VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

• URL: http://arxiv.org/abs/2501.00574v2
• Date: Fri, 10 Jan 2025 12:00:51 GMT
• Title: VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
• Authors: Xinhao Li, Yi Wang, Jiashuo Yu, Xiangyu Zeng, Yuhan Zhu, Haian Huang, Jianfei Gao, Kunchang Li, Yinan He, Chenting Wang, Yu Qiao, Yali Wang, Limin Wang,
• Abstract summary: This paper introduces a Hierarchical visual token Compression (HiCo) method designed for high-fidelity representation. HiCo capitalizes on the redundancy of visual information in long videos to compress long video context from the clip-level to the video-level. VideoChat-Flash shows the leading performance on both mainstream long and short video benchmarks at the 2B and 7B model scale.
• Score: 43.485687038460895
• License:
• Abstract: Long-context modeling is a critical capability for multimodal large language models (MLLMs), enabling them to process long-form contents with implicit memorization. Despite its advances, handling extremely long videos remains challenging due to the difficulty in maintaining crucial features over extended sequences. This paper introduces a Hierarchical visual token Compression (HiCo) method designed for high-fidelity representation and a practical context modeling system VideoChat-Flash tailored for multimodal long-sequence processing. HiCo capitalizes on the redundancy of visual information in long videos to compress long video context from the clip-level to the video-level, reducing the compute significantly while preserving essential details. VideoChat-Flash features a multi-stage short-to-long learning scheme, a rich dataset of real-world long videos named LongVid, and an upgraded "Needle-In-A-video-Haystack" (NIAH) for evaluating context capacities. In extensive experiments, VideoChat-Flash shows the leading performance on both mainstream long and short video benchmarks at the 2B and 7B model scale. It firstly gets 99.1% accuracy over 10,000 frames in NIAH among open-source models.

Related papers

• $\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation [19.616624959353697]
  $infty$-Video can process arbitrarily long videos through a continuous-time long-term memory (LTM) consolidation mechanism. Our framework augments video Q-formers by allowing them to process video contexts efficiently and without requiring additional training.
  arXiv  Detail & Related papers  (2025-01-31T12:45:46Z)
• HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding [52.696422425058245]
  We build a large-scale hour-long long video benchmark, HLV-1K, designed to evaluate long video understanding models. HLV-1K comprises 1009 hour-long videos with 14,847 high-quality question answering (QA) and multi-choice question asnwering (MCQA) We evaluate our benchmark using existing state-of-the-art methods and demonstrate its value for testing deep long video understanding capabilities at different levels and for various tasks.
  arXiv  Detail & Related papers  (2025-01-03T05:32:37Z)
• SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis [52.050036778325094]
  We introduce SALOVA: Segment-Augmented Video Assistant, a novel video-LLM framework designed to enhance the comprehension of lengthy video content. We present a high-quality collection of 87.8K long videos, each densely captioned at the segment level to enable models to capture scene continuity and maintain rich context. Our framework mitigates the limitations of current video-LMMs by allowing for precise identification and retrieval of relevant video segments in response to queries.
  arXiv  Detail & Related papers  (2024-11-25T08:04:47Z)
• 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)
• Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input [34.50993235961505]
  Kangaroo is a powerful Video LMM aimed at addressing the challenges of processing long videos. Data curation system to build a large-scale dataset with high-quality annotations for vision-language pre-training and instruction tuning. curriculum training pipeline with gradually increasing resolution and number of input frames to accommodate long videos.
  arXiv  Detail & Related papers  (2024-08-28T05:34:14Z)
• FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention [57.651429116402554]
  This paper investigates a straightforward and training-free approach to extend an existing short video diffusion model for consistent long video generation. We find that directly applying the short video diffusion model to generate long videos can lead to severe video quality degradation. Motivated by this, we propose a novel solution named FreeLong to balance the frequency distribution of long video features during the denoising process.
  arXiv  Detail & Related papers  (2024-07-29T11:52:07Z)
• LVBench: An Extreme Long Video Understanding Benchmark [38.839913137854104]
  We introduce LVBench, a benchmark specifically designed for long video understanding. Our dataset comprises publicly sourced videos and encompasses a diverse set of tasks aimed at long video comprehension and information extraction.
  arXiv  Detail & Related papers  (2024-06-12T09:36:52Z)
• MovieChat+: Question-aware Sparse Memory for Long Video Question Answering [36.14140811797466]
  We propose MovieChat to overcome the challenges of understanding long videos. We use tokens in Transformers as the carriers of memory in combination with our specially designed memory mechanism. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video, 2K temporal grounding labels, and 14K manual annotations for validation of the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-04-26T06:17:04Z)
• 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)

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.