{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:49:56Z","timestamp":1755802196568,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["62206193,62006093"],"award-info":[{"award-number":["62206193,62006093"]}]},{"name":"Jiangsu Big Data Intelligent Engineering Laboratory of Soochow University","award":["SDGC2158"],"award-info":[{"award-number":["SDGC2158"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658094","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"442-450","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2757-0801","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7621-8125","authenticated-orcid":false,"given":"Tongfei","family":"Shen","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8948-2856","authenticated-orcid":false,"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2580-8957","authenticated-orcid":false,"given":"Qingying","family":"Sun","sequence":"additional","affiliation":[{"name":"Huaiyin Normal University, Huai'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1000-3278","authenticated-orcid":false,"given":"Shoushan","family":"Li","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7887-5099","authenticated-orcid":false,"given":"Guodong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proc. of NeurIPS. 24206--24221","author":"Akbari Hassan","year":"2021","unstructured":"Hassan Akbari, Liangzhe Yuan, Rui Qian, Wei-Hong Chuang, Shih-Fu Chang, Yin Cui, and Boqing Gong. 2021. VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text. In Proc. of NeurIPS. 24206--24221."},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. of COLING. 6875--6886","author":"Alnajjar Khalid","year":"2022","unstructured":"Khalid Alnajjar, Mika Hamalainen, J\u00f6rg Tiedemann, Jorma Laaksonen, and Mikko Kurimo. 2022. When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and Its Intensity. In Proc. of COLING. 6875--6886."},{"key":"e_1_3_2_1_3_1","volume-title":"ColBERT: Using BERT Sentence Embedding for Humor Detection. CoRR","author":"Annamoradnejad Issa","year":"2020","unstructured":"Issa Annamoradnejad. 2020. ColBERT: Using BERT Sentence Embedding for Humor Detection. CoRR (2020)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.131"},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. of ICML. 813--824","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding?. In Proc. of ICML. 813--824."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1394"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. of COLING. 6752--6761","author":"Chauhan Dushyant Singh","year":"2022","unstructured":"Dushyant Singh Chauhan, Gopendra Vikram Singh, Aseem Arora, Asif Ekbal, and Pushpak Bhattacharyya. 2022. A Sentiment and Emotion Aware Multimodal Multiparty Humor Recognition in Multilingual Conversational Setting. In Proc. of COLING. 6752--6761."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479959"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2018"},{"key":"e_1_3_2_1_11_1","volume-title":"Hinton","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proc. of ICML. 1597--1607."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570431"},{"key":"e_1_3_2_1_13_1","volume-title":"Proc. of NAACL. 4171--4186","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 Proc. of NAACL. 4171--4186."},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. of ICLR.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proc. of ICLR."},{"key":"e_1_3_2_1_15_1","unstructured":"Christoph Feichtenhofer Haoqi Fan Yanghao Li and Kaiming He. 2022. Masked Autoencoders As Spatiotemporal Learners. In NeurIPS."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479919"},{"key":"e_1_3_2_1_19_1","volume-title":"Proc. of AAAI. 12972--12980","author":"Kamrul Hasan Md.","year":"2021","unstructured":"Md. Kamrul Hasan, Sangwu Lee, Wasifur Rahman, Amir Zadeh, Rada Mihalcea, Louis-Philippe Morency, and Ehsan Hoque. 2021. Humor Knowledge Enriched Transformer for Understanding Multimodal Humor. In Proc. of AAAI. 12972--12980."},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. of EMNLP. 2046--2056","author":"Kamrul Hasan Md.","year":"2019","unstructured":"Md. Kamrul Hasan, Wasifur Rahman, AmirAli Bagher Zadeh, Jianyuan Zhong, Md. Iftekhar Tanveer, Louis-Philippe Morency, and Mohammed (Ehsan) Hoque. 2019. UR-FUNNY: A Multimodal Language Dataset for Understanding Humor. In Proc. of EMNLP. 2046--2056."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_22_1","volume-title":"Proc. of ICLR.","author":"He Pengcheng","year":"2021","unstructured":"Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. Deberta: decoding-Enhanced Bert with Disentangled Attention. In Proc. of ICLR."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01427"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00212"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475431"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230438"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of ICLR.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In Proc. of ICLR."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"e_1_3_2_1_32_1","volume-title":"Edward Z. Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala.","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6 pf, Edward Z. Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Proc. of NeurIPS. 8024--8035."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746924"},{"key":"e_1_3_2_1_34_1","volume-title":"Brian Kingsbury, Michael Picheny, Antonio Torralba, and James R. Glass.","author":"Rouditchenko Andrew","year":"2021","unstructured":"Andrew Rouditchenko, Angie W. Boggust, David Harwath, Brian Chen, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Hilde Kuehne, Rameswar Panda, Rog\u00e9 rio Schmidt Feris, Brian Kingsbury, Michael Picheny, Antonio Torralba, and James R. Glass. 2021. AVLnet: Learning Audio-Visual Language Representations from Instructional Videos. In Proc. of Interspeech. 1584--1588."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548025"},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. of NeurIPS. 38032--38045","author":"Sun Yuchong","year":"2022","unstructured":"Yuchong Sun, Hongwei Xue, Ruihua Song, Bei Liu, Huan Yang, and Jianlong Fu. 2022b. Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning. In Proc. of NeurIPS. 38032--38045."},{"key":"e_1_3_2_1_38_1","volume-title":"Proc. of NeurIPS. 9617--9632","author":"Tang Zineng","year":"2022","unstructured":"Zineng Tang, Jaemin Cho, Yixin Nie, and Mohit Bansal. 2022. TVLT: Textless Vision-Language Transformer. In Proc. of NeurIPS. 9617--9632."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_41_1","volume-title":"Proc. of NeurIPS. 5998--6008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Proc. of NeurIPS. 5998--6008."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Yunwen Wang. 2020. Humor and camera view on mobile short-form video apps influence user experience and technology-adoption intent an example of TikTok (DouYin). Comput. Hum. Behav. (2020) 106373.","DOI":"10.1016\/j.chb.2020.106373"},{"key":"e_1_3_2_1_44_1","volume-title":"Seppi","author":"Weller Orion","year":"2019","unstructured":"Orion Weller and Kevin D. Seppi. 2019. Humor Detection: A Transformer Gets the Last Laugh. In Proc. of EMNLP. 3619--3623."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88480-2_49"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.6"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"key":"e_1_3_2_1_49_1","volume-title":"Proc. of NeurIPS. 23634--23651","author":"Zellers Rowan","year":"2021","unstructured":"Rowan Zellers, Ximing Lu, Jack Hessel, Youngjae Yu, Jae Sung Park, Jize Cao, Ali Farhadi, and Yejin Choi. 2021. MERLOT: Multimodal Neural Script Knowledge Models. In Proc. of NeurIPS. 23634--23651."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593583"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Phuket Thailand","acronym":"ICMR '24"},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658094","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:47:36Z","timestamp":1755766056000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658094"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":51,"alternative-id":["10.1145\/3652583.3658094","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658094","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}