Pith. sign in

REVIEW 9 cited by

KeyVideoLLM: Towards Large-scale Video Keyframe Selection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.03104 v3 pith:XGPQR4S7 submitted 2024-07-03 cs.CV cs.CLcs.MM

Hao Liang , Jiapeng Li , Tianyi Bai , Xijie Huang , Linzhuang Sun , Zhengren Wang , Conghui He , Bin Cui
show 2 more authors
Chong Chen Wentao Zhang
This is my paper · ORCID
classification cs.CVcs.CLcs.MM
keywords videodatakeyvideollmselectionefficiencykeyframedatasetsinference
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, with the rise of web videos, managing and understanding large-scale video datasets has become increasingly important. Video Large Language Models (VideoLLMs) have emerged in recent years due to their strong video understanding capabilities. However, training and inference processes for VideoLLMs demand vast amounts of data, presenting significant challenges to data management, particularly regarding efficiency, robustness, and effectiveness. In this work, we present KeyVideoLLM, a text-video frame similarity-based keyframe selection method designed to manage VideoLLM data efficiently, robustly, and effectively. Specifically, KeyVideoLLM achieves a remarkable data compression rate of up to 60.9 times, substantially lowering disk space requirements, which proves its high efficiency. Additionally, it maintains a 100% selection success rate across all video formats and scales, enhances processing speed by up to 200 times compared to existing keyframe selection methods, and does not require hyperparameter tuning. Beyond its outstanding efficiency and robustness, KeyVideoLLM further improves model performance in video question-answering tasks during both training and inference stages. Notably, it consistently achieved the state-of-the-art (SoTA) experimental results on diverse datasets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding

    cs.CV 2026-08 conditional novelty 6.0 of 10

    EviSelect uses the target multimodal model's internal attention as a prior to dynamically select frames, sampling rates, and resolutions, achieving about 50% token reduction and a 3.9x speedup with better benchmark accuracy.

  2. Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding

    cs.AI 2026-06 conditional novelty 6.0 of 10

    ReMem improves zero-shot long-video QA by combining LLM-based temporal granularity parsing, CLIP-based dual-semantic frame scoring, and structure-aware dynamic frame routing.

  3. Multi-Scale Separable Fourier Neural Networks for Solving High-Frequency PDEs

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    MS-SFNN encodes multi-scale Fourier features in a separable product of fixed-weight cosine subnetworks and solves for linear coefficients by least squares, claiming better accuracy than PINN and SV-SNN on high-frequency PDEs.

  4. AnchorSync: Global Consistency Optimization for Long Video Editing

    cs.CV 2025-08 conditional novelty 6.0 of 10

    By jointly editing sparse anchor frames and interpolating with flow and edge guidance, AnchorSync produces temporally consistent edits on videos longer than previous diffusion methods could handle.

  5. ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning

    cs.CV 2025-05 conditional novelty 6.0 of 10

    ViaRL uses rule-based reinforcement learning to train a frame selector for video QA, improving Qwen2.5-VL on VideoMME, LVBench, and MLVU by several points.

  6. VisualRouter: Query-Grounded Visual Sampling for Long Video Understanding

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Query-type routing plus hybrid relevance-coverage and event-aware DPP sampling beats uniform and other training-free frame selectors on long-video benchmarks.

  7. Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A CLIP-scored, Gumbel-Max frame sampler with per-frame multi-resolution allocation improves long-video question answering in Video-LLMs under a fixed token budget.

  8. OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

    cs.CV 2026-04 unverdicted novelty 4.0 of 10

    OpenWorldLib offers a standardized codebase and definition for world models that combine perception, interaction, and memory to understand and predict the world.

  9. TriPSS: A Tri-Modal Keyframe Extraction Framework Using Perceptual, Structural, and Semantic Representations

    cs.CV 2025-06 conditional novelty 4.0 of 10

    TriPSS fuses CIELAB color, ResNet-50, and LLaMA caption embeddings through PCA and HDBSCAN to extract keyframes, reporting F1 of 0.6104 on TVSum20 and 0.5902 on SumMe.

Pith tools