visual features but are limited by the scarcity of high-quality video-text datasets.<n>We propose Lightweight Video Compression (LVC), a novel method featuring the Query-Attention Video Compression mechanism.
• Score: 29.719450799231705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input, they suffer from information loss due to the sparse sampling strategy. In contrast, Video Large Language Models (Video-LLMs) capture temporal relationships within visual features but are limited by the scarcity of high-quality video-text datasets. To transfer long video understanding capabilities to VLMs with minimal data and computational cost, we propose Lightweight Video Compression (LVC), a novel method featuring the Query-Attention Video Compression mechanism, which effectively tackles the sparse sampling problem in VLMs. By training only the alignment layer with 10k short video-text pairs, LVC significantly enhances the temporal reasoning abilities of VLMs. Extensive experiments show that LVC provides consistent performance improvements across various models, including the InternVL2 series and Phi-3.5-Vision. Notably, the InternVL2-40B-LVC achieves scores of 68.2 and 65.9 on the long video understanding benchmarks MLVU and Video-MME, respectively, with relative improvements of 14.6% and 7.7%. The enhanced models and code will be publicly available soon.

Related papers

• AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding [55.320254859515714]
  Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos.<n>We propose AdaReTaKe, a training-free method that flexibly reduces visual redundancy by allocating compression ratios among time and layers with theoretical guarantees.<n>Experiments on VideoMME, MLVU, LongVideoBench, and LVBench datasets demonstrate that AdaReTaKe outperforms existing methods by 2.3% and 2.8% for 7B and 72B models, respectively.
  arXiv  Detail & Related papers  (2025-03-16T16:14:52Z)
• Token-Efficient Long Video Understanding for Multimodal LLMs [101.70681093383365]
  STORM is a novel architecture incorporating a dedicated temporal encoder between the image encoder and the Video-LLMs.<n>We show that STORM achieves state-of-the-art results across various long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T06:17:38Z)
• InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling [56.130911402831906]
  This paper aims to improve the performance of video large language models (LM) via long and rich context (LRC) modeling.<n>We develop a new version of InternVideo2.5 with focus on enhancing the original MLLMs' ability to perceive fine-grained details in videos.<n> Experimental results demonstrate this unique designML LRC greatly improves the results of video MLLM in mainstream understanding benchmarks.
  arXiv  Detail & Related papers  (2025-01-21T18:59:00Z)
• VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling [43.485687038460895]
  Long-context video modeling is critical for multimodal large language models (MLLMs) This paper aims to address this issue from aspects of model architecture, training data, training strategy and evaluation benchmark. We build a powerful video MLLM named VideoChat-Flash, which shows a leading performance on both mainstream long and short video benchmarks.
  arXiv  Detail & Related papers  (2024-12-31T18:01:23Z)
• Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension [83.00346826110041]
  Video-RAG is a training-free and cost-effective pipeline that employs visually-aligned auxiliary texts to help facilitate cross-modality alignment.<n>Our model demonstrates superior performance over proprietary models like Gemini-1.5-Pro and GPT-4o when utilized with a 72B model.
  arXiv  Detail & Related papers  (2024-11-20T07:44:34Z)
• AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction [10.579335027350263]
  AdaCM$2$ is an adaptive cross-modality memory reduction approach to video-text alignment on video streams.<n>It achieves a 4.5% improvement across multiple tasks in the LVU dataset with a GPU memory consumption reduction of up to 65%.
  arXiv  Detail & Related papers  (2024-11-19T18:04:13Z)
• TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models [52.590072198551944]
  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.
  arXiv  Detail & Related papers  (2024-11-17T13:08:29Z)
• LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding [65.46303012350207]
  LongVU is an adaptive compression mechanism that reduces the number of video tokens while preserving visual details of long videos. We leverage DINOv2 features to remove redundant frames that exhibit high similarity. We perform spatial token reduction across frames based on their temporal dependencies.
  arXiv  Detail & Related papers  (2024-10-22T21:21:37Z)
• Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding [25.61734041983714]
  Video-XL is a novel approach that leverages MLLMs' inherent key-value sparsification capacity to condense the visual input.<n>Video-XL's effectiveness is verified from three aspects. First, it achieves a superior long-video understanding capability, outperforming state-of-the-art models of comparable sizes.
  arXiv  Detail & Related papers  (2024-09-22T15:13:31Z)

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.