{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:35:45Z","timestamp":1763202945414,"version":"3.30.2"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00530-024-01560-0","type":"journal-article","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:59:32Z","timestamp":1732035572000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Exploring and exploiting model uncertainty for robust visual question answering"],"prefix":"10.1007","volume":"30","author":[{"given":"Xuesong","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jun","family":"He","sequence":"additional","affiliation":[]},{"given":"Jia","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Zhenzhen","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Xun","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jia","family":"Li","sequence":"additional","affiliation":[]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,19]]},"reference":[{"key":"1560_CR1","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Huang, F., Zhou, L., Jin, C., Zhang, Y., Zhang, T.: A hierarchical multimodal attention-based neural network for image captioning. In: ACM SIGIR, pp. 889\u2013892 (2017)","DOI":"10.1145\/3077136.3080671"},{"key":"1560_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: Vqa: Visual question answering. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"1560_CR3","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the v in vqa matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"1560_CR4","doi-asserted-by":"crossref","unstructured":"Xiao, J., Zhou, P., Yao, A., Li, Y., Hong, R., Yan, S., Chua, T.-S.: Contrastive video question answering via video graph transformer. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"1560_CR5","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yao, A., Li, Y., Chua, T.-S.: Can i trust your answer? visually grounded video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13204\u201313214 (2024)","DOI":"10.1109\/CVPR52733.2024.01254"},{"issue":"9","key":"1560_CR6","doi-asserted-by":"publisher","first-page":"6174","DOI":"10.1109\/TCSVT.2022.3162650","volume":"32","author":"HS Nawaz","year":"2022","unstructured":"Nawaz, H.S., Shi, Z., Gan, Y., Hirpa, A., Dong, J., Zheng, H.: Temporal moment localization via natural language by utilizing video question answers as a special variant and bypassing nlp for corpora. IEEE Trans. Circuits Syst. Video Technol. 32(9), 6174\u20136185 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"1560_CR7","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1109\/TCSVT.2020.3048440","volume":"32","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Shao, J., Cao, R., Gao, L., Xu, X., Shen, H.T.: Action-centric relation transformer network for video question answering. IEEE Trans. Circuits Syst. Video Technol. 32(1), 63\u201374 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1560_CR8","doi-asserted-by":"crossref","unstructured":"Dong, J., Li, X., Xu, C., Yang, X., Yang, G., Wang, X., Wang, M.: Dual encoding for video retrieval by text. IEEE Trans. Pattern Anal. Mach. Intell (2021)","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"1560_CR9","doi-asserted-by":"crossref","unstructured":"Yang, X., Dong, J., Cao, Y., Wang, X., Wang, M., Chua, T.-S.: Tree-augmented cross-modal encoding for complex-query video retrieval. In: ACM SIGIR, pp. 1339\u20131348 (2020)","DOI":"10.1145\/3397271.3401151"},{"key":"1560_CR10","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, F., Ji, W., Wang, M., Chua, T.-S.: Deconfounded video moment retrieval with causal intervention. In: ACM SIGIR, pp. 1\u201310 (2021)","DOI":"10.1145\/3404835.3462823"},{"key":"1560_CR11","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1109\/TIP.2022.3140611","volume":"31","author":"X Yang","year":"2022","unstructured":"Yang, X., Wang, S., Dong, J., Dong, J., Wang, M., Chua, T.-S.: Video moment retrieval with cross-modal neural architecture search. IEEE Trans. Image Process. 31, 1204\u20131216 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"1560_CR12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285","author":"H Ben-younes","year":"2017","unstructured":"Ben-younes, H., Cadene, R., Cord, M., Thome, N.: Mutan: multimodal tucker fusion for visual question answering. Proc. IEEE Int. Conf. Comput. Vis. (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.285","journal-title":"Proc. IEEE Int. Conf. Comput. Vis."},{"key":"1560_CR13","doi-asserted-by":"crossref","unstructured":"Zhao, L., Cai, D., Zhang, J., Sheng, L., Xu, D., Zheng, R., Zhao, Y., Wang, L., Fan, X.: Towards explainable 3d grounded visual question answering: a new benchmark and strong baseline. IEEE Trans. Circuits Syst. Video Technol. (2022)","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"1560_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, V., Li, Z., Kortylewski, A., Zhang, C., Li, Y., Yuille, A.: Swapmix: Diagnosing and regularizing the over-reliance on visual context in visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5078\u20135088 (2022)","DOI":"10.1109\/CVPR52688.2022.00502"},{"key":"1560_CR15","doi-asserted-by":"crossref","unstructured":"Ding, Y., Yu, J., Liu, B., Hu, Y., Cui, M., Wu, Q.: Mukea: Multimodal knowledge extraction and accumulation for knowledge-based visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5089\u20135098 (2022)","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"1560_CR16","unstructured":"Wu, J., Mooney, R.: Self-critical reasoning for robust visual question answering. Adv. Neural Inf. Process Syst. 32 (2019)"},{"key":"1560_CR17","doi-asserted-by":"publisher","unstructured":"Clark, C., Yatskar, M., Zettlemoyer, L.: Don\u2019t take the easy way out: Ensemble based methods for avoiding known dataset biases. In: Proc. Conf. Empir . Methods Nat. Lang. Process & Joint Conf. Nat. Lang. Process, Hong Kong, China, pp. 4069\u20134082 (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1418","DOI":"10.18653\/v1\/D19-1418"},{"key":"1560_CR18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081","author":"L Chen","year":"2020","unstructured":"Chen, L., Yan, X., Xiao, J., Zhang, H., Pu, S., Zhuang, Y.: Counterfactual samples synthesizing for robust visual question answering. Proc. IEEE Conf. Comput. Vis. Pattern. Recognit. (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01081","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern. Recognit."},{"key":"1560_CR19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522","author":"A Agrawal","year":"2018","unstructured":"Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don\u2019t just assume; look and answer Overcoming priors for visual question answering. Proc. IEEE Conf. Comput. Vis. Pattern. Recognit. (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00522","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern. Recognit."},{"key":"1560_CR20","unstructured":"Cadene, R., Dancette, C., Cord, M., Parikh, D., et al.: Rubi: Reducing unimodal biases for visual question answering. Adv. Neural Inf. Process Syst. 32 (2019)"},{"key":"1560_CR21","doi-asserted-by":"publisher","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 6077\u20136086 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00636","DOI":"10.1109\/CVPR.2018.00636"},{"key":"1560_CR22","unstructured":"Ramakrishnan, S., Agrawal, A., Lee, S.: Overcoming language priors in visual question answering with adversarial regularization. In: Adv. Neural Inf. Process Syst. NIPS\u201918, pp. 1548\u20131558. Curran Associates Inc., Red Hook, NY, USA (2018)"},{"key":"1560_CR23","doi-asserted-by":"crossref","unstructured":"Zhu, X., Mao, Z., Liu, C., Zhang, P., Wang, B., Zhang, Y.: Overcoming language priors with self-supervised learning for visual question answering. In: Process and Proc. Int. Joint Conf. Artif. Intell. (2021)","DOI":"10.24963\/ijcai.2020\/151"},{"key":"1560_CR24","unstructured":"Han, Y., Nie, L., Yin, J., Wu, J., Yan, Y.: Visual perturbation-aware collaborative learning for overcoming the language prior problem. ArXiv abs\/2207.11850 (2022)"},{"key":"1560_CR25","first-page":"407","volume":"33","author":"D Teney","year":"2020","unstructured":"Teney, D., Abbasnejad, E., Kafle, K., Shrestha, R., Kanan, C., Van Den Hengel, A.: On the value of out-of-distribution testing: an example of goodhart\u2019s law. Adv. Neural. Inf. Process. Syst. 33, 407\u2013417 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1560_CR26","doi-asserted-by":"crossref","unstructured":"Basu, A., Addepalli, S., Babu, R.V.: Rmlvqa: A margin loss approach for visual question answering with language biases. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11671\u201311680 (2023)","DOI":"10.1109\/CVPR52729.2023.01123"},{"key":"1560_CR27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251","author":"Y Niu","year":"2021","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.-S., Wen, J.-R.: Counterfactual vqa: A cause-effect look at language bias. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01251","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit."},{"key":"1560_CR28","doi-asserted-by":"publisher","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 21\u201329 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.10","DOI":"10.1109\/CVPR.2016.10"},{"key":"1560_CR29","unstructured":"Kim, J.-H., Jun, J., Zhang, B.-T.: Bilinear attention networks. Adv. Neural Inf. Process Syst. 31 (2018)"},{"key":"1560_CR30","doi-asserted-by":"crossref","unstructured":"Kervadec, C., Antipov, G.-g., Baccouche, M., Wolf, C.: Roses are red, violets are blue... but should vqa expect them to? In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 2776\u20132785 (2021)","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"1560_CR31","doi-asserted-by":"publisher","unstructured":"Li, L., Gan, Z., Cheng, Y., Liu, J.: Relation-aware graph attention network for visual question answering. In: Proc. IEEE Int. Conf. Comput. Vis., 10312\u201310321 (2019) https:\/\/doi.org\/10.1109\/ICCV.2019.01041","DOI":"10.1109\/ICCV.2019.01041"},{"issue":"11","key":"1560_CR32","doi-asserted-by":"publisher","first-page":"9015","DOI":"10.1007\/s00521-022-06923-0","volume":"34","author":"J Zhao","year":"2022","unstructured":"Zhao, J., Zhang, X., Wang, X., Yang, Y., Sun, G.: Overcoming language priors in VQA via adding visual module. Neural. Comput. Appl. 34(11), 9015\u20139023 (2022)","journal-title":"Neural. Comput. Appl."},{"key":"1560_CR33","doi-asserted-by":"crossref","unstructured":"Gokhale, T., Banerjee, P., Baral, C., Yang, Y.: Mutant: A training paradigm for out-of-distribution generalization in visual question answering. In: Proc. Conf. Empir . Methods Nat. Lang. Process, pp. 878\u2013892 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"1560_CR34","doi-asserted-by":"crossref","unstructured":"Liang, Z., Jiang, W., Hu, H., Zhu, J.: Learning to contrast the counterfactual samples for robust visual question answering. In: Proc. Conf. Empir . Methods Nat. Lang. Process, pp. 3285\u20133292 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"1560_CR35","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1109\/TIP.2021.3128322","volume":"31","author":"Y Guo","year":"2022","unstructured":"Guo, Y., Nie, L., Cheng, Z., Tian, Q., Zhang, M.: Loss re-scaling VQA: revisiting the language prior problem from a class-imbalance view. IEEE Trans. Image Process. 31, 227\u2013238 (2022). https:\/\/doi.org\/10.1109\/TIP.2021.3128322","journal-title":"IEEE Trans. Image Process."},{"key":"1560_CR36","doi-asserted-by":"publisher","unstructured":"Shrestha, R., Kafle, K., Kanan, C.: A negative case analysis of visual grounding methods for VQA. In: Proc. Assoc. Comput. Linguist., pp. 8172\u20138181 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.727","DOI":"10.18653\/v1\/2020.acl-main.727"},{"key":"1560_CR37","unstructured":"Cao, R., Li, Z.: Overcoming language priors for visual question answering via loss rebalancing label and global context. In: Uncertainty in Artificial Intelligence, pp. 249\u2013259 (2023). PMLR"},{"key":"1560_CR38","first-page":"11809","volume":"34","author":"D-B Wang","year":"2021","unstructured":"Wang, D.-B., Feng, L., Zhang, M.-L.: Rethinking calibration of deep neural networks: Do not be afraid of overconfidence. Adv. Neural. Inf. Process. Syst. 34, 11809\u201311820 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1560_CR39","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International Conference on Machine Learning, pp. 1321\u20131330 (2017). PMLR"},{"key":"1560_CR40","unstructured":"Zhang, J., Kailkhura, B., Han, T.Y.-J.: Mix-n-match: Ensemble and compositional methods for uncertainty calibration in deep learning. In: International Conference on Machine Learning, pp. 11117\u201311128 (2020). PMLR"},{"key":"1560_CR41","unstructured":"Gruber, S.G., Buettner, F.: Better uncertainty calibration via proper scores for classification and beyond. In: Advances in Neural Information Processing Systems (2022)"},{"key":"1560_CR42","unstructured":"Ghosh, A., Schaaf, T., Gormley, M.R.: Adafocal: Calibration-aware adaptive focal loss. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022). https:\/\/openreview.net\/forum?id=kUOm0Fdtvh"},{"key":"1560_CR43","unstructured":"Gupta, C., Ramdas, A.: Top-label calibration and multiclass-to-binary reductions. In: International Conference on Learning Representations (2022)"},{"key":"1560_CR44","doi-asserted-by":"crossref","unstructured":"Ren, A.Z., Clark, J., Dixit, A., Itkina, M., Majumdar, A., Sadigh, D.: Explore until confident: Efficient exploration for embodied question answering. In: First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA 2024","DOI":"10.15607\/RSS.2024.XX.089"},{"key":"1560_CR45","doi-asserted-by":"crossref","unstructured":"Munir, M.A., Khan, M.H., Khan, S., Khan, F.S.: Bridging precision and confidence: A train-time loss for calibrating object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11474\u201311483 (2023)","DOI":"10.1109\/CVPR52729.2023.01104"},{"key":"1560_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Zheng, C., Zhang, Z., Shao, W., Zhang, D.: Dynamic confidence-aware multi-modal emotion recognition. IEEE Trans. Affect. Comput. (2023)","DOI":"10.1109\/TAFFC.2023.3340924"},{"key":"1560_CR47","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1560_CR48","unstructured":"Gawlikowski, J., Tassi, C.R.N., Ali, M., Lee, J., Humt, M., Feng, J., Kruspe, A., Triebel, R., Jung, P., Roscher, R., et al.: A survey of uncertainty in deep neural networks. arXiv preprint arXiv:2107.03342 (2021)"},{"key":"1560_CR49","doi-asserted-by":"crossref","unstructured":"Xie, M., Han, Z., Zhang, C., Bai, Y., Hu, Q.: Exploring and exploiting uncertainty for incomplete multi-view classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19873\u201319882 (2023)","DOI":"10.1109\/CVPR52729.2023.01903"},{"key":"1560_CR50","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Cui, J., Liu, S., Jia, J.: Improving calibration for long-tailed recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 16489\u201316498 (2021)","DOI":"10.1109\/CVPR46437.2021.01622"},{"key":"1560_CR51","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 (EMNLP-IJCNLP), pp. 5100\u20135111 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"1560_CR52","first-page":"32897","volume":"35","author":"H Bao","year":"2022","unstructured":"Bao, H., Wang, W., Dong, L., Liu, Q., Mohammed, O.K., Aggarwal, K., Som, S., Piao, S., Wei, F.: Vlmo: Unified vision-language pre-training with mixture-of-modality-experts. Adv. Neural. Inf. Process. Syst. 35, 32897\u201332912 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1560_CR53","doi-asserted-by":"publisher","unstructured":"Pan, Y., Liu, J., Jin, L., Li, Z.: Unbiased visual question answering by leveraging instrumental variable. IEEE Transactions on Multimedia, 1\u201316 (2024) https:\/\/doi.org\/10.1109\/TMM.2024.3355640","DOI":"10.1109\/TMM.2024.3355640"},{"key":"1560_CR54","doi-asserted-by":"crossref","unstructured":"Si, Q., Liu, Y., Meng, F., Lin, Z., Fu, P., Cao, Y., Wang, W., Zhou, J.: Towards robust visual question answering: Making the most of biased samples via contrastive learning. In: Conference on Empirical Methods in Natural Language Processing (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.495"},{"key":"1560_CR55","unstructured":"Wu, Y., Zhao, Y., Zhao, S., Zhang, Y., Yuan, X., Zhao, G., Jiang, N.: Overcoming language priors in visual question answering via distinguishing superficially similar instances. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 5721\u20135729 (2022)"},{"key":"1560_CR56","doi-asserted-by":"crossref","unstructured":"Li, Y., Hu, B., Zhang, F., Yu, Y., Liu, J., Chen, Y., Xu, J.: A multi-modal debiasing model with dynamical constraint for robust visual question answering. In: Annual Meeting of the Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.findings-acl.311"},{"key":"1560_CR57","doi-asserted-by":"crossref","unstructured":"Shu, X., Yan, S., Yang, X., Wu, Z., Chen, Z., Lu, Z.: Sc-ml: Self-supervised counterfactual metric learning for debiased visual question answering. ArXiv abs\/2304.01647 (2023)","DOI":"10.2139\/ssrn.4544155"},{"issue":"2","key":"1560_CR58","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1109\/TCSVT.2023.3291379","volume":"34","author":"Y Bi","year":"2024","unstructured":"Bi, Y., Jiang, H., Hu, Y., Sun, Y., Yin, B.: See and learn more: dense caption-aware representation for visual question answering. IEEE Trans. Circuits Syst. Video Technol. 34(2), 1135\u20131146 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3291379","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01560-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01560-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01560-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T09:16:13Z","timestamp":1734340573000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01560-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,19]]},"references-count":58,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["1560"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01560-0","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2024,11,19]]},"assertion":[{"value":"15 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"348"}}