{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:42:40Z","timestamp":1777657360889,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755484","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:47:42Z","timestamp":1761371262000},"page":"4514-4523","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8623-0976","authenticated-orcid":false,"given":"Hongxu","family":"Ma","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6391-4385","authenticated-orcid":false,"given":"Guanshuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4062-696X","authenticated-orcid":false,"given":"Fufu","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9576-6559","authenticated-orcid":false,"given":"Qiong","family":"Jia","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3175-3553","authenticated-orcid":false,"given":"Shouhong","family":"Ding","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01365"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_12"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"e_1_3_2_1_7_1","unstructured":"Victor Escorcia Mattia Soldan Josef Sivic Bernard Ghanem and Bryan Russell. 2019. Temporal localization of moments in video collections with natural language. (2019)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_1_10_1","first-page":"245","article-title":"Mac: Mining activity concepts for language-based temporal localization. In 2019 IEEE winter conference on applications of computer vision (WACV)","author":"Ge Runzhou","year":"2019","unstructured":"Runzhou Ge, Jiyang Gao, Kan Chen, and Ram Nevatia. 2019. Mac: Mining activity concepts for language-based temporal localization. In 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, 245-253.","journal-title":"IEEE"},{"key":"e_1_3_2_1_11_1","volume-title":"Excl: Extractive clip localization using natural language descriptions. arXiv preprint arXiv:1904.02755","author":"Ghosh Soham","year":"2019","unstructured":"Soham Ghosh, Anuva Agarwal, Zarana Parekh, and Alexander Hauptmann. 2019. Excl: Extractive clip localization using natural language descriptions. arXiv preprint arXiv:1904.02755 (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.114"},{"key":"e_1_3_2_1_13_1","volume-title":"Mini-net: Multiple instance ranking network for video highlight detection. In Computer Vision-ECCV 2020: 16th European Conference","author":"Hong Fa-Ting","year":"2020","unstructured":"Fa-Ting Hong, Xuanteng Huang, Wei-Hong Li, and Wei-Shi Zheng. 2020. Mini-net: Multiple instance ranking network for video highlight detection. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XIII 16. Springer, 345-360."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR, 4904-4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904-4916."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2017.141"},{"key":"e_1_3_2_1_18_1","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei Jie","year":"2021","unstructured":"Jie Lei, Tamara L Berg, and Mohit Bansal. 2021. Detecting moments and highlights in videos via natural language queries. Advances in Neural Information Processing Systems, Vol. 34 (2021), 11846-11858.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"Tvr: A large-scale dataset for video-subtitle moment retrieval. In Computer Vision-ECCV 2020: 16th European Conference","author":"Lei Jie","year":"2020","unstructured":"Jie Lei, Licheng Yu, Tamara L Berg, and Mohit Bansal. 2020. Tvr: A large-scale dataset for video-subtitle moment retrieval. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXI 16. Springer, 447-463."},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_21_1","volume-title":"From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs. arXiv preprint arXiv:2502.09093","author":"Li Mingxiao","year":"2025","unstructured":"Mingxiao Li, Fang Qu, Zhanpeng Chen, Na Su, Zhizhou Zhong, Ziyang Chen, Nan Du, and Xiaolong Li. 2025a. From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs. arXiv preprint arXiv:2502.09093 (2025)."},{"key":"e_1_3_2_1_22_1","volume-title":"VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization. arXiv preprint arXiv:2505.10917","author":"Li Mingxiao","year":"2025","unstructured":"Mingxiao Li, Na Su, Fang Qu, Zhizhou Zhong, Ziyang Chen, Yuan Li, Zhaopeng Tu, and Xiaolong Li. 2025b. VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization. arXiv preprint arXiv:2505.10917 (2025)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"e_1_3_2_1_24_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00614"},{"key":"e_1_3_2_1_29_1","unstructured":"Hongxu Ma Kai Tian Tao Zhang Xuefeng Zhang Han Zhou Chunjie Chen Han Li Jihong Guan and Shuigeng Zhou. 2025. Generative Regression Based Watch Time Prediction for Short-Video Recommendation. arXiv:2412.20211 [cs.LG]"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00297"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01975"},{"key":"e_1_3_2_1_33_1","volume-title":"Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Grounding. arXiv preprint arXiv:2311.08835","author":"Moon WonJun","year":"2023","unstructured":"WonJun Moon, Sangeek Hyun, SuBeen Lee, and Jae-Pil Heo. 2023a. Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Grounding. arXiv preprint arXiv:2311.08835 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.395"},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983349"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 5179-5187","author":"Song Yale","year":"2015","unstructured":"Yale Song, Jordi Vallmitjana, Amanda Stent, and Alejandro Jaimes. 2015. Tvsum: Summarizing web videos using titles. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5179-5187."},{"key":"e_1_3_2_1_43_1","volume-title":"TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection. arXiv preprint arXiv:2401.02309","author":"Sun Hao","year":"2024","unstructured":"Hao Sun, Mingyao Zhou, Wenjing Chen, and Wei Xie. 2024. TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection. arXiv preprint arXiv:2401.02309 (2024)."},{"key":"e_1_3_2_1_44_1","first-page":"787","volume-title":"Zurich","author":"Sun Min","year":"2014","unstructured":"Min Sun, Ali Farhadi, and Steve Seitz. 2014. Ranking domain-specific highlights by analyzing edited videos. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13. Springer, 787-802."},{"key":"e_1_3_2_1_45_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_18"},{"key":"e_1_3_2_1_47_1","volume-title":"Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection. arXiv preprint arXiv:2311.16464","author":"Xiao Yicheng","year":"2023","unstructured":"Yicheng Xiao, Zhuoyan Luo, Yong Liu, Yue Ma, Hengwei Bian, Yatai Ji, Yujiu Yang, and Xiu Li. 2023. Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection. arXiv preprint arXiv:2311.16464 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"e_1_3_2_1_51_1","volume-title":"Mh-detr: Video moment and highlight detection with cross-modal transformer. arXiv preprint arXiv:2305.00355","author":"Xu Yifang","year":"2023","unstructured":"Yifang Xu, Yunzhuo Sun, Yang Li, Yilei Shi, Xiaoxiang Zhu, and Sidan Du. 2023. Mh-detr: Video moment and highlight detection with cross-modal transformer. arXiv preprint arXiv:2305.00355 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"2nd Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ ICML","author":"Xu Zunnan","year":"2024","unstructured":"Zunnan Xu, Jiaqi Huang, Ting Liu, Yong Liu, Haonan Han, Kehong Yuan, and Xiu Li. 2024. Enhancing fine-grained multi-modal alignment via adapters: a parameter-efficient training framework for referring image segmentation. In 2nd Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ ICML 2024)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01483"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00785"},{"key":"e_1_3_2_1_56_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Yuan Yitian","year":"2019","unstructured":"Yitian Yuan, Lin Ma, Jingwen Wang, Wei Liu, and Wenwu Zhu. 2019. Semantic conditioned dynamic modulation for temporal sentence grounding in videos. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"e_1_3_2_1_58_1","volume-title":"Learning Implicit Features with Flow Infused Attention for Realistic Virtual Try-On. arXiv preprint arXiv:2412.11435","author":"Zhang Delong","year":"2024","unstructured":"Delong Zhang, Qiwei Huang, Yuanliu Liu, Yang Sun, Wei-Shi Zheng, Pengfei Xiong, and Wei Zhang. 2024a. Learning Implicit Features with Flow Infused Attention for Realistic Virtual Try-On. arXiv preprint arXiv:2412.11435 (2024)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681262"},{"key":"e_1_3_2_1_60_1","volume-title":"Joey Tianyi Zhou, and Rick Siow Mong Goh","author":"Zhang Hao","year":"2021","unstructured":"Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, and Rick Siow Mong Goh. 2021. Natural language video localization: A revisit in span-based question answering framework. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 8 (2021), 4252-4266."},{"key":"e_1_3_2_1_61_1","volume-title":"Span-based localizing network for natural language video localization. arXiv preprint arXiv:2004.13931","author":"Zhang Hao","year":"2020","unstructured":"Hao Zhang, Aixin Sun, Wei Jing, and Joey Tianyi Zhou. 2020b. Span-based localizing network for natural language video localization. arXiv preprint arXiv:2004.13931 (2020)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"e_1_3_2_1_64_1","volume-title":"Musetalk: Real-time high quality lip synchronization with latent space inpainting. arXiv preprint arXiv:2410.10122","author":"Zhang Yue","year":"2024","unstructured":"Yue Zhang, Zhizhou Zhong, Minhao Liu, Zhaokang Chen, Bin Wu, Yubin Zeng, Chao Zhan, Junxin Huang, Yingjie He, and Wenjiang Zhou. 2024c. Musetalk: Real-time high quality lip synchronization with latent space inpainting. arXiv preprint arXiv:2410.10122 (2024)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:17:24Z","timestamp":1765307844000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755484"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":65,"alternative-id":["10.1145\/3746027.3755484","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755484","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}