{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T03:38:30Z","timestamp":1775533110895,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,8]]},"DOI":"10.1109\/hsi61632.2024.10613524","type":"proceedings-article","created":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T17:18:16Z","timestamp":1723223896000},"page":"1-4","source":"Crossref","is-referenced-by-count":6,"title":["Towards Retrieval Augmented Generation over Large Video Libraries"],"prefix":"10.1109","author":[{"given":"Yannis","family":"Tevissen","sequence":"first","affiliation":[{"name":"Moments Lab Research,Boulogne- Billancourt,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khalil","family":"Guetari","sequence":"additional","affiliation":[{"name":"Moments Lab Research,Boulogne- Billancourt,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fr\u00e9d\u00e9ric","family":"Petitpont","sequence":"additional","affiliation":[{"name":"Moments Lab Research,Boulogne- Billancourt,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/s11042-024-20016-1","article-title":"Generative Artificial Intelligence: A Systematic Review and Applications","volume-title":"arXiv","author":"Sengar","year":"2024"},{"key":"ref2","article-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Lewis","year":"2020"},{"key":"ref3","article-title":"Retrieval-Augmented Generation for Large Language Models: A Survey","volume-title":"arXiv","author":"Gao","year":"2024"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-63646-2_29","article-title":"CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering","volume-title":"arXiv","author":"Wiratunga","year":"2024"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.findings-acl.372","article-title":"Benchmarking Retrieval-Augmented Generation for Medicine","volume-title":"arXiv","author":"Xiong","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-023-00267-8"},{"key":"ref7","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01262"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00234"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.571"},{"key":"ref12","article-title":"Finding Moments in Video Collections Using Natural Language","volume-title":"arXiv","author":"Escorcia","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.618"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3140611"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00264"},{"key":"ref16","article-title":"iRAG: An Incremental Retrieval Augmented Generation System for Videos","volume-title":"arXiv","author":"Arefeen","year":"2024"},{"key":"ref17","article-title":"The Rise and Potential of Large Language Model Based Agents: A Survey","volume-title":"arXiv","author":"Xi","year":"2023"},{"key":"ref18","article-title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","volume-title":"arXiv","author":"Wang","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645143"},{"key":"ref20","volume-title":"OpenSearch"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"ref22","article-title":"Mixtral of Experts","volume-title":"arXiv","author":"Jiang","year":"2024"},{"key":"ref23","article-title":"Command-R","volume-title":"Cohere"},{"key":"ref24","volume-title":"PySceneDetect"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref26","article-title":"Learning Language-Visual Embedding for Movie Understanding with Natural-Language","volume-title":"arXiv","author":"Torabi","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_46"},{"key":"ref28","article-title":"Video Chat: Chat-Centric Video Understanding","volume-title":"arXiv","author":"Li","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref30","article-title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","author":"Li","year":"2023"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.01357","article-title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","volume-title":"arXiv","author":"Ren","year":"2024"},{"key":"ref32","volume-title":"A Simple LLM Framework for Long-Range Video Question-Answering","author":"Zhang","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref34","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning, in ICML23","author":"Radford","year":"2023"},{"key":"ref35","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref36","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","volume-title":"arXiv","author":"Reid","year":"2024"},{"key":"ref37","author":"Penedo","year":"2024","journal-title":"FineWeb"},{"key":"ref38","article-title":"MTEB: Massive Text Embedding Benchmark","author":"Muennighoff","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"CinePile: A Long Video Question Answering Dataset and Benchmark","volume-title":"arXiv","author":"Rawal","year":"2024"},{"key":"ref40","article-title":"How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs","volume-title":"arXiv","author":"Khattak","year":"2024"},{"key":"ref41","article-title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","author":"Li","year":"2023","journal-title":"arXiv"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.02095","article-title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","volume-title":"arXiv","author":"Li","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531860"}],"event":{"name":"2024 16th International Conference on Human System Interaction (HSI)","location":"Paris, France","start":{"date-parts":[[2024,7,8]]},"end":{"date-parts":[[2024,7,11]]}},"container-title":["2024 16th International Conference on Human System Interaction (HSI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10613508\/10613523\/10613524.pdf?arnumber=10613524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T15:11:35Z","timestamp":1732633895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10613524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/hsi61632.2024.10613524","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]}}}