{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:04:30Z","timestamp":1765343070416,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","funder":[{"name":"The Ministry of Education and Culture through the Finnish Doctoral program Network in Artificial Intelligence (AI-DOC)","award":["VN\/3137\/2024-OKM-6"],"award-info":[{"award-number":["VN\/3137\/2024-OKM-6"]}]},{"name":"Research Council of Finland through the Finnish Center for Artificial Intelligence flagship","award":["345552"],"award-info":[{"award-number":["345552"]}]},{"name":"Research Council of Finland","award":["345791"],"award-info":[{"award-number":["345791"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758261","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"13097-13103","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Valor32k-AVQA v2.0: Open-Ended Audio-Visual Question Answering Dataset and Benchmark"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8480-5128","authenticated-orcid":false,"given":"Ines","family":"Riahi","sequence":"first","affiliation":[{"name":"Aalto University, Espoo, Uusimaa, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6317-9752","authenticated-orcid":false,"given":"Abduljalil","family":"Radman","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Uusimaa, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7088-2331","authenticated-orcid":false,"given":"Zixin","family":"Guo","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Uusimaa, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9065-9591","authenticated-orcid":false,"given":"Rachid","family":"Hedjam","sequence":"additional","affiliation":[{"name":"Bishop's University, Sherbrooke, QC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7218-3131","authenticated-orcid":false,"given":"Jorma","family":"Laaksonen","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Uusimaa, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"e_1_3_2_1_5_1","first-page":"72842","article-title":"VAST: A vision-audio-subtitle-text omni-modality foundation model and dataset","volume":"36","author":"Chen Sihan","year":"2023","unstructured":"Sihan Chen, Handong Li, Qunbo Wang, Zijia Zhao, Mingzhen Sun, Xinxin Zhu, and Jing Liu. 2023a. VAST: A vision-audio-subtitle-text omni-modality foundation model and dataset. Advances in Neural Information Processing Systems (NeurIPS), Vol. 36 (2023), 72842-72866.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML). 5178-5193","author":"Chen Sanyuan","year":"2023","unstructured":"Sanyuan Chen, Yu Wu, Chengyi Wang, Shujie Liu, Daniel Tompkins, Zhuo Chen, Wanxiang Che, Xiangzhan Yu, and Furu Wei. 2023b. BEATs: Audio pre-training with acoustic tokenizers. In Proceedings of the 40th International Conference on Machine Learning (ICML). 5178-5193."},{"key":"e_1_3_2_1_7_1","unstructured":"Zesen Cheng Sicong Leng Hang Zhang Yifei Xin Xin Li Guanzheng Chen Yongxin Zhu Wenqi Zhang Ziyang Luo Deli Zhao et al. 2024. VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in Video-LLMs. arXiv preprint arXiv:2406.07476 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.","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."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Learning Representations (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 International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01752"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_13_1","volume-title":"Selen Pehlivan, Abduljalil Radman, Min Cao, and Jorma Laaksonen.","author":"Guo Zixin","year":"2025","unstructured":"Zixin Guo, Tzu-Jui Julius Wang, Selen Pehlivan, Abduljalil Radman, Min Cao, and Jorma Laaksonen. 2025. Prompt-based weakly-supervised vision-language pre-training. Pattern Recognition Letters (2025)."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Learning Representations (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 International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_17_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612293"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (ICML). 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022a. BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In Proceedings of the 39th International Conference on Machine Learning (ICML). 12888-12900."},{"key":"e_1_3_2_1_23_1","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out. 74-81.","journal-title":"Text Summarization Branches Out."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3479776"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00442"},{"key":"e_1_3_2_1_26_1","volume-title":"Ola: Pushing the frontiers of omni-modal language model. arXiv preprint arXiv:2502.04328","author":"Liu Zuyan","year":"2025","unstructured":"Zuyan Liu, Yuhao Dong, Jiahui Wang, Ziwei Liu, Winston Hu, Jiwen Lu, and Yongming Rao. 2025b. Ola: Pushing the frontiers of omni-modal language model. arXiv preprint arXiv:2502.04328 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"FortisAVQA and MAVEN: A benchmark dataset and debiasing framework for robust multimodal reasoning. arXiv preprint arXiv:2504.00487","author":"Ma Jie","year":"2025","unstructured":"Jie Ma, Zhitao Gao, Qi Chai, Jun Liu, Pinghui Wang, Jing Tao, and Zhou Su. 2025. FortisAVQA and MAVEN: A benchmark dataset and debiasing framework for robust multimodal reasoning. arXiv preprint arXiv:2504.00487 (2025)."},{"key":"e_1_3_2_1_28_1","first-page":"9507","article-title":"Look, listen, and answer: Overcoming biases for audio-visual question answering","author":"Ma Jie","year":"2024","unstructured":"Jie Ma, Min Hu, Pinghui Wang, Wangchun Sun, Lingyun Song, Hongbin Pei, Jun Liu, and Youtian Du. 2024. Look, listen, and answer: Overcoming biases for audio-visual question answering. In Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track. 9507-9531.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5220\/0012431500003660"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_32_1","volume-title":"Unleashing the potential of LLMs for audio-visual question answering. Master's thesis","author":"Riahi Ines","year":"2024","unstructured":"Ines Riahi. 2024. Unleashing the potential of LLMs for audio-visual question answering. Master's thesis. Aalto University, School of Science, Department of Computer Science. hrefhttps:\/\/doi.org\/URN:NBN:fi:aalto-202405263822doi:URN:NBN:fi:aalto-202405263822"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_2_1_34_1","volume-title":"Qwen2 technical report. arXiv preprint arXiv:2407.10671","author":"Team Qwen","year":"2024","unstructured":"Qwen Team. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 2031-2041","author":"Yun Heeseung","year":"2021","unstructured":"Heeseung Yun, Youngjae Yu, Wonsuk Yang, Kangil Lee, and Gunhee Kim. 2021. Pano-AVQA: Grounded audio-visual question answering on 360textdegree videos. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 2031-2041."},{"key":"e_1_3_2_1_38_1","volume-title":"BERTScore: Evaluating text generation with BERT. arXiv preprint arXiv:1904.09675","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. BERTScore: Evaluating text generation with BERT. arXiv preprint arXiv:1904.09675 (2019)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:00:00Z","timestamp":1765342800000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758261"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":38,"alternative-id":["10.1145\/3746027.3758261","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758261","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"}}]}}