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

• URL: http://arxiv.org/abs/2501.00574v3
• Date: Sun, 09 Mar 2025 07:32:35 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: Long-context video modeling is critical for multimodal large language models (MLLMs)<n>This paper aims to address this issue from aspects of model architecture, training data, training strategy and evaluation benchmark.<n>We build a powerful video MLLM named VideoChat-Flash, which shows a leading performance on both mainstream long and short video benchmarks.
• Score: 43.485687038460895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-context video modeling is critical for multimodal large language models (MLLMs), enabling them to process movies, online video streams, and so on. Despite its advances, handling long videos remains challenging due to the difficulty in efficiently understanding the extremely long video context. This paper aims to address this issue from aspects of model architecture, training data, training strategy and evaluation benchmark. First, we propose a novel Hierarchical video token Compression (HiCo) method, which leverages visual redundancy in long videos to compress long video context from Clip-level to Video-level, reducing the computation significantly while preserving essential details, achieving an extreme compression ratio of approximately 1/50 with almost no performance loss. Second, we introduce a multi-stage short-to-long learning scheme, a large-scale dataset of real-world long videos named LongVid, and a challenging ``Multi-Hop Needle-In-A-Video-Haystack'' benchmark. Finally, we build a powerful video MLLM named VideoChat-Flash, which shows a leading performance on both mainstream long and short video benchmarks at the 2B and 7B model scale. It first gets 99.1% accuracy over 10,000 frames in NIAH among open-source models.

Related papers

• 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)
• VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges [42.555895949250704]
  VideoLLaMB is a novel framework that utilizes temporal memory tokens within bridge layers to allow for the encoding of entire video sequences. SceneTilling algorithm segments videos into independent semantic units to preserve semantic integrity. In terms of efficiency, VideoLLaMB, trained on 16 frames, supports up to 320 frames on a single Nvidia A100 GPU.
  arXiv  Detail & Related papers  (2024-09-02T08:52:58Z)
• 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)
• DrVideo: Document Retrieval Based Long Video Understanding [44.34473173458403]
  DrVideo is a document-retrieval-based system designed for long video understanding. It first transforms a long video into a coarse text-based long document to retrieve key frames and then updates the documents with the augmented key frame information. It then employs an agent-based iterative loop to continuously search for missing information and augment the document until sufficient question-related information is gathered.
  arXiv  Detail & Related papers  (2024-06-18T17:59:03Z)
• 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)
• 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 Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames [57.758863967770594]
  We build on the common paradigm of transferring large-scale, image--text models to video via shallow temporal fusion. We expose two limitations to the approach: (1) decreased spatial capabilities, likely due to poor video--language alignment in standard video datasets, and (2) higher memory consumption, bottlenecking the number of frames that can be processed.
  arXiv  Detail & Related papers  (2023-12-12T16:10:19Z)

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.