{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:18:49Z","timestamp":1783556329716,"version":"3.55.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032222664","type":"print"},{"value":"9783032222671","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-22267-1_35","type":"book-chapter","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:08:33Z","timestamp":1783555713000},"page":"441-456","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DDVT: Dynamic Dual-Level Vision Transformer Fusion Network for\u00a0Answer Grounding in\u00a0Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Yue","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanshu","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"35_CR2","unstructured":"Ben\u00a0Abacha, A., Hasan, S.A., Datla, V.V., Demner-Fushman, D., M\u00fcller, H.: VQA-med: overview of the medical visual question answering task at imageCLEF 2019. In: Proceedings of Conference and Labs of the Evaluation Forum, 9\u201312 September 2019 (2019)"},{"key":"35_CR3","unstructured":"Bolukbasi, T., Wang, J., Dekel, O., Saligrama, V.: Adaptive neural networks for efficient inference. In: Proceedings of the 2022 International Conference on Machine Learning, pp. 527\u2013536 (2017)"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Anjum, S., Gurari, D.: Grounding answers for visual questions asked by visually impaired people. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 19098\u201319107 (2022)","DOI":"10.1109\/CVPR52688.2022.01851"},{"key":"35_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1007\/978-3-030-58568-6_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Cheng","year":"2020","unstructured":"Cheng, T., Wang, X., Huang, L., Liu, W.: Boundary-preserving mask R-CNN. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 660\u2013676. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_39"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Gan, C., Li, Y., Li, H., Sun, C., Gong, B.: VQS: linking segmentations to questions and answers for supervised attention in VQA and question-focused semantic segmentation. In: Proceedings of the 2022 IEEE\/CVF International Conference on Computer Vision, pp. 1811\u20131820 (2017)","DOI":"10.1109\/ICCV.2017.201"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Gan, C., Li, Y., Li, H., Sun, C., Gong, B.: VQS: linking segmentations to questions and answers for supervised attention in VQA and question-focused semantic segmentation, pp. 1829\u20131838 (2017)","DOI":"10.1109\/ICCV.2017.201"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Dynamic fusion with intra- and inter-modality attention flow for visual question answering. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 6632\u20136641 (2019)","DOI":"10.1109\/CVPR.2019.00680"},{"key":"35_CR11","doi-asserted-by":"publisher","first-page":"7436","DOI":"10.1109\/TPAMI.2021.3117837","volume":"44","author":"Y Han","year":"2021","unstructured":"Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44, 7436\u20137456 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, A., Darrell, T., Saenko, K.: Language-conditioned graph networks for relational reasoning. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 10294\u201310303 (2019)","DOI":"10.1109\/ICCV.2019.01039"},{"key":"35_CR14","unstructured":"Huang, G., Chen, D., Li, T., Wu, F., van\u00a0der Maaten, L., Weinberger, K.Q.: Multi-scale dense networks for resource efficient image classification. In: Proceedings of the 2022 International Conference on Learning Representation (2018)"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"35_CR16","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: Proceedings of the 2022 International Conference on Learning Representation (2017)"},{"key":"35_CR17","unstructured":"Jiang, Y., Natarajan, V., Chen, X., Rohrbach, M., Batra, D., Parikh, D.: Pythia v0.1: the winning entry to the VQA challenge 2018. CoRR abs\/1807.09956 (2018)"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Khan, A.U., Kuehne, H., Duarte, K., Gan, C., da\u00a0Vitoria\u00a0Lobo, N., Shah, M.: Found a reason for me? Weakly-supervised grounded visual question answering using capsules. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 8465\u20138474 (2021)","DOI":"10.1109\/CVPR46437.2021.00836"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Khan, A.U., Mazaheri, A., da\u00a0Vitoria\u00a0Lobo, N., Shah, M.: MMFT-BERT: multimodal fusion transformer with BERT encodings for visual question answering. In: EMNLP, pp. 4648\u20134660 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.417"},{"key":"35_CR20","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1109\/LSP.2021.3135825","volume":"29","author":"H Lan","year":"2022","unstructured":"Lan, H., Zhang, P.: Learning and integrating multi-level matching features for image-text retrieval. IEEE Signal Process. Lett. 29, 374\u2013378 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Li, R., He, C., Li, S., Zhang, Y., Zhang, L.: DynaMask: dynamic mask selection for instance segmentation. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 11279\u201311288 (2023)","DOI":"10.1109\/CVPR52729.2023.01085"},{"key":"35_CR22","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.1109\/LSP.2023.3310870","volume":"30","author":"W Li","year":"2023","unstructured":"Li, W., Ma, Z., Shi, J., Fan, X.: The style transformer with common knowledge optimization for image-text retrieval. IEEE Signal Process. Lett. 30, 1197\u20131201 (2023)","journal-title":"IEEE Signal Process. Lett."},{"key":"35_CR23","unstructured":"Lin, J., Rao, Y., Lu, J., Zhou, J.: Runtime neural pruning. In: NIPS, vol. 30 (2017)"},{"key":"35_CR24","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1109\/LSP.2022.3178899","volume":"29","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Liu, H., Wang, H., Liu, M.: Regularizing visual semantic embedding with contrastive learning for image-text matching. IEEE Signal Process. Lett. 29, 1332\u20131336 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the 2022 IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"35_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of the 2022 International Conference on Learning Representation (2019)"},{"key":"35_CR27","unstructured":"Lu, J., Clark, C., Zellers, R., Mottaghi, R., Kembhavi, A.: UNIFIED-IO: a unified model for vision, language, and multi-modal tasks. In: Proceedings of the 2022 International Conference on Learning Representation (2023)"},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Mullapudi, R.T., Mark, W.R., Shazeer, N., Fatahalian, K.: HydraNets: specialized dynamic architectures for efficient inference. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 8080\u20138089 (2018)","DOI":"10.1109\/CVPR.2018.00843"},{"key":"35_CR29","unstructured":"Pan, J., et al.: Tell me the evidence? Dual visual-linguistic interaction for answer grounding. CoRR abs\/2207.05703 (2022)"},{"key":"35_CR30","unstructured":"Paszke, A., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: Annual Conference on Neural Information Processing Systems, vol. 32 (2019)"},{"key":"35_CR31","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.3390\/s20082281","volume":"20","author":"Y Qiu","year":"2020","unstructured":"Qiu, Y., Satoh, Y., Suzuki, R., Iwata, K., Kataoka, H.: Multi-view visual question answering with active viewpoint selection. Sensors 20, 2281 (2020)","journal-title":"Sensors"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 5099\u20135110 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"35_CR33","unstructured":"Tian, W., Li, H., Zhao, Z.Q.: Dual capsule attention mask network with mutual learning for visual question answering. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 5678\u20135688 (2022)"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, F., Dou, Z.Y., Darrell, T., Gonzalez, J.E.: SkipNet: learning dynamic routing in convolutional networks. In: Proceedings of the 2022 European Conference on Computer Vision, pp. 409\u2013424 (2018)","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"35_CR35","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., et\u00a0al., J.C.: Transformers: state-of-the-art natural language processing. In: EMNLP, pp. 38\u201345 (2020)","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"35_CR36","unstructured":"Yang, B., Bender, G., Le, Q.V., Ngiam, J.: CondConv: conditionally parameterized convolutions for efficient inference. In: Annual Conference on Neural Information Processing Systems, vol. 32 (2019)"},{"key":"35_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.S.: LAVT: language-aware vision transformer for referring image segmentation. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"35_CR38","unstructured":"You, Z., Yan, K., Ye, J., Ma, M., Wang, P.: Gate decorator: global filter pruning method for accelerating deep convolutional neural networks. In: 2019 Annual Conference on Neural Information Processing Systems, vol. 32 (2019)"},{"key":"35_CR39","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"35_CR40","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 6274\u20136283 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"35_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, S., Qu, L., You, S., Yang, Z., Zhang, J.: Automatic generation of grounded visual questions. In: IJCAI International Joint Conference on Artificial Intelligence, pp. 4235\u20134243 (2017)","DOI":"10.24963\/ijcai.2017\/592"},{"key":"35_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Ren, T., Zhu, C., Sun, X., Liu, J.: TRAR: routing the attention spans in transformer for visual question answering. In: Proceedings of the 2022 IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2074\u20132084 (2021)","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"35_CR43","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.patrec.2023.04.003","volume":"171","author":"L Zhu","year":"2023","unstructured":"Zhu, L., Peng, L., Zhou, W., Yang, J.: Dual-decoder transformer network for answer grounding in visual question answering. Pattern Recognit. Lett. 171, 53\u201360 (2023)","journal-title":"Pattern Recognit. Lett."},{"key":"35_CR44","unstructured":"Zhu, M., et al.: Dynamic resolution network. In: Annual Conference on Neural Information Processing Systems, vol. 34, pp. 27319\u201327330 (2021)"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-22267-1_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:08:38Z","timestamp":1783555718000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-22267-1_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032222664","9783032222671"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-22267-1_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"42","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cgs-network.org\/cgi25","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}