I know why you like this movie: Interpretable Efficient Multimodal Recommender
专题命中 视频多模态 :multimodal(title,abstract)
AI 大模型
跨文本、图像、视频、音频等模态的大模型与学习方法。
专题命中 视频多模态 :multimodal(title,abstract)
专题命中 视频多模态 :multi-modal(title,abstract)
Comments RA-L with presentation at ICRA 2020
Journal ref IEEE ROBOTICS AND AUTOMATION LETTERS, VOL. 5, NO. 3, JULY 2020. 3791-3798
专题命中 视频多模态 :multi-modal(title);分类 cs.CV、cs.MM、eess.AS
Journal ref In Proceedings of the 11th ACM Multimedia Systems Conference (MMSys2020), June 06-11, 2020, Istanbul, Turkey
专题命中 视频多模态 :multimodal(title,abstract)
Comments to appear in IEEE/IFIP International Workshop on Analytics for Network and Service Management (AnNet 2020)
专题命中 视频多模态 :multimodal(title,abstract)
Comments 18 pages, 9 figures, Intelligent System Conference (Intellisys 2020 - Accepted)
专题命中 视频多模态 :multi-modal(title,abstract)
Comments Journal article published in MDPI Brain Sciences. arXiv admin note: text overlap with arXiv:1905.00503
专题命中 视频多模态 :multi-modal(title,abstract)
Comments 15 pages, 5 figures
专题命中 视频多模态 :multi-modal(title,abstract)
专题命中 视频多模态 :multimodal(title,abstract)
Comments 5 figures, 1 table, 1 supplementary figure, 2 supplementary tables
Journal ref Network Neuroscience 2019
专题命中 视频多模态 :multi-modal(title,abstract)
Comments Accepted for publication in IEEE Transactions on Affective Computing. This version on the arXiv is the updated version of the same manuscript
专题命中 视频多模态 :multi-modal(title,abstract)
Journal ref The 2019 International Conference on Robotics and Automation (ICRA)
专题命中 视频多模态 :multimodal(title,abstract)
Journal ref SPIE Defense+Security 2018
专题命中 视频多模态 :multimodal(title,abstract)
专题命中 视频多模态 :multimodal(title,abstract)
专题命中 视频多模态 :multimodal(title,abstract)
Comments 25 pages, 6 figures
专题命中 视频多模态 :multimodal(title,abstract)
Comments IEEE Transactions on Affective Computing 2018
专题命中 视频多模态 :multi-modal(title,abstract)
Comments Published in IEEE 40th International Engineering in Medicine and Biology Conference (EMBC) 2018
专题命中 视频多模态 :multimodal(title,abstract)
专题命中 视频多模态 :multimodal(title,abstract)
Comments 14 pages, 14 figures, IEEE Transactions on Cognitive and Developmental Systems, 2017
专题命中 视频多模态 :multi-modal(title,abstract)
Comments Paper accepted to NIPS 2017
专题命中 视频多模态 :multi-modal(title,abstract)
Comments Video: https://www.youtube.com/watch?v=N1IhHHkUzYg Dataset: http://www2.informatik.uni-freiburg.de/~radwann/freiburg_street_crossing_dataset.html
专题命中 视频多模态 :multimodal(title,abstract)
Comments 11 pages, 4 figures
Journal ref Journal of Next Generation Information Technology (JNIT), Volume 3, Number 1, November 2012
专题命中 视频多模态 :multimodal(title,abstract)
Comments 15 pages, 11 figures
专题命中 视频多模态 :multimodal(title,abstract)
专题命中 视频多模态 :multimodal(title,abstract)
专题命中 视频多模态 :multimodal(title,abstract)
专题命中 视频多模态 :multimodal(title,abstract)
Comments The 30th AAAI Conference on Artificial Intelligence (AAAI-16)
专题命中 视频多模态 :multimodal(title,abstract)
Comments 9 pages, 7 figures +supplementary information (9 pages and 9 figures)
Journal ref Scientific Reports 4:6911 (2014)
专题命中 视频多模态 :multimodal(title,abstract)
Comments NIPS 2013
CRAFT: 基于批评的自适应关键帧目标定位用于多模态视频问答
机构 * University at Buffalo(布法罗大学) ; New York University(纽约大学)
专题命中 视频多模态 :multimodal(title,comments);分类 cs.CV、cs.AI
AI总结 该研究提出CRAFT方法,通过动态关键帧选择、每视频ASR与多语言回退以及混合批评循环,迭代验证和修复声明,最终实现多模态视频问答的准确证据聚合。
Comments Accepted at ACL 2026 Multimodal Augmented Generation via MultimodAl Retrieval Workshop