{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T06:04:06Z","timestamp":1777615446710,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Guangdong Natural Science Funds for Distinguished Young Scholar","award":["2017A030306028"],"award-info":[{"award-number":["2017A030306028"]}]},{"name":"Guangdong special branch plans young talent with scientific and technological innovation","award":["2017TQ04X866"],"award-info":[{"award-number":["2017TQ04X866"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076263"],"award-info":[{"award-number":["62076263"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3487553.3524214","type":"proceedings-article","created":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T22:41:30Z","timestamp":1660689690000},"page":"94-98","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Semantic IR fused Heterogeneous Graph Model in Tag-based Video Search"],"prefix":"10.1145","author":[{"given":"Liming","family":"Gao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongliang","family":"Liao","sequence":"additional","affiliation":[{"name":"Tencent Inc., China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongfu","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Inc., China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Future Technology, South China University of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hankz Hankui","family":"Zhuo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,8,16]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Collecting Highly Parallel Data for Paraphrase Evaluation. In The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference","author":"L.","year":"2011","unstructured":"David\u00a0 L. Chen and William\u00a0B. Dolan. 2011 . Collecting Highly Parallel Data for Paraphrase Evaluation. In The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference , 19-24 June , 2011 , Portland, Oregon, USA, Dekang Lin, Yuji Matsumoto, and Rada Mihalcea (Eds.). The Association for Computer Linguistics, 190\u2013200. https:\/\/aclanthology.org\/P11-1020\/ David\u00a0L. Chen and William\u00a0B. Dolan. 2011. Collecting Highly Parallel Data for Paraphrase Evaluation. In The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, 19-24 June, 2011, Portland, Oregon, USA, Dekang Lin, Yuji Matsumoto, and Rada Mihalcea (Eds.). The Association for Computer Linguistics, 190\u2013200. https:\/\/aclanthology.org\/P11-1020\/"},{"key":"e_1_3_2_1_2_1","volume-title":"Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Chen Shizhe","year":"2020","unstructured":"Shizhe Chen , Yida Zhao , Qin Jin , and Qi Wu . 2020 . Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 , Seattle, WA, USA , June 13-19, 2020. Computer Vision Foundation \/ IEEE, 10635\u201310644. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01065 10.1109\/CVPR42600.2020.01065 Shizhe Chen, Yida Zhao, Qin Jin, and Qi Wu. 2020. Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. Computer Vision Foundation \/ IEEE, 10635\u201310644. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01065"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277784"},{"key":"e_1_3_2_1_4_1","volume-title":"Dual Encoding for Zero-Example Video Retrieval. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019","author":"Dong Jianfeng","year":"2019","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 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019 , Long Beach, CA, USA , June 16-20, 2019. Computer Vision Foundation \/ IEEE, 9346\u20139355. https:\/\/doi.org\/10.1109\/CVPR.2019.00957 10.1109\/CVPR.2019.00957 Jianfeng Dong, Xirong Li, Chaoxi Xu, Shouling Ji, Yuan He, Gang Yang, and Xun Wang. 2019. Dual Encoding for Zero-Example Video Retrieval. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. Computer Vision Foundation \/ IEEE, 9346\u20139355. https:\/\/doi.org\/10.1109\/CVPR.2019.00957"},{"key":"e_1_3_2_1_5_1","volume-title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems","author":"Ging Simon","year":"2020","unstructured":"Simon Ging , Mohammadreza Zolfaghari , Hamed Pirsiavash , and Thomas Brox . 2020 . COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds .). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/ff0abbcc0227c9124a804b084d161a2d-Abstract.html Simon Ging, Mohammadreza Zolfaghari, Hamed Pirsiavash, and Thomas Brox. 2020. COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/ff0abbcc0227c9124a804b084d161a2d-Abstract.html"},{"key":"e_1_3_2_1_6_1","volume-title":"Localizing Moments in Video with Natural Language. In IEEE International Conference on Computer Vision, ICCV 2017","author":"Hendricks Lisa\u00a0Anne","year":"2017","unstructured":"Lisa\u00a0Anne Hendricks , Oliver Wang , Eli Shechtman , Josef Sivic , Trevor Darrell , and Bryan\u00a0 C. Russell . 2017 . Localizing Moments in Video with Natural Language. In IEEE International Conference on Computer Vision, ICCV 2017 , Venice, Italy , October 22-29, 2017. IEEE Computer Society, 5804\u20135813. https:\/\/doi.org\/10.1109\/ICCV.2017.618 10.1109\/ICCV.2017.618 Lisa\u00a0Anne Hendricks, Oliver Wang, Eli Shechtman, Josef Sivic, Trevor Darrell, and Bryan\u00a0C. Russell. 2017. Localizing Moments in Video with Natural Language. In IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017. IEEE Computer Society, 5804\u20135813. https:\/\/doi.org\/10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654918"},{"key":"e_1_3_2_1_8_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014).","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0 P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014). Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390393"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912015"},{"key":"e_1_3_2_1_11_1","unstructured":"Huaishao Luo Lei Ji Ming Zhong Yang Chen Wen Lei Nan Duan and Tianrui Li. 2021. CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval. CoRR abs\/2104.08860(2021). arxiv:2104.08860https:\/\/arxiv.org\/abs\/2104.08860  Huaishao Luo Lei Ji Ming Zhong Yang Chen Wen Lei Nan Duan and Tianrui Li. 2021. CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval. CoRR abs\/2104.08860(2021). arxiv:2104.08860https:\/\/arxiv.org\/abs\/2104.08860"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"e_1_3_2_1_13_1","volume-title":"MCPR 2021, Mexico City, Mexico, June 23-26, 2021, Proceedings(Lecture Notes in Computer Science, Vol.\u00a012725)","author":"Portillo-Quintero Jes\u00fas\u00a0Andr\u00e9s","year":"2021","unstructured":"Jes\u00fas\u00a0Andr\u00e9s Portillo-Quintero , Jos\u00e9\u00a0Carlos Ortiz-Bayliss , and Hugo Terashima-Mar\u00edn . 2021 . A Straightforward Framework for Video Retrieval Using CLIP. In Pattern Recognition - 13th Mexican Conference , MCPR 2021, Mexico City, Mexico, June 23-26, 2021, Proceedings(Lecture Notes in Computer Science, Vol.\u00a012725) , Edgar Roman-Rangel, \u00c1ngel Fernando\u00a0Kuri Morales, Jos\u00e9 Francisco\u00a0Mart\u00ednez Trinidad, Jes\u00fas\u00a0Ariel Carrasco-Ochoa, and Jos\u00e9\u00a0Arturo Olvera-L\u00f3pez (Eds.). Springer, 3\u201312. https:\/\/doi.org\/10.1007\/978-3-030-77004-4_1 10.1007\/978-3-030-77004-4_1 Jes\u00fas\u00a0Andr\u00e9s Portillo-Quintero, Jos\u00e9\u00a0Carlos Ortiz-Bayliss, and Hugo Terashima-Mar\u00edn. 2021. A Straightforward Framework for Video Retrieval Using CLIP. In Pattern Recognition - 13th Mexican Conference, MCPR 2021, Mexico City, Mexico, June 23-26, 2021, Proceedings(Lecture Notes in Computer Science, Vol.\u00a012725), Edgar Roman-Rangel, \u00c1ngel Fernando\u00a0Kuri Morales, Jos\u00e9 Francisco\u00a0Mart\u00ednez Trinidad, Jes\u00fas\u00a0Ariel Carrasco-Ochoa, and Jos\u00e9\u00a0Arturo Olvera-L\u00f3pez (Eds.). Springer, 3\u201312. https:\/\/doi.org\/10.1007\/978-3-030-77004-4_1"},{"key":"e_1_3_2_1_14_1","volume-title":"Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data","author":"Qiu Yuanyuan","unstructured":"Yuanyuan Qiu , Hongzheng Li , Shen Li , Yingdi Jiang , Renfen Hu , and Lijiao Yang . 2018. Revisiting Correlations between Intrinsic and Extrinsic Evaluations of Word Embeddings . In Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data . Springer , 209\u2013221. Yuanyuan Qiu, Hongzheng Li, Shen Li, Yingdi Jiang, Renfen Hu, and Lijiao Yang. 2018. Revisiting Correlations between Intrinsic and Extrinsic Evaluations of Word Embeddings. In Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. Springer, 209\u2013221."},{"key":"e_1_3_2_1_15_1","volume-title":"GCPR 2015, Aachen, Germany, October 7-10, 2015, Proceedings(Lecture Notes in Computer Science, Vol.\u00a09358)","author":"Rohrbach Anna","year":"2015","unstructured":"Anna Rohrbach , Marcus Rohrbach , and Bernt Schiele . 2015 . The Long-Short Story of Movie Description. In Pattern Recognition - 37th German Conference , GCPR 2015, Aachen, Germany, October 7-10, 2015, Proceedings(Lecture Notes in Computer Science, Vol.\u00a09358) , Juergen Gall, Peter\u00a0V. Gehler, and Bastian Leibe (Eds.). Springer, 209\u2013221. https:\/\/doi.org\/10.1007\/978-3-319-24947-6_17 10.1007\/978-3-319-24947-6_17 Anna Rohrbach, Marcus Rohrbach, and Bernt Schiele. 2015. The Long-Short Story of Movie Description. In Pattern Recognition - 37th German Conference, GCPR 2015, Aachen, Germany, October 7-10, 2015, Proceedings(Lecture Notes in Computer Science, Vol.\u00a09358), Juergen Gall, Peter\u00a0V. Gehler, and Bastian Leibe (Eds.). Springer, 209\u2013221. https:\/\/doi.org\/10.1007\/978-3-319-24947-6_17"},{"key":"e_1_3_2_1_16_1","volume-title":"Concept-based video retrieval","author":"Snoek GM","unstructured":"Cees\u00a0 GM Snoek and Marcel Worring . 2009. Concept-based video retrieval . Now Publishers Inc . Cees\u00a0GM Snoek and Marcel Worring. 2009. Concept-based video retrieval. Now Publishers Inc."},{"key":"e_1_3_2_1_17_1","unstructured":"Xiao Wang Houye Ji Chuan Shi Bai Wang Peng Cui Philip\u00a0S. Yu and Yanfang Ye. 2019. Heterogeneous Graph Attention Network. CoRR abs\/1903.07293(2019). arxiv:1903.07293http:\/\/arxiv.org\/abs\/1903.07293  Xiao Wang Houye Ji Chuan Shi Bai Wang Peng Cui Philip\u00a0S. Yu and Yanfang Ye. 2019. Heterogeneous Graph Attention Network. CoRR abs\/1903.07293(2019). arxiv:1903.07293http:\/\/arxiv.org\/abs\/1903.07293"},{"key":"e_1_3_2_1_18_1","volume-title":"Zero-Shot Event Detection Using Multi-modal Fusion of Weakly Supervised Concepts. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014","author":"Wu Shuang","year":"2014","unstructured":"Shuang Wu , Sravanthi Bondugula , Florian Luisier , Xiaodan Zhuang , and Pradeep Natarajan . 2014 . Zero-Shot Event Detection Using Multi-modal Fusion of Weakly Supervised Concepts. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 , Columbus, OH, USA , June 23-28, 2014. IEEE Computer Society, 2665\u20132672. https:\/\/doi.org\/10.1109\/CVPR.2014.341 10.1109\/CVPR.2014.341 Shuang Wu, Sravanthi Bondugula, Florian Luisier, Xiaodan Zhuang, and Pradeep Natarajan. 2014. Zero-Shot Event Detection Using Multi-modal Fusion of Weakly Supervised Concepts. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, June 23-28, 2014. IEEE Computer Society, 2665\u20132672. https:\/\/doi.org\/10.1109\/CVPR.2014.341"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2433396.2433481"},{"key":"e_1_3_2_1_20_1","volume-title":"MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","author":"Xu Jun","year":"2016","unstructured":"Jun Xu , Tao Mei , Ting Yao , and Yong Rui . 2016 . MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 , Las Vegas, NV, USA , June 27-30, 2016. IEEE Computer Society, 5288\u20135296. https:\/\/doi.org\/10.1109\/CVPR.2016.571 10.1109\/CVPR.2016.571 Jun Xu, Tao Mei, Ting Yao, and Yong Rui. 2016. MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016. IEEE Computer Society, 5288\u20135296. https:\/\/doi.org\/10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2021.06.009"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"e_1_3_2_1_23_1","volume-title":"ActBERT: Learning Global-Local Video-Text Representations. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Zhu Linchao","year":"2020","unstructured":"Linchao Zhu and Yi Yang . 2020 . ActBERT: Learning Global-Local Video-Text Representations. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 , Seattle, WA, USA , June 13-19, 2020. Computer Vision Foundation \/ IEEE, 8743\u20138752. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00877 10.1109\/CVPR42600.2020.00877 Linchao Zhu and Yi Yang. 2020. ActBERT: Learning Global-Local Video-Text Representations. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020. Computer Vision Foundation \/ IEEE, 8743\u20138752. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00877"}],"event":{"name":"WWW '22: The ACM Web Conference 2022","location":"Virtual Event, Lyon France","acronym":"WWW '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the Web Conference 2022"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3487553.3524214","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3487553.3524214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:33Z","timestamp":1750188633000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3487553.3524214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":23,"alternative-id":["10.1145\/3487553.3524214","10.1145\/3487553"],"URL":"https:\/\/doi.org\/10.1145\/3487553.3524214","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-08-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}