C-RAG consistently improves diverse backbones across three benchmarks—Video-MME, MLVU, and LongVideoBench—outperforming existing RAG-based methods under every tested setting. Notably, with the 72B LLaVA-Video backbone, EC-RAG surpasses both GPT-4o and Gemini-1.5-Pro on Video-MME using a fully open-source pipeline, demonstrating that structured event-level retrieval enables open-source models to rival and even surpass proprietary systems without additional training.
Beyond the benchmarks evaluated in this work, we believe the event-chain paradigm holds broader potential for other video-centric tasks such as video summarization, temporal grounding, and multi-turn video dialogue, where preserving temporal structure and aggregating cross-modal evidence are equally critical. The training-free nature of EC-RAG also makes it readily applicable to emerging LVLMs as they continue to evolve, offering a flexible and scalable augmentation strategy.
References
Cao et al. (2025)
Z. Cao, Y. He, A. Liu, J. Xie, F. Chen, and Z. Wang
Tv-rag: a temporal-aware and semantic entropy-weighted framework for long video retrieval and understanding.
In Proceedings of the 33rd ACM International Conference on Multimedia,
pp. 9071–9079.
Cited by: Table 6,
Table 6,
Appendix A,
§1,
§2.3,
§3.2,
§3.2,
§3.2,
Table 1,
§4.2,
Table 2,
Table 3.
Chen et al. (2024a)
L. Chen, J. Li, X. Dong, P. Zhang, C. He, J. Wang, F. Zhao, and D. Lin
Sharegpt4v: improving large multi-modal models with better captions.
In European Conference on Computer Vision,
pp. 370–387.
Cited by: §1.
Chen et al. (2024b)
L. Chen, X. Wei, J. Li, X. Dong, P. Zhang, Y. Zang, Z. Chen, H. Duan, B. Lin, Z. Tang, et al.
Sharegpt4video: improving video understanding and generation with better captions.
Advances in Neural Information Processing Systems 37, pp. 19472–19495.
Cited by: Table 3.
Fan et al. (2024)
Y. Fan, X. Ma, R. Wu, Y. Du, J. Li, Z. Gao, and Q. Li
Videoagent: a memory-augmented multimodal agent for video understanding.
In European Conference on Computer Vision,
pp. 75–92.
Cited by: §2.2.
Fei et al. (2024)
J. Fei, D. Li, Z. Deng, Z. Wang, G. Liu, and H. Wang
Video-ccam: enhancing video-language understanding with causal cross-attention masks for short and long videos.
arXiv preprint arXiv:2408.14023.
Cited by: Table 2.
Fu et al. (2025)
C. Fu, Y. Dai, Y. Luo, L. Li, S. Ren, R. Zhang, Z. Wang, C. Zhou, Y. Shen, M. Zhang, et al.
Video-mme: the first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis.
In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,
pp. 24108–24118.
Cited by: Table 5,
Table 6,
Appendix A,
Figure 5,
Table 7,
Appendix C,
§1,
§1,
Table 1,
§4.1.
Gupta and Kembhavi (2023)
T. Gupta and A. Kembhavi
Visual programming: compositional visual reasoning without training.
In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,
pp. 14953–14962.
Cited by: §2.2.
Izacard et al. (2021)
G. Izacard, M. Caron, L. Hosseini, S. Riedel, P. Bojanowski, A. Joulin, and E. Grave
Unsupervised dense information retrieval with contrastive learning.
arXiv preprint arXiv:2112.09118.
Cited by: §3.2,
§4.2.
JaidedAI (2023)
JaidedAI
EasyOCR.
Note: https://github.com/JaidedAI/EasyOCRAccessed: 2026-03-30
Cited by: §3.2,
§4.2.
Johnson et al. (2019)
J. Johnson, M. Douze, and H. Jégou
Billion-scale similarity search with gpus.
IEEE transactions on big data 7 (3), pp. 535–547.
Cited by: §3.2,
§4.2.
Li et al. (2024)
D. Li, Y. Liu, H. Wu, Y. Wang, Z. Shen, B. Qu, X. Niu, F. Zhou, C. Huang, Y. Li, et al.
Aria: an open multimodal native mixture-of-experts model.
arXiv preprint arXiv:2410.05993.
Cited by: Table 2.
Li et al. (2025)
K. Li, Y. He, Y. Wang, Y. Li, W. Wang, P. Luo, Y. Wang, L. Wang, and Y. Qiao
Videochat: chat-centric video understanding.
Science China Information Sciences 68 (10), pp. 200102.
Cited by: §2.1,
Table 3.
Lin et al. (2024a)
B. Lin, Y. Ye, B. Zhu, J. Cui, M. Ning, P. Jin, and L. Yuan
Video-llava: learning unit