{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:17:39Z","timestamp":1781587059001,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":41,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3414002","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:53Z","timestamp":1602505613000},"page":"2553-2561","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["A W2VV++ Case Study with Automated and Interactive Text-to-Video Retrieval"],"prefix":"10.1145","author":[{"given":"Jakub","family":"Loko\u0107","sequence":"first","affiliation":[{"name":"Charles University, Prague, Czech Rep"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom\u00e1\u0161","family":"Sou\u0107ek","sequence":"additional","affiliation":[{"name":"Charles University, Prague, Czech Rep"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrik","family":"Vesel\u00fd","sequence":"additional","affiliation":[{"name":"Charles University, Prague, Czech Rep"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franti\u0161ek","family":"Mejzl\u00edk","sequence":"additional","affiliation":[{"name":"Charles University, Prague, Czech Rep"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Ji","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoxi","family":"Xu","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xirong","family":"Li","sequence":"additional","affiliation":[{"name":"Renmin University of China, 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","volume-title":"VERGE in VBS","author":"Andreadis Stelios","year":"2020"},{"key":"e_1_3_2_2_2_1","volume-title":"TRECVID 2018: Benchmarking Video Activity Detection, Video Captioning and Matching, Video Storytelling Linking and Video Search. In Proceedings of TRECVID 2018 . NIST, USA.","author":"Awad George","year":"2018"},{"key":"e_1_3_2_2_3_1","volume-title":"TRECVID 2019: An evaluation campaign to benchmark Video Activity Detection, Video Captioning and Matching, and Video Search & retrieval. In Proceedings of TRECVID 2019. NIST, USA.","author":"Awad George","year":"2019"},{"key":"e_1_3_2_2_4_1","volume-title":"TRECVID 2017: Evaluating Ad-hoc and Instance Video Search, Events Detection, Video Captioning and Hyperlinking. In Proceedings of TRECVID 2017. NIST, USA.","author":"Awad George","year":"2017"},{"key":"e_1_3_2_2_5_1","volume-title":"TRECVID 2016: Evaluating Video Search, Video Event Detection, Localization, and Hyperlinking. In TRECVID .","author":"Awad G."},{"key":"e_1_3_2_2_6_1","volume-title":"MMM 2015, Sydney, NSW, Australia, January 5--7, 2015, Proceedings, Part II. 287--290","author":"Barthel Kai Uwe","year":"2015"},{"key":"e_1_3_2_2_7_1","unstructured":"Kyunghyun Cho Bart van Merrienboer Caglar Gulcehre Dzmitry Bahdanau Fethi Bougares Holger Schwenk and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In EMNLP .  Kyunghyun Cho Bart van Merrienboer Caglar Gulcehre Dzmitry Bahdanau Fethi Bougares Holger Schwenk and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In EMNLP ."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Ingemar J Cox Matthew L Miller Thomas P Minka Thomas V Papathomas and Peter N Yianilos. 2000. The Bayesian image retrieval system PicHunter: theory implementation and psychophysical experiments. IEEE transactions on image processing Vol. 9 1 (2000) 20--37.  Ingemar J Cox Matthew L Miller Thomas P Minka Thomas V Papathomas and Peter N Yianilos. 2000. The Bayesian image retrieval system PicHunter: theory implementation and psychophysical experiments. IEEE transactions on image processing Vol. 9 1 (2000) 20--37.","DOI":"10.1109\/83.817596"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Jianfeng Dong Xirong Li Chaoxi Xu Shouling Ji Yuan He Gang Yang and Xun Wang. 2019. Dual Encoding for Zero-Example Video Retrieval. In CVPR .  Jianfeng Dong Xirong Li Chaoxi Xu Shouling Ji Yuan He Gang Yang and Xun Wang. 2019. Dual Encoding for Zero-Example Video Retrieval. In CVPR .","DOI":"10.1109\/CVPR.2019.00957"},{"key":"e_1_3_2_2_10_1","unstructured":"F. Faghri D. J Fleet J. R. Kiros and S. Fidler. 2018. VSE  F. Faghri D. J Fleet J. R. Kiros and S. Fidler. 2018. VSE"},{"key":"e_1_3_2_2_11_1","unstructured":": Improved visual-semantic embeddings. In BMVC .  : Improved visual-semantic embeddings. In BMVC ."},{"key":"e_1_3_2_2_12_1","unstructured":"Ian Goodfellow Yoshua Bengio and Aaron Courville. 2016. Deep Learning .MIT Press. http:\/\/www.deeplearningbook.org.  Ian Goodfellow Yoshua Bengio and Aaron Courville. 2016. Deep Learning .MIT Press. http:\/\/www.deeplearningbook.org."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.3169\/mta.7.46"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Bj\u00f6rn \u00de\u00f3r J\u00f3nsson Omar Shahbaz Khan Dennis C. Koelma Stevan Rudinac Marcel Worring and Jan Zah\u00e1lka. 2020. Exquisitor at the Video Browser Showdown 2020. In MultiMedia Modeling Yong Man Ro Wen-Huang Cheng Junmo Kim Wei-Ta Chu Peng Cui Jung-Woo Choi Min-Chun Hu and Wesley De Neve (Eds.). Springer International Publishing Cham 796--802.  Bj\u00f6rn \u00de\u00f3r J\u00f3nsson Omar Shahbaz Khan Dennis C. Koelma Stevan Rudinac Marcel Worring and Jan Zah\u00e1lka. 2020. Exquisitor at the Video Browser Showdown 2020. In MultiMedia Modeling Yong Man Ro Wen-Huang Cheng Junmo Kim Wei-Ta Chu Peng Cui Jung-Woo Choi Min-Chun Hu and Wesley De Neve (Eds.). Springer International Publishing Cham 796--802.","DOI":"10.1007\/978-3-030-37734-2_72"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Miroslav Kratochv\u00edl Patrik Vesel\u00fd Frantivs ek Mejzl\u00edk and Jakub Lokovc. 2020. SOM-Hunter: Video Browsing with Relevance-to-SOM Feedback Loop. In MultiMedia Modeling Yong Man Ro Wen-Huang Cheng Junmo Kim Wei-Ta Chu Peng Cui Jung-Woo Choi Min-Chun Hu and Wesley De Neve (Eds.). Springer International Publishing Cham 790--795.  Miroslav Kratochv\u00edl Patrik Vesel\u00fd Frantivs ek Mejzl\u00edk and Jakub Lokovc. 2020. SOM-Hunter: Video Browsing with Relevance-to-SOM Feedback Loop. In MultiMedia Modeling Yong Man Ro Wen-Huang Cheng Junmo Kim Wei-Ta Chu Peng Cui Jung-Woo Choi Min-Chun Hu and Wesley De Neve (Eds.). Springer International Publishing Cham 790--795.","DOI":"10.1007\/978-3-030-37734-2_71"},{"key":"e_1_3_2_2_16_1","volume-title":"MultiMedia Modeling , , Yong Man Ro, Wen-Huang Cheng, Junmo Kim, Wei-Ta Chu, Peng Cui, Jung-Woo Choi, Min-Chun Hu","author":"Le Nguyen-Khang"},{"key":"e_1_3_2_2_17_1","volume-title":"MultiMedia Modeling, Yong Man Ro, Wen-Huang Cheng, Junmo Kim, Wei-Ta Chu, Peng Cui, Jung-Woo Choi, Min-Chun Hu","author":"Leibetseder Andreas"},{"key":"e_1_3_2_2_18_1","volume-title":"TRECVID 2018 Workshop .","author":"Li Xirong","year":"2018"},{"key":"e_1_3_2_2_19_1","unstructured":"Xirong Li Chaoxi Xu Gang Yang Zhineng Chen and Jianfeng Dong. 2019 a. W2VV  Xirong Li Chaoxi Xu Gang Yang Zhineng Chen and Jianfeng Dong. 2019 a. W2VV"},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the 27th ACM International Conference on Multimedia, MM 2019","year":"2019"},{"key":"e_1_3_2_2_21_1","unstructured":"Xirong Li Jinde Ye Chaoxi Xu Shanjinwen Yun Leimin Zhang Xun Wang Rui Qian and Jianfeng Dong. 2019 b. Renmin University of China and Zhejiang Gongshang University at TRECVID 2019: Learn to Search and Describe Videos. In TRECVID .  Xirong Li Jinde Ye Chaoxi Xu Shanjinwen Yun Leimin Zhang Xun Wang Rui Qian and Jianfeng Dong. 2019 b. Renmin University of China and Zhejiang Gongshang University at TRECVID 2019: Learn to Search and Describe Videos. In TRECVID ."},{"key":"e_1_3_2_2_22_1","volume-title":"TGIF: A New Dataset and Benchmark on Animated GIF Description. In CVPR .","author":"Li Y.","year":"2016"},{"key":"e_1_3_2_2_23_1","unstructured":"Y. Liu S. Albanie A. Nagrani and A. Zisserman. 2019 a. Use What You Have: Video Retrieval Using Representations From Collaborative Experts. In BMVC .  Y. Liu S. Albanie A. Nagrani and A. Zisserman. 2019 a. Use What You Have: Video Retrieval Using Representations From Collaborative Experts. In BMVC ."},{"key":"e_1_3_2_2_24_1","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019 b. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR Vol. abs\/1907.11692 (2019). arxiv: 1907.11692 http:\/\/arxiv.org\/abs\/1907.11692  Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019 b. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR Vol. abs\/1907.11692 (2019). arxiv: 1907.11692 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Jakub Lokovc Gregor Kovalvc \u00edk and Tom\u00e1vs Souvc ek. 2020. VIRET at Video Browser Showdown 2020. In MultiMedia Modeling Yong Man Ro Wen-Huang Cheng Junmo Kim Wei-Ta Chu Peng Cui Jung-Woo Choi Min-Chun Hu and Wesley De Neve (Eds.). Springer International Publishing Cham 784--789.  Jakub Lokovc Gregor Kovalvc \u00edk and Tom\u00e1vs Souvc ek. 2020. VIRET at Video Browser Showdown 2020. In MultiMedia Modeling Yong Man Ro Wen-Huang Cheng Junmo Kim Wei-Ta Chu Peng Cui Jung-Woo Choi Min-Chun Hu and Wesley De Neve (Eds.). Springer International Publishing Cham 784--789.","DOI":"10.1007\/978-3-030-37734-2_70"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2830110"},{"key":"e_1_3_2_2_27_1","article-title":"a. Interactive Search or Sequential Browsing? A Detailed Analysis of the Video Browser Showdown 2018","volume":"15","author":"Lokovc Jakub","year":"2019","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351046"},{"key":"e_1_3_2_2_29_1","unstructured":"Yi-Jie Lu Hao Zhang Maaike de Boer and Chong-Wah Ngo. 2016. Event Detection with Zero Example: Select the Right and Suppress the Wrong Concepts. In ICMR .  Yi-Jie Lu Hao Zhang Maaike de Boer and Chong-Wah Ngo. 2016. Event Detection with Zero Example: Select the Right and Suppress the Wrong Concepts. In ICMR ."},{"key":"e_1_3_2_2_30_1","unstructured":"T. Mikolov K. Chen G. Corrado and J. Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In ICLR .  T. Mikolov K. Chen G. Corrado and J. Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In ICLR ."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-018-00166-3"},{"key":"e_1_3_2_2_32_1","volume-title":"MultiMedia Modeling , , Yong Man Ro, Wen-Huang Cheng, Junmo Kim, Wei-Ta Chu, Peng Cui, Jung-Woo Choi, Min-Chun Hu","author":"Nguyen Phuong Anh"},{"key":"e_1_3_2_2_33_1","volume-title":"IVIST: Interactive VIdeo Search Tool in VBS","author":"Park Sungjune","year":"2020"},{"key":"e_1_3_2_2_34_1","volume-title":"Interactive Video Retrieval in the Age of Deep Learning - Detailed Evaluation of VBS 2019","author":"Rossetto L.","year":"2020"},{"key":"e_1_3_2_2_35_1","volume-title":"MMM 2019, Thessaloniki, Greece, January 8--11, 2019, Proceedings, Part I. 349--360","author":"Rossetto Luca"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Loris Sauter Mahnaz Amiri Parian Ralph Gasser Silvan Heller Luca Rossetto and Heiko Schuldt. 2020. Combining Boolean and Multimedia Retrieval in vitrivr for Large-Scale Video Search. In MultiMedia Modeling Yong Man Ro Wen-Huang Cheng Junmo Kim Wei-Ta Chu Peng Cui Jung-Woo Choi Min-Chun Hu and Wesley De Neve (Eds.). Springer International Publishing Cham 760--765.  Loris Sauter Mahnaz Amiri Parian Ralph Gasser Silvan Heller Luca Rossetto and Heiko Schuldt. 2020. Combining Boolean and Multimedia Retrieval in vitrivr for Large-Scale Video Search. In MultiMedia Modeling Yong Man Ro Wen-Huang Cheng Junmo Kim Wei-Ta Chu Peng Cui Jung-Woo Choi Min-Chun Hu and Wesley De Neve (Eds.). Springer International Publishing Cham 760--765.","DOI":"10.1007\/978-3-030-37734-2_66"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2808796"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000014"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-012-0014-4"},{"key":"e_1_3_2_2_40_1","unstructured":"X. Wu D. Chen Y. He H. Xue M. Song and F. Mao. 2019. Hybrid Sequence Encoder For Text Based Video Retrieval. In TRECVID .  X. Wu D. Chen Y. He H. Xue M. Song and F. Mao. 2019. Hybrid Sequence Encoder For Text Based Video Retrieval. In TRECVID ."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"J. Xu T. Mei T. Yao and Y. Rui. 2016. MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In CVPR .  J. Xu T. Mei T. Yao and Y. Rui. 2016. MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In CVPR .","DOI":"10.1109\/CVPR.2016.571"}],"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\/3394171.3414002","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3414002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:07Z","timestamp":1750195927000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3414002"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":41,"alternative-id":["10.1145\/3394171.3414002","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3414002","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"}}]}}