Event-Causal RAG (EC‑RAG) is a lightweight retrieval‑augmented framework designed for reasoning over ultra‑long and streaming videos. It segments video streams into semantically complete events using a dual visual‑audio sentinel mechanism, representing each event as a State‑Event‑State (SES) structure that captures pre‑event, event, and post‑event states. During question answering, bidirectional graph retrieval accesses relevant predecessor and successor events from a dual vector‑graph memory, and answers are generated using both this structured memory and the corresponding video evidence. The authors also introduce ECV‑1H, an hour‑scale long‑video QA benchmark with over 150 hours of untrimmed video and 1,251 human‑annotated QA pairs, where EC‑RAG achieves significant accuracy gains across multiple video foundation models while maintaining efficient streaming memory usage on a single RTX 5090 GPU.
By Peizheng Yan, Yu Zhao, Liang Xie, Juntong Qi, Mingming Wang, Erwei Yin
arXiv:2609.00551v1 Announce Type: cross
Abstract: Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, s...
By Yijun Chen, Yaqi Zheng, Yanya Li, Boyi Xiao, Buqiang Xu, Shuofei Qiao, Jizhan Fang, Xinle Deng, Yunzhi Yao, Xuehai Wang, Liuxin Zhang, Hui Li, Huajun Chen, Shumin Deng
arXiv:2606. 19627v1 Announce Type: cross Abstract: The digital commerce landscape is shifting from static, search-driven catalogs to dynamic, immersive video feeds.
By Katya Mirylenka, Egor Malykh, Mahdyar Ravanbakhsh, Michael Gygli, Marco-Andrea Buchmann, Andrew Dzhoha, Svitlana Borzenko, Francesca Catino, Mohamed Gaafar, Maarten Versteegh, Thomas Kober, Dario d'Andrea, Ellie Langhans
ShotFinder introduces a new benchmark for open‑domain video shot retrieval, formalizing editing requirements as keyframe‑oriented shot descriptions and adding five controllable constraints—temporal order, color, visual style, audio, and resolution. The benchmark comprises 1,210 high‑quality YouTube samples across 20 themes, generated with large models and verified by humans. A three‑stage retrieval pipeline—query expansion via video imagination, candidate video retrieval, and description‑guided shot localization—shows a notable performance gap to humans, especially for color and visual style constraints.
By Tao Yu, Haopeng Jin, Hao Wang, Shenghua Chai, Yujia Yang, Junhao Gong, Jiaming Guo, Minghui Zhang, Xinlong Chen, Zhenghao Zhang, Yuxuan Zhou, Yufei Xiong, Shanbin Zhang, Jiabing Yang, YiFan Zhang, Hongzhu Yi, Xinming Wang, Cheng Zhong, Xiao Ma, Zhang Zhang, Yan Huang, Liang Wang
arXiv:2608. 07663v1 Announce Type: cross Abstract: When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs).
By Yeeun Choi, Youngbeom Yoo, Joon-Young Lee, Hyolim Kang, Seon Joo Kim
arXiv:2602.19001v2 Announce Type: replace
Abstract: As large language models increasingly power personal assistants, users expect them to reason over multimodal life histories, from recognizing peopl...
By Xia Hu, Honglei Zhuang, Brian Potetz, Alireza Fathi, Bo Hu, Babak Samari, Howard Zhou
arXiv:2606. 07433v1 Announce Type: cross Abstract: Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios.
By Jiahao Meng, Yue Tan, Qi Xu, Kuan Gao, Weisong Liu, Yanwei Li, Jason Li, Lingdong Kong, Haochen Wang, Qianyu Zhou, Jiangning Zhang, Guangliang Cheng, Yunhai Tong, Lu Qi, Minghsuan Yang
TimeBlind is a diagnostic benchmark designed to evaluate fine‑grained spatio‑temporal compositionality in video large language models (LLMs). It categorizes temporal understanding into three levels—atomic event recognition, event property characterization, and reasoning about event interdependencies—and uses a minimal‑pairs paradigm where video pairs share identical static content but differ only in temporal structure. Across 20 state‑of‑the‑art MLLMs tested on 600 curated instances, the best model achieved only 48.2% instance accuracy, far below human performance of 98.2%, highlighting a reliance on static visual shortcuts rather than true temporal reasoning.
By Baiqi Li, Kangyi Zhao, Ce Zhang, Chancharik Mitra, Jean de Dieu Nyandwi, Gedas Bertasius
arXiv:2607. 25266v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible.
By Ghazal Kaviani, Ghassan AlRegib
VidOmni-Bench is a new benchmark for fine‑grained video understanding that asks models to verify whether each event in dense video captions is supported by the video. It contains 500 videos covering five complexity types and durations from 4 seconds to 90 minutes, and uses human‑verified sentence‑level labels to create hard negatives. Experiments show that Video‑LLMs often hallucinate events, struggle to detect incorrect descriptions, and exhibit varying weaknesses depending on video complexity and duration.
By Changbeen Kim, Junwon Chang, Kipyo Kim, Risa Shinoda, Kuniaki Saito, Donghyun Kim
arXiv:2606. 03635v1 Announce Type: cross Abstract: Understanding short online videos involves more than identifying visible objects and actions; video makers often include an underlying message or purpose in the clip.
By Issar Tzachor, Michael Green, Rami Ben-Ari
arXiv:2608.24845v1 Announce Type: cross
Abstract: We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific video URLs collected from Commo...
By Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti, Andrej Radonjic, Thadd\"aus Wiedemer, Christoph Schuhmann, Romain Beaumont, Wieland Brendel, Bernhard Sch\"olkopf, A. Sophia Koepke, Jenia Jitsev, Matthias Bethge