{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T04:25:31Z","timestamp":1744172731386,"version":"3.40.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Fundamental Research Funds for  the Central Universities","award":["No.31920240127","No.31920240127","No.31920240127"],"award-info":[{"award-number":["No.31920240127","No.31920240127","No.31920240127"]}]},{"name":"Gansu Province Education Technology Innovation Project","award":["No.2022QB-02"],"award-info":[{"award-number":["No.2022QB-02"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11760-025-03999-8","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T04:13:01Z","timestamp":1741666381000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimedia event extraction based on multimodal low-dimensional feature representation space"],"prefix":"10.1007","volume":"19","author":[{"given":"Yiming","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongrui","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"3999_CR1","unstructured":"Doddington, G., Mitchell, A., Przybocki, M., Ramshaw, L., Strassel, S., Weischedel, R.: The automatic content extraction (ACE) program \u2013 tasks, data, and evaluation. In: Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC\u201904). European Language Resources Association (ELRA), Lisbon, Portugal (2004)"},{"key":"3999_CR2","unstructured":"Ji, H., Grishman, R.: Refining event extraction through cross-document inference. In: Moore, J.D., Teufel, S., Allan, J., Furui, S. (eds.) Proceedings of ACL-08: HLT. Association for Computational Linguistics, Columbus, Ohio (2008)"},{"key":"3999_CR3","unstructured":"Wei, X., Cui, X., Cheng, N., Wang, X., Zhang, X., Huang, S., Xie, P., Xu, J., Chen, Y., Zhang, M., Jiang, Y., Han, W.: Zero-shot information extraction via chatting with ChatGPT (2023)"},{"key":"3999_CR4","doi-asserted-by":"crossref","unstructured":"Yatskar, M., Zettlemoyer, L., Farhadi, A.: Situation recognition: visual semantic role labeling for image understanding. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5534\u20135542 (2016)","DOI":"10.1109\/CVPR.2016.597"},{"key":"3999_CR5","doi-asserted-by":"crossref","unstructured":"Li, M., Zareian, A., Zeng, Q., Whitehead, S., Lu, D., Ji, H., Chang, S.-F.: Cross-media structured common space for multimedia event extraction. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online (2020)","DOI":"10.18653\/v1\/2020.acl-main.230"},{"key":"3999_CR6","doi-asserted-by":"crossref","unstructured":"Wang, X., Han, X., Liu, Z., Sun, M., Li, P.: Adversarial training for weakly supervised event detection. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 998\u20131008 (2019)","DOI":"10.18653\/v1\/N19-1105"},{"key":"3999_CR7","unstructured":"Li, J., Selvaraju, R.R., Gotmare, A.D., Joty, S.R., Xiong, C., Hoi, S.C.H.: Align before fuse: Vision and language representation learning with momentum distillation. CoRR (2021) arXiv:2107.07651"},{"key":"3999_CR8","unstructured":"He, P., Gao, J., Chen, W.: Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. CoRR (2021) arXiv:2111.09543"},{"key":"3999_CR9","doi-asserted-by":"crossref","unstructured":"Li, M., Xu, R., Wang, S., Zhou, L., Lin, X., Zhu, C., Zeng, M., Ji, H., Chang, S.-F.: Clip-event: Connecting text and images with event structures. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16399\u201316408 (2022)","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"3999_CR10","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. CoRR (2021) arXiv:2103.00020"},{"key":"3999_CR11","doi-asserted-by":"crossref","unstructured":"Liu, J., Chen, Y., Xu, J.: Multimedia event extraction from news with a unified contrastive learning framework. In: Proceedings of the 30th ACM International Conference on Multimedia. MM \u201922, pp. 1945\u20131953. Association for Computing Machinery, New York, NY, USA (2022)","DOI":"10.1145\/3503161.3548132"},{"key":"3999_CR12","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the Knowledge in a Neural Network (2015)"},{"key":"3999_CR13","doi-asserted-by":"crossref","unstructured":"Duan, J., Chen, L., Tran, S., Yang, J., Xu, Y., Zeng, B., Chilimbi, T.: Multi-modal alignment using representation codebook. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15651\u201315660 (2022)","DOI":"10.1109\/CVPR52688.2022.01520"},{"key":"3999_CR14","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: Simvlm: Simple visual language model pretraining with weak supervision. CoRR (2021) arXiv:2108.10904"},{"key":"3999_CR15","unstructured":"Zeng, A., Attarian, M., Ichter, B., Choromanski, K., Wong, A., Welker, S., Tombari, F., Purohit, A., Ryoo, M., Sindhwani, V., Lee, J., Vanhoucke, V., Florence, P.: Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022). arXiv:2204.00598"},{"key":"3999_CR16","unstructured":"Su, Y., Lan, T., Liu, Y., Liu, F., Yogatama, D., Wang, Y., Kong, L., Collier, N.: Language Models Can See: Plugging Visual Controls in Text Generation (2022). arXiv:2205.02655"},{"key":"3999_CR17","doi-asserted-by":"crossref","unstructured":"Fei, J., Wang, T., Zhang, J., He, Z., Wang, C., Zheng, F.: Transferable decoding with visual entities for zero-shot image captioning (2023)","DOI":"10.1109\/ICCV51070.2023.00291"},{"key":"3999_CR18","doi-asserted-by":"publisher","first-page":"109806","DOI":"10.1016\/j.engappai.2024.109806","volume":"141","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Zhang, T., Wang, S., Yu, P.: An efficient perceptual video compression scheme based on deep learning-assisted video saliency and just noticeable distortion. Eng. Appl. Artif. Intell. 141, 109806 (2025). https:\/\/doi.org\/10.1016\/j.engappai.2024.109806","journal-title":"Eng. Appl. Artif. Intell."},{"key":"3999_CR19","doi-asserted-by":"publisher","first-page":"173850","DOI":"10.1109\/ACCESS.2024.3503276","volume":"12","author":"S Babu Veesam","year":"2024","unstructured":"Babu Veesam, S., Satish, A.R.: An empirical taxonomy of video summarization model from a statistical perspective. IEEE Access 12, 173850\u2013173866 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3503276","journal-title":"IEEE Access"},{"issue":"4","key":"3999_CR20","doi-asserted-by":"publisher","first-page":"2775","DOI":"10.1109\/TCSVT.2023.3312325","volume":"34","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Liu, Y., Kang, W., Tao, R.: Vss-net: visual semantic self-mining network for video summarization. IEEE Trans. Circuits Syst. Video Technol. 34(4), 2775\u20132788 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3312325","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"3999_CR21","doi-asserted-by":"publisher","first-page":"013005","DOI":"10.1117\/1.JEI.34.1.013005","volume":"34","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Wang, S., Zhang, Y., Yu, P.: Asymmetric light-aware progressive decoding network for rgb-thermal salient object detection. J. Electron. Imaging 34(1), 013005\u2013013005 (2025)","journal-title":"J. Electron. Imaging"},{"issue":"1","key":"3999_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-024-80830-3","volume":"14","author":"F Huang","year":"2024","unstructured":"Huang, F., Zheng, J., Liu, X., Shen, Y., Chen, J.: Polarization of road target detection under complex weather conditions. Sci. Rep. 14(1), 1\u201318 (2024)","journal-title":"Sci. Rep."},{"key":"3999_CR23","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 397\u2013406 (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"3999_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3392794","volume":"62","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Wu, C., Zhang, T., Zheng, Y.: Full-scale feature aggregation and grouping feature reconstruction-based uav image target detection. IEEE Trans. Geosci. Remote Sens. 62, 1\u201311 (2024). https:\/\/doi.org\/10.1109\/TGRS.2024.3392794","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3999_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhen, J., Liu, T., Yang, Y., Cheng, Y.: Adaptive differentiation siamese fusion network for remote sensing change detection. IEEE Geoscience and Remote Sensing Letters (2024)","DOI":"10.1109\/LGRS.2024.3516775"},{"key":"3999_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Yan, W.: Cfanet: A cross-layer feature aggregation network for camouflaged object detection. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 2441\u20132446 (2023). IEEE","DOI":"10.1109\/ICME55011.2023.00416"},{"key":"3999_CR27","doi-asserted-by":"publisher","first-page":"4183","DOI":"10.1109\/TMM.2023.3321394","volume":"26","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Zhang, T., Wu, C., Tao, R.: Multi-scale spatiotemporal feature fusion network for video saliency prediction. IEEE Trans. Multimed. 26, 4183\u20134193 (2024). https:\/\/doi.org\/10.1109\/TMM.2023.3321394","journal-title":"IEEE Trans. Multimed."},{"key":"3999_CR28","unstructured":"Zhang, J., Yan, W., Zhang, Y.: A new Speech Feature Fusion method with cross gate parallel CNN for Speaker Recognition (2022). arXiv:2211.13377"},{"key":"3999_CR29","unstructured":"Boguraev, B., Mu\u00f1oz, R., Pustejovsky, J. (eds.): Proceedings of the Workshop on Annotating and Reasoning About Time and Events. Association for Computational Linguistics, Sydney, Australia (2006)"},{"key":"3999_CR30","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. (2019)"},{"key":"3999_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. CoRR (2019) arXiv:1911.05722","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"3999_CR32","unstructured":"Walker, C., Strassel, S., Medero, J., Maeda, K.: Ace 2005 multilingual training corpus-linguistic data consortium (2005)"},{"key":"3999_CR33","doi-asserted-by":"crossref","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Research Logistics (NRL) (1955)","DOI":"10.1002\/nav.3800020109"},{"key":"3999_CR34","unstructured":"Zhang, T., Ji, H.: Event Extraction with Generative Adversarial Imitation Learning (2018)"},{"key":"3999_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, T., Whitehead, S., Zhang, H., Li, H., Ellis, J., Huang, L., Liu, W., Ji, H., Chang, S.-F.: Improving event extraction via multimodal integration. In: Proceedings of the 25th ACM International Conference on Multimedia. MM 17, pp. 270\u2013278. Association for Computing Machinery, New York, NY, USA (2017)","DOI":"10.1145\/3123266.3123294"},{"key":"3999_CR36","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Le\u00a0Scao, T., Gugger, S., Drame, M., Lhoest, Q., Rush, A.: Transformers: State-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online (2020)","DOI":"10.18653\/v1\/2020.emnlp-demos.6"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03999-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-03999-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03999-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T20:09:30Z","timestamp":1744142970000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-03999-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,11]]},"references-count":36,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["3999"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-03999-8","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,3,11]]},"assertion":[{"value":"11 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2025","order":4,"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":"397"}}