{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:19:02Z","timestamp":1791303542699,"version":"4.1.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant No. 62173045"],"award-info":[{"award-number":["Grant No. 62173045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273054"],"award-info":[{"award-number":["62273054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["Grant No. 2020XD-A04-3"],"award-info":[{"award-number":["Grant No. 2020XD-A04-3"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004761","name":"Natural Science Foundation of Hainan Province","doi-asserted-by":"publisher","award":["Grant No. 622RC675"],"award-info":[{"award-number":["Grant No. 622RC675"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11263-024-02289-z","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T10:37:29Z","timestamp":1733395049000},"page":"2581-2598","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3494-3117","authenticated-orcid":false,"given":"Yuanyuan","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqin","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"2289_CR1","doi-asserted-by":"crossref","unstructured":"Afouras, T., Owens, A., & Chung, J. S., et\u00a0al. (2020). Self-supervised learning of audio-visual objects from video. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVIII 16, (pp. 208\u2013224).","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"2289_CR2","first-page":"24206","volume":"34","author":"H Akbari","year":"2021","unstructured":"Akbari, H., Yuan, L., Qian, R., et al. (2021). Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text. Advances in Neural Information Processing Systems, 34, 24206\u201324221.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2289_CR3","doi-asserted-by":"crossref","unstructured":"Chen, B., Rouditchenko, A., & Duarte, K., et\u00a0al. (2021a). Multimodal clustering networks for self-supervised learning from unlabeled videos. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 8012\u20138021).","DOI":"10.1109\/ICCV48922.2021.00791"},{"key":"2289_CR4","first-page":"1081","volume":"2021","author":"F Chen","year":"2021","unstructured":"Chen, F., Chen, X., Xu, C., et al. (2021). Learning to ground visual objects for visual dialog. Findings of the Association for Computational Linguistics: EMNLP, 2021, 1081\u20131091.","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"2289_CR5","doi-asserted-by":"crossref","unstructured":"Fan, C., Zhang, X., & Zhang, S., et\u00a0al. (2019). Heterogeneous memory enhanced multimodal attention model for video question answering. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1999\u20132007).","DOI":"10.1109\/CVPR.2019.00210"},{"key":"2289_CR6","doi-asserted-by":"publisher","first-page":"2283","DOI":"10.1109\/TASLP.2020.3010650","volume":"28","author":"HM Fayek","year":"2020","unstructured":"Fayek, H. M., & Johnson, J. (2020). Temporal reasoning via audio question answering. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 28, 2283\u20132294.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"2289_CR7","doi-asserted-by":"crossref","unstructured":"Gabeur, V., Sun, C., & Alahari, K., et\u00a0al. (2020). Multi-modal transformer for video retrieval. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, Part IV 16 (pp. 214\u2013229).","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"2289_CR8","doi-asserted-by":"crossref","unstructured":"Gemmeke, J. F., Ellis, D. P., & Freedman, D., et\u00a0al. (2017a). Audio set: An ontology and human-labeled dataset for audio events. In 2017 IEEE International conference on acoustics, speech and signal processing (ICASSP) (pp. 776\u2013780).","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"2289_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., & Ren, S., et\u00a0al. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2289_CR10","first-page":"10077","volume":"33","author":"D Hu","year":"2020","unstructured":"Hu, D., Qian, R., Jiang, M., et al. (2020). Discriminative sounding objects localization via self-supervised audiovisual matching. Advances in Neural Information Processing Systems, 33, 10077\u201310087.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2289_CR11","doi-asserted-by":"crossref","unstructured":"Hu, X., Chen, Z., & Owens, A. (2022). Mix and localize: Localizing sound sources in mixtures. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10483\u201310492).","DOI":"10.1109\/CVPR52688.2022.01023"},{"key":"2289_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Y., Tang, J., & Chen, Z., et\u00a0al. (2024). Structure-clip: Towards scene graph knowledge to enhance multi-modal structured representations. In Proceedings of the AAAI conference on artificial intelligence (Vol. 38, No. 3, pp. 2417-2425).","DOI":"10.1609\/aaai.v38i3.28017"},{"issue":"1","key":"2289_CR13","first-page":"1","volume":"132","author":"J Jiang","year":"2023","unstructured":"Jiang, J., Liu, Z., & Zheng, N. (2023). Correlation information bottleneck: Towards adapting pretrained multimodal models for robust visual question answering. International Journal of Computer Vision, 132(1), 1\u201323.","journal-title":"International Journal of Computer Vision"},{"key":"2289_CR14","first-page":"9399","volume":"2023","author":"Y Jiang","year":"2023","unstructured":"Jiang, Y., & Yin, J. (2023). Target-aware spatio-temporal reasoning via answering questions in dynamics audio-visual scenarios. Findings of the Association for Computational Linguistics: EMNLP, 2023, 9399\u20139409.","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"2289_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Yin, J., & Dang, Y. (2023b). Leveraging the video-level semantic consistency of event for audio-visual event localization. IEEE transactions on multimedia.","DOI":"10.1109\/TMM.2023.3324498"},{"key":"2289_CR16","doi-asserted-by":"crossref","unstructured":"Lao, M., Pu, N., & Liu, Y., et\u00a0al. (2023). Coca: Collaborative causal regularization for audio-visual question answering. In Proceedings of the AAAI conference on artificial intelligence (pp. 12995\u201313003).","DOI":"10.1609\/aaai.v37i11.26527"},{"key":"2289_CR17","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., & Bansal, M., et\u00a0al. (2018). Tvqa: Localized, compositional video question answering. In: EMNLP (pp 1369\u20131379).","DOI":"10.18653\/v1\/D18-1167"},{"key":"2289_CR18","doi-asserted-by":"crossref","unstructured":"Lei, J., Li, L., & Zhou, L., et\u00a0al. (2021). Less is more: Clipbert for video-and-language learning via sparse sampling. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7331\u20137341).","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"2289_CR19","doi-asserted-by":"crossref","unstructured":"Li, G., Wei, Y., & Tian, Y., et\u00a0al. (2022). Learning to answer questions in dynamic audio-visual scenarios. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19108\u201319118).","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"2289_CR20","doi-asserted-by":"crossref","unstructured":"Li, G., Hou, W., & Hu, D. (2023). Progressive spatio-temporal perception for audio-visual question answering. In Proceedings of the 31st ACM international conference on multimedia (pp. 7808\u20137816).","DOI":"10.1145\/3581783.3612293"},{"key":"2289_CR21","doi-asserted-by":"crossref","unstructured":"Lin, YLYan-Bo an\u00a0Sung., Lei, J., & Bansal, M., et\u00a0al. (2023). Vision transformers are parameter-efficient audio-visual learners. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2299\u20132309).","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"2289_CR22","unstructured":"Liu, S., Quan, W., & Wang, C., et\u00a0al. (2022). Dense modality interaction network for audio-visual event localization. IEEE Transactions on Multimedia (pp. 1\u20131)."},{"key":"2289_CR23","unstructured":"Lu, J., Batra, D., & Parikh, D., et\u00a0al. (2019). Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In NeurIPS (pp. 13\u201323)."},{"key":"2289_CR24","doi-asserted-by":"crossref","unstructured":"Mercea, O. B., Riesch, L., & Koepke, A., et\u00a0al. (2022). Audio-visual generalised zero-shot learning with cross-modal attention and language. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10553\u201310563).","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"2289_CR25","unstructured":"Mikolov, T., Chen, K., & Corrado, G., et\u00a0al. (2013). Efficient estimation of word representations in vector space. arXiv preprint[SPACE]arXiv:1301.3781."},{"key":"2289_CR26","doi-asserted-by":"crossref","unstructured":"Miyanishi, T., & Kawanabe, M. (2021). Watch, listen, and answer: Open-ended videoqa with modulated multi-stream 3d convnets. In 2021 29th European signal processing conference (EUSIPCO) (pp. 706\u2013710).","DOI":"10.23919\/EUSIPCO54536.2021.9616257"},{"key":"2289_CR27","unstructured":"Radford, A., Kim, J. W., & Hallacy, C., et\u00a0al. (2021). Learning transferable visual models from natural language supervision. In International conference on machine learning (pp. 8748\u20138763)."},{"key":"2289_CR28","doi-asserted-by":"crossref","unstructured":"Rao, Y., Zhao, W., & Chen, G., et\u00a0al. (2022). Denseclip: Language-guided dense prediction with context-aware prompting. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 18082\u201318091).","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"2289_CR29","doi-asserted-by":"crossref","unstructured":"Rouditchenko, A., Boggust, A., & Harwath, D., et\u00a0al. (2020). Avlnet: Learning audio-visual language representations from instructional videos. arXiv preprint[SPACE]arXiv:2006.09199.","DOI":"10.21437\/Interspeech.2021-1312"},{"key":"2289_CR30","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115, 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2289_CR31","doi-asserted-by":"crossref","unstructured":"Schwartz, I., Schwing, A. G., & Hazan, T. (2019). A simple baseline for audio-visual scene-aware dialog. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12548\u201312558).","DOI":"10.1109\/CVPR.2019.01283"},{"key":"2289_CR32","doi-asserted-by":"crossref","unstructured":"Subramanian, S., Merrill, W., & Darrell, T., et\u00a0al. (2022). Reclip: A strong zero-shot baseline for referring expression comprehension. In Proceedings of the 60th annual meeting of the association for computational linguistics.","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"2289_CR33","doi-asserted-by":"crossref","unstructured":"Tan, R., Raym, A., & Burns, A., et\u00a0al. (2023). Language-guided audio-visual source separation via trimodal consistency. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10575\u201310584).","DOI":"10.1109\/CVPR52729.2023.01019"},{"key":"2289_CR34","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., & Li, B., et\u00a0al. (2018). Audio-visual event localization in unconstrained videos. In Proceedings of the European conference on computer vision (ECCV) (pp. 247\u2013263).","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"2289_CR35","doi-asserted-by":"crossref","unstructured":"Tian, Y., Li, D., & Xu, C. (2020). Unified multisensory perception: Weakly-supervised audio-visual video parsing. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, Part III 16 (pp. 436\u2013454).","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"2289_CR36","first-page":"2280","volume":"2021","author":"J Wang","year":"2021","unstructured":"Wang, J., Ji, Y., Sun, J., et al. (2021). Mirtt: Learning multimodal interaction representations from trilinear transformers for visual question answering. Findings of the Association for Computational Linguistics: EMNLP, 2021, 2280\u20132292.","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"2289_CR37","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhu, L., & Yan, Y., et\u00a0al. (2019). Dual attention matching for audio-visual event localization. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6292\u20136300).","DOI":"10.1109\/ICCV.2019.00639"},{"key":"2289_CR38","doi-asserted-by":"crossref","unstructured":"Xuan, H., Zhang, Z., & Chen, S., et\u00a0al. (2020). Cross-modal attention network for temporal inconsistent audio-visual event localization. In Proceedings of the AAAI conference on artificial intelligence (pp. 279\u2013286).","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"2289_CR39","first-page":"28","volume":"2021","author":"C You","year":"2021","unstructured":"You, C., Chen, N., & Zou, Y. (2021). Self-supervised contrastive cross-modality representation learning for spoken question answering. Findings of the Association for Computational Linguistics: EMNLP, 2021, 28\u201339.","journal-title":"Findings of the Association for Computational Linguistics: EMNLP"},{"key":"2289_CR40","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., & Cui, Y., et\u00a0al. (2019). Deep modular co-attention networks for visual question answering. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6281\u20136290).","DOI":"10.1109\/CVPR.2019.00644"},{"key":"2289_CR41","doi-asserted-by":"crossref","unstructured":"Yun, H., Yu, Y., & Yang, W., et\u00a0al (2021). Pano-avqa: Grounded audio-visual question answering on 360deg videos. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2031\u20132041).","DOI":"10.1109\/ICCV48922.2021.00204"},{"key":"2289_CR42","doi-asserted-by":"crossref","unstructured":"Zellers, R., Lu, J., & Lu, X., et\u00a0al. (2022). Merlot reserve: Neural script knowledge through vision and language and sound. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16375\u201316387).","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"2289_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C. C., Dai, B. (2022a). Extract free dense labels from clip. In European conference on computer vision, Springer (pp. 696\u2013712).","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"2289_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, J., Zheng, L., & Zhong, Y., et\u00a0al. (2021). Positive sample propagation along the audio-visual event line. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8436\u20138444).","DOI":"10.1109\/CVPR46437.2021.00833"},{"issue":"9","key":"2289_CR45","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C. C., et al. (2022). Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9), 2337\u20132348.","journal-title":"International Journal of Computer Vision"},{"key":"2289_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Wu, Y., & Yang, Y., et\u00a0al. (2020). Describing unseen videos via multi-modal cooperative dialog agents. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, Part XXIII 16 (pp. 153\u2013169).","DOI":"10.1007\/978-3-030-58592-1_10"},{"issue":"1s","key":"2289_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3366710","volume":"16","author":"Y Zhuang","year":"2020","unstructured":"Zhuang, Y., Xu, D., Yan, X., et al. (2020). Multichannel attention refinement for video question answering. ACM Transactions on Multimedia Computing, Communications, and Applications, 16(1s), 1\u201323.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02289-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02289-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02289-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T06:02:37Z","timestamp":1744869757000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02289-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"references-count":47,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2289"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02289-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"6 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}