{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:35:32Z","timestamp":1781613332312,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Ministry of Education-China Mobile Research Foundation Project","award":["2016\/2-7"],"award-info":[{"award-number":["2016\/2-7"]}]},{"name":"National Key Research and Development Program of China","award":["No.2019YFB1406302"],"award-info":[{"award-number":["No.2019YFB1406302"]}]},{"name":"National Natural Science Foundation of China","award":["No. 61370137"],"award-info":[{"award-number":["No. 61370137"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413498","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:27:35Z","timestamp":1602505655000},"page":"4355-4363","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Learning Semantic Concepts and Temporal Alignment for Narrated Video Procedural Captioning"],"prefix":"10.1145","author":[{"given":"Botian","family":"Shi","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Ji","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhendong","family":"Niu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Duan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences & Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie . 2005 . METEOR: An automatic metric for MT evaluation with improved correlation with human judgments . In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72 . Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding . In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , Volume 1 (Long and Short Papers). 4171--4186. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171--4186."},{"key":"e_1_3_2_2_5_1","unstructured":"Li Dong Nan Yang Wenhui Wang Furu Wei Xiaodong Liu Yu Wang Jianfeng Gao Ming Zhou and Hsiao-Wuen Hon. 2019. Unified Language Model Pretraining for Natural Language Understanding and Generation. (2019) 13063-- 13075. http:\/\/papers.nips.cc\/paper\/9464-unified-language-model-pre-trainingfor- natural-language-understanding-and-generation.pdf  Li Dong Nan Yang Wenhui Wang Furu Wei Xiaodong Liu Yu Wang Jianfeng Gao Ming Zhou and Hsiao-Wuen Hon. 2019. Unified Language Model Pretraining for Natural Language Understanding and Generation. (2019) 13063-- 13075. http:\/\/papers.nips.cc\/paper\/9464-unified-language-model-pre-trainingfor- natural-language-understanding-and-generation.pdf"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1039"},{"key":"e_1_3_2_2_9_1","volume-title":"Dense Multimodal Fusion for Hierarchically Joint Representation. In ICASSP 2019--2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 3941--3945","author":"Hu Di","year":"2019","unstructured":"Di Hu , Chengze Wang , Feiping Nie , and Xuelong Li . 2019 . Dense Multimodal Fusion for Hierarchically Joint Representation. In ICASSP 2019--2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 3941--3945 . Di Hu, Chengze Wang, Feiping Nie, and Xuelong Li. 2019. Dense Multimodal Fusion for Hierarchically Joint Representation. In ICASSP 2019--2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 3941--3945."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_2_11_1","volume-title":"Adam: A Method for Stochastic Optimization. International Conference on Learning Representations","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba . 2015 . Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (2015). Diederik P Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (2015)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1015"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1017"},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni , Salim Roukos , Todd Ward , and Wei-Jing Zhu . 2002 . BLEU: a method for automatic evaluation of machine translation . In Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318 . Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1641"},{"key":"e_1_3_2_2_20_1","volume-title":"Contrastive Bidirectional Transformer for Temporal Representation Learning. arXiv preprint arXiv:1906.05743","author":"Sun Chen","year":"2019","unstructured":"Chen Sun , Fabien Baradel , Kevin Murphy , and Cordelia Schmid . 2019. Contrastive Bidirectional Transformer for Temporal Representation Learning. arXiv preprint arXiv:1906.05743 ( 2019 ). Chen Sun, Fabien Baradel, Kevin Murphy, and Cordelia Schmid. 2019. Contrastive Bidirectional Transformer for Temporal Representation Learning. arXiv preprint arXiv:1906.05743 (2019)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_2_22_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1197"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00629"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413498","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:12Z","timestamp":1750193232000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":31,"alternative-id":["10.1145\/3394171.3413498","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413498","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}