{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:04:25Z","timestamp":1765339465663,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2024HGTG031,JZ2025HGTB0226,PA2025IISL0110"],"award-info":[{"award-number":["JZ2024HGTG031,JZ2025HGTB0226,PA2025IISL0110"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172138,62202139"],"award-info":[{"award-number":["62172138,62202139"]}],"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":[[2025,10,27]]},"DOI":"10.1145\/3746027.3762018","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"13909-13916","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Listening to the Unspoken: Exploring '365' Aspects of Multimodal Interview Performance Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9446-249X","authenticated-orcid":false,"given":"Jia","family":"Li","sequence":"first","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7243-2177","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2574-4630","authenticated-orcid":false,"given":"Wenhao","family":"Qian","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3196-2188","authenticated-orcid":false,"given":"Jialong","family":"Hu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1042-8361","authenticated-orcid":false,"given":"Zhenzhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology of Anhui Province, Hefei, China and Intelligent Interconnected Systems Laboratory of Anhui Province, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1080\/09540091.2023.2259115"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1109\/APSIPAASC58517.2023.10317109"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.1017\/S1357321724000102"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1016\/j.eswa.2024.123587"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1016\/j.inffus.2024.102832"},{"key":"e_1_3_2_1_6_1","volume-title":"Advancing Head and Neck Cancer Survival Prediction via Multi-Label Learning and Deep Model Interpretation. ArXiv","author":"Chen Meixu","year":"2024","unstructured":"Meixu Chen, Kai Wang, and Jing Wang. 2024. Advancing Head and Neck Cancer Survival Prediction via Multi-Label Learning and Deep Model Interpretation. ArXiv (2024), arXiv-2405."},{"key":"e_1_3_2_1_7_1","first-page":"4171","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."},{"unstructured":"Thomas G Dietterich et al. 2002. Ensemble learning. The handbook of brain theory and neural networks Vol. 2 1 (2002) 110-125.","key":"e_1_3_2_1_8_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1016\/j.eswa.2022.117166"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1007\/s11704-019-8208-z"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1145\/1873951.1874246"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1016\/j.eswa.2023.122731"},{"key":"e_1_3_2_1_13_1","volume-title":"Unsupervised multimodal learning for dependency-free personality recognition","author":"Ghassemi Sina","year":"2023","unstructured":"Sina Ghassemi, Tianyi Zhang, Ward van Breda, Antonis Koutsoumpis, Janneke K Oostrom, Djurre Holtrop, and Reinout E de Vries. 2023. Unsupervised multimodal learning for dependency-free personality recognition. IEEE transactions on affective computing, Vol. 15, 3 (2023), 1053-1066."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.1109\/CVPRW.2017.214"},{"key":"e_1_3_2_1_15_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735-1780."},{"unstructured":"Aaditya Jadhav Rushikesh Ghodake Karthik Muralidharan and G Tarun Varma. 2023. AI based multimodal emotion and behavior analysis of interviewee. (2023).","key":"e_1_3_2_1_16_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.3390\/bdcc8120173"},{"key":"e_1_3_2_1_18_1","first-page":"1716","article-title":"Multiresponse robust design: Mean square error (MSE) criterion","volume":"175","author":"K\u00f6ksoy Onur","year":"2006","unstructured":"Onur K\u00f6ksoy. 2006. Multiresponse robust design: Mean square error (MSE) criterion. Appl. Math. Comput., Vol. 175, 2 (2006), 1716-1729.","journal-title":"Appl. Math. Comput."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1016\/j.chb.2023.108128"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1109\/IJCNN48605.2020.9207258"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1109\/5.726791"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.3390\/systems13010057"},{"unstructured":"Paloma Helena Lira Fontes. 2024. Machine Learning alternative to sparseness: a Radon transform application for multiple and ground roll attenuation. (2024).","key":"e_1_3_2_1_23_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1093\/bib\/bbac095"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.1609\/aaai.v39i12.33337"},{"key":"e_1_3_2_1_26_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems, Vol. 32 (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1016\/j.inffus.2024.102272"},{"key":"e_1_3_2_1_28_1","volume-title":"emotion2vec: Self-supervised pre-training for speech emotion representation. arXiv preprint arXiv:2312.15185","author":"Ma Ziyang","year":"2023","unstructured":"Ziyang Ma, Zhisheng Zheng, Jiaxin Ye, Jinchao Li, Zhifu Gao, Shiliang Zhang, and Xie Chen. 2023. emotion2vec: Self-supervised pre-training for speech emotion representation. arXiv preprint arXiv:2312.15185 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"e_1_3_2_1_30_1","first-page":"6","article-title":"Sfrembedding-mistral: enhance text retrieval with transfer learning","volume":"3","author":"Meng Rui","year":"2024","unstructured":"Rui Meng, Ye Liu, Shafiq Rayhan Joty, Caiming Xiong, Yingbo Zhou, and Semih Yavuz. 2024. Sfrembedding-mistral: enhance text retrieval with transfer learning. Salesforce AI Research Blog, Vol. 3 (2024), 6.","journal-title":"Salesforce AI Research Blog"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_31_1","DOI":"10.1109\/ACCESS.2022.3207287"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1109\/JBHI.2024.3352970"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1145\/2522848.2522860"},{"key":"e_1_3_2_1_34_1","volume-title":"Cross-Aligned Fusion For Multimodal Understanding. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, 5730-5740","author":"Rajora Abshishek","year":"2025","unstructured":"Abshishek Rajora, Shubham Gupta, and Suman Kundu. 2025. Cross-Aligned Fusion For Multimodal Understanding. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, 5730-5740."},{"key":"e_1_3_2_1_35_1","volume-title":"Learning representations by back-propagating errors. nature","author":"Rumelhart David E","year":"1986","unstructured":"David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. 1986. Learning representations by back-propagating errors. nature, Vol. 323, 6088 (1986), 533-536."},{"key":"e_1_3_2_1_36_1","volume-title":"Dynamic fusion for multimodal data. arXiv preprint arXiv:1911.03821","author":"Sahu Gaurav","year":"2019","unstructured":"Gaurav Sahu and Olga Vechtomova. 2019. Dynamic fusion for multimodal data. arXiv preprint arXiv:1911.03821 (2019)."},{"key":"e_1_3_2_1_37_1","volume-title":"Asian Conference on Machine Learning. PMLR, 831-846","author":"Shang Junyuan","year":"2018","unstructured":"Junyuan Shang, Shenda Hong, Yuxi Zhou, Meng Wu, and Hongyan Li. 2018. Knowledge guided multi-instance multi-label learning via neural networks in medicines prediction. In Asian Conference on Machine Learning. PMLR, 831-846."},{"key":"e_1_3_2_1_38_1","volume-title":"Using ontologies to improve performance in massively multi-label prediction models. arXiv preprint arXiv:1905.12126","author":"Steinberg Ethan","year":"2019","unstructured":"Ethan Steinberg and Peter J Liu. 2019. Using ontologies to improve performance in massively multi-label prediction models. arXiv preprint arXiv:1905.12126 (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_39_1","DOI":"10.18653\/v1\/2021.acl-long.412"},{"key":"e_1_3_2_1_40_1","volume-title":"Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, et al.","author":"Tschannen Michael","year":"2025","unstructured":"Michael Tschannen, Alexey Gritsenko, Xiao Wang, Muhammad Ferjad Naeem, Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, et al., 2025. Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)."},{"key":"e_1_3_2_1_41_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_42_1","DOI":"10.1016\/j.jhydrol.2024.131996"},{"key":"e_1_3_2_1_43_1","volume-title":"Deep multimodal fusion by channel exchanging. Advances in neural information processing systems","author":"Wang Yikai","year":"2020","unstructured":"Yikai Wang, Wenbing Huang, Fuchun Sun, Tingyang Xu, Yu Rong, and Junzhou Huang. 2020. Deep multimodal fusion by channel exchanging. Advances in neural information processing systems, Vol. 33 (2020), 4835-4845."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_44_1","DOI":"10.1007\/978-981-32-9298-7_18"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1109\/TCBB.2014.2323058"},{"key":"e_1_3_2_1_46_1","volume-title":"ML-FOREST: A multi-label tree ensemble method for multi-label classification","author":"Wu Qingyao","year":"2016","unstructured":"Qingyao Wu, Mingkui Tan, Hengjie Song, Jian Chen, and Michael K Ng. 2016. ML-FOREST: A multi-label tree ensemble method for multi-label classification. IEEE transactions on knowledge and data engineering, Vol. 28, 10 (2016), 2665-2680."},{"volume-title":"Automatic speech recognition","author":"Yu Dong","unstructured":"Dong Yu and Lin Deng. 2016. Automatic speech recognition. Vol. 1. Springer.","key":"e_1_3_2_1_47_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_48_1","DOI":"10.1109\/TAFFC.2024.3374875"},{"key":"e_1_3_2_1_49_1","volume-title":"Deep multimodal data fusion. ACM computing surveys","author":"Zhao Fei","year":"2024","unstructured":"Fei Zhao, Chengcui Zhang, and Baocheng Geng. 2024. Deep multimodal data fusion. ACM computing surveys, Vol. 56, 9 (2024), 1-36."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_50_1","DOI":"10.1016\/j.ins.2022.12.022"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3762018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:00:09Z","timestamp":1765339209000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3762018"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3762018","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3762018","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"}}]}}