{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:42:42Z","timestamp":1778258562956,"version":"3.51.4"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,3,9]],"date-time":"2025-03-09T00:00:00Z","timestamp":1741478400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,9]],"date-time":"2025-03-09T00:00:00Z","timestamp":1741478400000},"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":[[2025,4]]},"DOI":"10.1007\/s00530-025-01683-y","type":"journal-article","created":{"date-parts":[[2025,3,9]],"date-time":"2025-03-09T14:48:51Z","timestamp":1741531731000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["KN-VLM: KNowledge-guided Vision-and-Language Model for visual abductive reasoning"],"prefix":"10.1007","volume":"31","author":[{"given":"Kuo","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaobo","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianping","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanrong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weigang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,9]]},"reference":[{"key":"1683_CR1","doi-asserted-by":"crossref","unstructured":"Hayes, B.K., Heit, E., Swendsen, H.: Inductive reasoning. Wiley interdisciplinary reviews: Cognitive science. 1(2), 278\u2013292 (2010)","DOI":"10.1002\/wcs.44"},{"issue":"1","key":"1683_CR2","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1146\/annurev.psych.50.1.109","volume":"50","author":"PN Johnson-Laird","year":"1999","unstructured":"Johnson-Laird, P.N.: Deductive reasoning. Annu. Rev. Psychol. 50(1), 109\u2013135 (1999)","journal-title":"Annu. Rev. Psychol."},{"key":"1683_CR3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511529863","volume-title":"Similarity and analogical reasoning","author":"S Vosniadou","year":"1989","unstructured":"Vosniadou, S., Ortony, A.: Similarity and analogical reasoning. Cambridge University Press (1989)"},{"issue":"10","key":"1683_CR4","doi-asserted-by":"publisher","first-page":"3476","DOI":"10.1109\/TPAMI.2020.2985708","volume":"43","author":"J Gao","year":"2020","unstructured":"Gao, J., Zhang, T., Xu, C.: Learning to model relationships for zero-shot video classification. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3476\u20133491 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1683_CR5","unstructured":"Xue, H., Sun, Y., Liu, B., Fu, J., Song, R., Li, H., Luo, J.: Clip-vip: Adapting pre-trained image-text model to video-language alignment. In: Proceedings of the 11th International Conference on Learning Representations (2023)"},{"issue":"12","key":"1683_CR6","doi-asserted-by":"publisher","first-page":"15949","DOI":"10.1109\/TPAMI.2023.3311447","volume":"45","author":"J Gao","year":"2023","unstructured":"Gao, J., Chen, M., Xu, C.: Vectorized evidential learning for weakly-supervised temporal action localization. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15949\u201315963 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"1683_CR7","doi-asserted-by":"publisher","first-page":"6715","DOI":"10.1109\/TPAMI.2021.3059923","volume":"45","author":"Z Qi","year":"2023","unstructured":"Qi, Z., Wang, S., Su, C., Su, L., Huang, Q., Tian, Q.: Self-regulated learning for egocentric video activity anticipation. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 6715\u20136730 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1683_CR8","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the International Conference on Machine Learning, pp. 19730\u201319742 (2023)"},{"key":"1683_CR9","doi-asserted-by":"crossref","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., Hou, L.: Timechat: A time-sensitive multimodal large language model for long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14313\u201314323 (2024)","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"1683_CR10","doi-asserted-by":"crossref","unstructured":"Qi, Z., Wang, S., Zhang, W., Huang, Q.: Uncertainty-boosted robust video activity anticipation. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 7775\u20137792 (2024)","DOI":"10.1109\/TPAMI.2024.3393730"},{"key":"1683_CR11","unstructured":"Dai, W., Li, J., Li, D., Tiong, A.M.H., Zhao, J., Wang, W., Li, B., Fung, P.N., Hoi, S.: Instructblip: Towards general-purpose vision-language models with instruction tuning. In: Proceedings of Advances in Neural Information Processing Systems, pp. 49250\u201349267 (2023)"},{"key":"1683_CR12","unstructured":"Luo, G., Zhou, Y., Ren, T., Chen, S., Sun, X., Ji, R.: Cheap and quick: Efficient vision-language instruction tuning for large language models. In: Proceedings of Advances in Neural Information Processing Systems, pp. 29615\u201329627 (2023)"},{"key":"1683_CR13","doi-asserted-by":"crossref","unstructured":"Qi, Z., Yuan, Y., Ruan, X., Wang, S., Zhang, W., Huang, Q.: Bias-conflict sample synthesis and adversarial removal debias strategy for temporal sentence grounding in video. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4533\u20134541 (2024)","DOI":"10.1609\/aaai.v38i5.28252"},{"key":"1683_CR14","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, B., Ye, Y., Ning, M., Jin, P., Yuan, L.: Video-llava: Learning united visual representation by alignment before projection. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 5971\u20135984 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"1683_CR15","unstructured":"Lin, B., Tang, Z., Ye, Y., Cui, J., Zhu, B., Jin, P., Zhang, J., Ning, M., Yuan, L.: Moe-llava: Mixture of experts for large vision-language models. arXiv preprint arXiv:2401.15947 (2024)"},{"key":"1683_CR16","doi-asserted-by":"crossref","unstructured":"Qi, Z., Yuan, Y., Ruan, X., Wang, S., Zhang, W., Huang, Q.: Collaborative debias strategy for temporal sentence grounding in video. IEEE Transactions on Circuits and Systems for Video Technology. 34(11), 10972\u201310986 (2024)","DOI":"10.1109\/TCSVT.2024.3413074"},{"key":"1683_CR17","doi-asserted-by":"crossref","unstructured":"Liang, C., Wang, W., Zhou, T., Yang, Y.: Visual abductive reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15565\u201315575 (2022)","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"1683_CR18","unstructured":"Tan, C., Yeo, C.K., Tan, C., Fernando, B.: Abductive action inference. arXiv preprint arXiv:2210.13984 (2022)"},{"key":"1683_CR19","unstructured":"Hong, X., Lan, Y., Pang, L., Guo, J., Cheng, X.: Visual transformation telling. arXiv preprint arXiv:2305.01928 (2023)"},{"key":"1683_CR20","doi-asserted-by":"crossref","unstructured":"Charoenpitaks, K., Nguyen, V.-Q., Suganuma, M., Takahashi, M., Niihara, R., Okatani, T.: Exploring the potential of multi-modal ai for driving hazard prediction. IEEE Transactions on Intelligent Vehicles, 1\u201311 (2024)","DOI":"10.1109\/TIV.2024.3417353"},{"key":"1683_CR21","doi-asserted-by":"crossref","unstructured":"Hong, X., Lan, Y., Pang, L., Guo, J., Cheng, X.: Visual reasoning: From state to transformation. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 11352\u201311364 (2023)","DOI":"10.1109\/TPAMI.2023.3268093"},{"key":"1683_CR22","doi-asserted-by":"crossref","unstructured":"Li, M., Wang, T., Xu, J., Han, K., Zhang, S., Zhao, Z., Miao, J., Zhang, W., Pu, S., Wu, F.: Multi-modal action chain abductive reasoning. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, pp. 4617\u20134628 (2023)","DOI":"10.18653\/v1\/2023.acl-long.254"},{"key":"1683_CR23","doi-asserted-by":"crossref","unstructured":"Speer, R., Chin, J., Havasi, C.: Conceptnet 5.5: An open multilingual graph of general knowledge. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4444\u20134451 (2017)","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"1683_CR24","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., Ji, L., Zhong, M., Chen, Y., Lei, W., Duan, N., Li, T.: Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing.\u00a0508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"1683_CR25","first-page":"8483","volume":"35","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Li, M., Xu, R., Zhou, L., Lei, J., Lin, X., Wang, S., Yang, Z., Zhu, C., Hoiem, D., et al.: Language models with image descriptors are strong few-shot video-language learners. In: Proceedings of Advances in Neural Information Processing Systems, pp.\u00a08483\u20138497\u00a0(2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1683_CR26","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.: Towards automatic learning of procedures from web instructional videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 7590\u20137598 (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"1683_CR27","volume-title":"Collected Papers of Charles Sanders Peirce","author":"CS Peirce","year":"1931","unstructured":"Peirce, C.S.: Collected Papers of Charles Sanders Peirce. Harvard University Press. 1\u00a0(1931)"},{"key":"1683_CR28","unstructured":"Bhagavatula, C., Le Bras, R., Malaviya, C., Sakaguchi, K., Holtzman, A., Rashkin, H., Downey, D., Yih, W.-T., Choi, Y.: Abductive commonsense reasoning. In: Proceedings of the 7th International Conference on Learning Representations (2019)"},{"key":"1683_CR29","unstructured":"Shi, X., Xue, S., Wang, K., Zhou, F., Zhang, J., Zhou, J., Tan, C., Mei, H.: Language models can improve event prediction by few-shot abductive reasoning. In: Proceedings of Advances in Neural Information Processing Systems, pp. 29532\u201329557 (2023)"},{"key":"1683_CR30","doi-asserted-by":"crossref","unstructured":"Fang, J., Li, L.-l., Zhou, J., Xiao, J., Yu, H., Lv, C., Xue, J., Chua, T.-S.: Abductive ego-view accident video understanding for safe driving perception. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22030\u201322040 (2024)","DOI":"10.1109\/CVPR52733.2024.02080"},{"key":"1683_CR31","unstructured":"Yao, L., Mao, C., Luo, Y.: Kg-bert: Bert for knowledge graph completion. arXiv preprint arXiv:1909.03193 (2019)"},{"key":"1683_CR32","doi-asserted-by":"crossref","unstructured":"Lv, S., Guo, D., Xu, J., Tang, D., Duan, N., Gong, M., Shou, L., Jiang, D., Cao, G., Hu, S.: Graph-based reasoning over heterogeneous external knowledge for commonsense question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8449\u20138456 (2020)","DOI":"10.1609\/aaai.v34i05.6364"},{"issue":"2","key":"1683_CR33","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1109\/TNNLS.2021.3070843","volume":"33","author":"S Ji","year":"2021","unstructured":"Ji, S., Pan, S., Cambria, E., Marttinen, P., Philip, S.Y.: A survey on knowledge graphs: representation, acquisition, and applications. IEEE transactions on neural networks and learning systems.\u00a033(2), 494\u2013514 (2021)","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"1683_CR34","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.aiopen.2021.03.001","volume":"2","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Chen, B., Zhang, L., Ke, X., Ding, H.: Neural, symbolic and neural-symbolic reasoning on knowledge graphs. AI Open.\u00a02, 14\u201335 (2021)","journal-title":"AI Open"},{"key":"1683_CR35","unstructured":"Zeng, P., Zhang, H., Gao, L., Li, X., Qian, J., Shen, H.T.: Visual commonsense-aware representation network for video captioning. arXiv preprint arXiv:2211.09469 (2022)"},{"key":"1683_CR36","doi-asserted-by":"crossref","unstructured":"Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., Wu, X.: Unifying large language models and knowledge graphs: A roadmap. IEEE Transactions on Knowledge and Data Engineering. 36(7), 3580\u20133599 (2023)","DOI":"10.1109\/TKDE.2024.3352100"},{"key":"1683_CR37","doi-asserted-by":"crossref","unstructured":"Hu, Y., Gao, J., Dong, J., Fan, B., Liu, H.: Exploring rich semantics for open-set action recognition. IEEE Transactions on Multimedia. 26, 5410\u20135421 (2024)","DOI":"10.1109\/TMM.2023.3333206"},{"issue":"10","key":"1683_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3678882","volume":"20","author":"Z Wu","year":"2024","unstructured":"Wu, Z., Gao, J., Huang, S., Xu, C.: Learning commonsense-aware moment-text alignment for fast video temporal grounding. ACM Trans. Multimed. Comput. Commun. Appl. 20(10), 1\u201322 (2024)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"1683_CR39","doi-asserted-by":"crossref","unstructured":"Sap, M., Le Bras, R., Allaway, E., Bhagavatula, C., Lourie, N., Rashkin, H., Roof, H., A.Smit, N., Choi, Y.: Atomic: An atlas of machine commonsense for if-then reasoning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3027\u20133035 (2019)","DOI":"10.1609\/aaai.v33i01.33013027"},{"key":"1683_CR40","unstructured":"Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., Choi, Y.: Comet: Commonsense transformers for automatic knowledge graph construction. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4617\u20134628 (2023)"},{"key":"1683_CR41","doi-asserted-by":"crossref","unstructured":"Qi, Z., Wang, S., Su, C., Su, L., Huang, Q., Tian, Q.: Towards more explainability: concept knowledge mining network for event recognition. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 3857\u20133865 (2020)","DOI":"10.1145\/3394171.3413954"},{"key":"1683_CR42","doi-asserted-by":"crossref","unstructured":"Qi, Z., Wang, S., Su, C., Su, L., Zhang, W., Huang, Q.: Modeling temporal concept receptive field dynamically for untrimmed video analysis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 3798\u20133806 (2020)","DOI":"10.1145\/3394171.3413618"},{"key":"1683_CR43","doi-asserted-by":"crossref","unstructured":"Chou, S.-H., Little, J.J., Sigal, L.: Implicit and explicit commonsense for multi-sentence video captioning. Computer Vision and Image Understanding. 247, 104064 (2024)","DOI":"10.1016\/j.cviu.2024.104064"},{"key":"1683_CR44","doi-asserted-by":"crossref","unstructured":"Gupta, S., Saini, N., Kundu, S., Das, D.: Crisiskan: Knowledge-infused and explainable multimodal attention network for crisis event classification. In: Proceedings of the 46th European Conference on Information Retrieval, pp. 18\u201333 (2024)","DOI":"10.1007\/978-3-031-56060-6_2"},{"key":"1683_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhou, Y., Corso, J.J., Socher, R., Xiong, C.: End-to-end dense video captioning with masked transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8739\u20138748 (2018)","DOI":"10.1109\/CVPR.2018.00911"},{"key":"1683_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, L., Kalantidis, Y., Chen, X., Corso, J.J., Rohrbach, M.: Grounded video description. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6578\u20136587 (2019)","DOI":"10.1109\/CVPR.2019.00674"},{"key":"1683_CR47","doi-asserted-by":"crossref","unstructured":"Iashin, V., Rahtu, E.: Multi-modal dense video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 958\u2013959 (2020)","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"1683_CR48","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhang, R., Lu, Z., Zheng, F., Cheng, R., Luo, P.: End-to-end dense video captioning with parallel decoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6847\u20136857 (2021)","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"1683_CR49","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, Y., He, Y., Li, Y., Wang, Y., Liu, Y., Wang, Z., Xu, J., Chen, G., Luo, P., et al.: Mvbench: A comprehensive multi-modal video understanding benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 22195\u201322206 (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"1683_CR50","unstructured":"Cao, Y., Zhang, P., Dong, X., Lin, D., Wang, J.: Dualfocus: Integrating macro and micro perspectives in multi-modal large language models. arXiv preprint arXiv:2402.14767 (2024)"},{"key":"1683_CR51","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"1683_CR52","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhu, C., Xu, R., Liu, Y., Zeng, M., Huang, X.: Fusing context into knowledge graph for commonsense question answering. In: Proceedings of the Findings of the Association for Computational Linguistics, pp. 1201\u20131207 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.102"},{"key":"1683_CR53","unstructured":"Kenton, J.D.M.-W.C., Toutanova, L.K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, pp. 4171\u20134186 (2019)"},{"key":"1683_CR54","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"1683_CR55","unstructured":"Banerjee, S., Lavie, A.: Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation And\/or Summarization, pp. 65\u201372 (2005)"},{"key":"1683_CR56","doi-asserted-by":"crossref","unstructured":"Lin, C.-Y., Hovy, E.: Manual and automatic evaluation of summaries. In: Proceedings of the ACL Workshop on Automatic Summarization, pp. 45\u201351 (2002)","DOI":"10.3115\/1118162.1118168"},{"key":"1683_CR57","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"1683_CR58","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: Evaluating text generation with bert. In: Proceedings of the 7th International Conference on Learning Representations (2019)"},{"key":"1683_CR59","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Dai, B., Lin, D.: Move forward and tell: A progressive generator of video descriptions. In: Proceedings of the European Conference on Computer Vision, pp. 468\u2013483 (2018)","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"1683_CR60","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J.G., Le, Q., Salakhutdinov, R.: Transformer-xl: Attentive language models beyond a fixed-length context. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2978\u20132988 (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"1683_CR61","doi-asserted-by":"crossref","unstructured":"Lei, J., Wang, L., Shen, Y., Yu, D., Berg, T., Bansal, M.: Mart: Memory-augmented recurrent transformer for coherent video paragraph captioning. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2603\u20132614 (2020)","DOI":"10.18653\/v1\/2020.acl-main.233"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01683-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01683-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01683-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T15:36:03Z","timestamp":1745249763000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01683-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,9]]},"references-count":61,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["1683"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01683-y","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4934011\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,9]]},"assertion":[{"value":"18 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2025","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"146"}}