{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T01:09:20Z","timestamp":1761181760459,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62176076"],"award-info":[{"award-number":["62176076"]}]},{"name":"Natural Science Foundation of Guangdong Province","award":["2023A151501292"],"award-info":[{"award-number":["2023A151501292"]}]},{"name":"Shenzhen Foundational Research Funding","award":["JCYJ20220818102415032"],"award-info":[{"award-number":["JCYJ20220818102415032"]}]},{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","award":["2022B1212010005"],"award-info":[{"award-number":["2022B1212010005"]}]},{"name":"the Major Key Project of PCL2023A09","award":["PCL2023A09"],"award-info":[{"award-number":["PCL2023A09"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746270.3760222","type":"proceedings-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T15:14:09Z","timestamp":1760973249000},"page":"64-68","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Lightweight Multimodal Framework for Big Five Personality Trait Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7580-5876","authenticated-orcid":false,"given":"Taiyu","family":"Niu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5414-8010","authenticated-orcid":false,"given":"Tianhao","family":"Wu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7095-7498","authenticated-orcid":false,"given":"Pengtao","family":"Han","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1764-4181","authenticated-orcid":false,"given":"Shengzhe","family":"Sun","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5561-7704","authenticated-orcid":false,"given":"Yifan","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8256-7049","authenticated-orcid":false,"given":"Geng","family":"Tu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9885-2364","authenticated-orcid":false,"given":"Ruifeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Mdpe: A multimodal deception dataset with personality and emotional characteristics. arXiv preprint arXiv:2407.12274","author":"Cai Cong","year":"2024","unstructured":"Cong Cai, Shan Liang, Xuefei Liu, Kang Zhu, Zhengqi Wen, Jianhua Tao, Heng Xie, Jizhou Cui, Yiming Ma, Zhenhua Cheng, et al., 2024. Mdpe: A multimodal deception dataset with personality and emotional characteristics. arXiv preprint arXiv:2407.12274 (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"e_1_3_2_1_3_1","first-page":"110805","article-title":"Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning","volume":"37","author":"Cheng Zebang","year":"2024","unstructured":"Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, and Alexander Hauptmann. 2024. Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning. Advances in Neural Information Processing Systems, Vol. 37 (2024), 110805-110853.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689092.3689414"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689092.3689415"},{"key":"e_1_3_2_1_7_1","volume-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793","author":"Aohan Zeng Team GLM","year":"2024","unstructured":"Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, et al., 2024. Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Kushal Lakhotia","author":"Hsu Wei-Ning","year":"2021","unstructured":"Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. 2021. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM transactions on audio, speech, and language processing, Vol. 29 (2021), 3451-3460."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1037\/emo0000644"},{"key":"e_1_3_2_1_10_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.049"},{"key":"e_1_3_2_1_12_1","volume-title":"Affectgpt: A new dataset, model, and benchmark for emotion understanding with multimodal large language models. arXiv preprint arXiv:2501.16566","author":"Lian Zheng","year":"2025","unstructured":"Zheng Lian, Haoyu Chen, Lan Chen, Haiyang Sun, Licai Sun, Yong Ren, Zebang Cheng, Bin Liu, Rui Liu, Xiaojiang Peng, et al., 2025a. Affectgpt: A new dataset, model, and benchmark for emotion understanding with multimodal large language models. arXiv preprint arXiv:2501.16566 (2025)."},{"key":"e_1_3_2_1_13_1","unstructured":"Zheng Lian Rui Liu Kele Xu Bin Liu Xuefei Liu Yazhou Zhang Xin Liu Yong Li Zebang Cheng Haolin Zuo et al. 2025b. Mer 2025: When affective computing meets large language models. arXiv preprint arXiv:2504.19423 (2025)."},{"key":"e_1_3_2_1_14_1","unstructured":"Zheng Lian Haiyang Sun Licai Sun Haoyu Chen Lan Chen Hao Gu Zhuofan Wen Shun Chen Siyuan Zhang Hailiang Yao et al. 2024a. OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition. arXiv preprint arXiv:2410.01495 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612836"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689092.3689959"},{"key":"e_1_3_2_1_17_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_18_1","volume-title":"Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues. arXiv preprint arXiv:2409.19723","author":"Sun Lei","year":"2024","unstructured":"Lei Sun, Jinming Zhao, and Qin Jin. 2024. Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues. arXiv preprint arXiv:2409.19723 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Generalizing to Unseen Speakers: Multimodal Emotion Recognition in Conversations With Speaker Generalization","author":"Tu Geng","year":"2025","unstructured":"Geng Tu, Ran Jing, Bin Liang, Yue Yu, Min Yang, Bing Qin, and Ruifeng Xu. 2025a. Generalizing to Unseen Speakers: Multimodal Emotion Recognition in Conversations With Speaker Generalization. IEEE Transactions on Affective Computing (2025)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730231"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657944"},{"key":"e_1_3_2_1_22_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)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/PerCom59722.2024.10494487"},{"key":"e_1_3_2_1_24_1","unstructured":"Aiyuan Yang Bin Xiao Bingning Wang Borong Zhang Ce Bian Chao Yin Chenxu Lv Da Pan Dian Wang Dong Yan et al. 2023. Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 543-553","author":"Zhang Hang","year":"2023","unstructured":"Hang Zhang, Xin Li, and Lidong Bing. 2023. Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 543-553."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689092.3689408"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2951656"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689092.3689407"}],"event":{"name":"MM '25:The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland"},"container-title":["Proceedings of the 3rd International Workshop on Multimodal and Responsible Affective Computing"],"original-title":[],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:23:07Z","timestamp":1761153787000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746270.3760222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":28,"alternative-id":["10.1145\/3746270.3760222","10.1145\/3746270"],"URL":"https:\/\/doi.org\/10.1145\/3746270.3760222","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]},"assertion":[{"value":"2025-10-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}