APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval

• URL: http://arxiv.org/abs/2506.04953v2
• Date: Sat, 28 Jun 2025 07:30:15 GMT
• Title: APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval
• Authors: Hong Gao, Yiming Bao, Xuezhen Tu, Bin Zhong, Minling Zhang,
• Abstract summary: Current large language models (LMs) struggle with hour-level video understanding.<n>bftextAdaptive textbfPivot MLbfVisual information textbfRetrieval (textbfAPVR), a training-free framework that hierarchically retrieves and retains sufficient and important visual information.
• Score: 41.81696346270799
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current multimodal large language models (MLLMs) struggle with hour-level video understanding, facing significant challenges not only in modeling the substantial information volume of long videos but also in overcoming the memory wall and resource constraints during both training and inference. Although recent training-free approaches have alleviated resource demands by compressing visual features, their reliance on incomplete visual information limits the performance potential. To address these limitations, we propose \textbf{A}daptive \textbf{P}ivot \textbf{V}isual information \textbf{R}etrieval (\textbf{APVR}), a training-free framework that hierarchically retrieves and retains sufficient and important visual information. It breakthroughs the memory wall limitation via two complementary components: Pivot Frame Retrieval employs query expansion and iterative spatio-semantic confidence scoring to identify relevant video frames, and Pivot Token Retrieval performs query-aware attention-driven token selection within up to 1024 pivot frames. This dual granularity approach enables the processing of hour-long videos while maintaining semantic fidelity. Experimental validations demonstrate significant performance improvements, achieving 64.9\% on LongVideoBench and 68.4\% on VideoMME, which are state-of-the-art results for both training-free and training-based approaches. Meanwhile, our method provides plug-and-play integration capability with existing MLLM architectures.

Related papers

• Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency [56.475612147721264]
  We propose a dual-reward formulation that supervises both semantic and temporal reasoning through discrete and continuous reward signals.<n>We evaluate our approach across eight representative video understanding tasks, including VideoQA, Temporal Video Grounding, and Grounded VideoQA.<n>Results underscore the importance of reward design and data selection in advancing reasoning-centric video understanding with MLLMs.
  arXiv  Detail & Related papers  (2025-06-02T17:28:26Z)
• Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing [30.94114120434789]
  We propose KVTP (Keyframe-oriented Vision Token MME), a novel framework that overcomes the token pruning and selection drawbacks.<n> KVTP effectively retains essential contextual information while significantly reducing redundant computation.
  arXiv  Detail & Related papers  (2025-03-13T17:47:52Z)
• HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding [14.464718780172582]
  We introduce HierarQ, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling.<n>We introduce a lightweight two-stream language-guided feature modulator to incorporate task awareness in video understanding.<n>Extensive evaluations on 10 video benchmarks across video understanding, question answering, and captioning tasks demonstrate HierarQ's state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-11T16:21:23Z)
• 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)
• TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler [10.92767902813594]
  We introduce TinyLLaVA-Video, a lightweight yet powerful video understanding model with approximately 3.6B parameters.<n>The cornerstone of our design is the video-level group resampler, a novel mechanism that significantly reduces and controls the number of visual tokens at the video level.<n>TinyLLaVA-Video demonstrates exceptional efficiency, requiring only one day of training on 8 A100-40G GPUs.
  arXiv  Detail & Related papers  (2025-01-26T13:10:12Z)
• 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.<n>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.<n>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)
• 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)
• 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-based Person Re-identification with Long Short-Term Representation Learning [101.62570747820541]
  Video-based person Re-Identification (V-ReID) aims to retrieve specific persons from raw videos captured by non-overlapped cameras. We propose a novel deep learning framework named Long Short-Term Representation Learning (LSTRL) for effective V-ReID.
  arXiv  Detail & Related papers  (2023-08-07T16:22:47Z)
• Temporal Context Aggregation for Video Retrieval with Contrastive Learning [81.12514007044456]
  We propose TCA, a video representation learning framework that incorporates long-range temporal information between frame-level features. The proposed method shows a significant performance advantage (17% mAP on FIVR-200K) over state-of-the-art methods with video-level features.
  arXiv  Detail & Related papers  (2020-08-04T05:24:20Z)

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.