{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T23:57:03Z","timestamp":1781308623327,"version":"3.54.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:00:00Z","timestamp":1741219200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:00:00Z","timestamp":1741219200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems"},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["345791"],"award-info":[{"award-number":["345791"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476188"],"award-info":[{"award-number":["62476188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis. Intell."],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Text-to-video retrieval (TVR) has made significant progress with advances in vision and language representation learning. Most existing methods use real-valued and hash-based embeddings to represent the video and text, allowing retrieval by computing their similarities. However, these methods are often inefficient for large volumes of video, and require significant storage and computing resources. In this work, we present a plug-and-play multi-modal multi-tagger-driven pre-screening framework, which pre-screens a substantial number of videos before applying any TVR algorithms, thereby efficiently reducing the search space of videos. We predict discrete semantic tags for video and text with our proposed multi-modal multi-tagger module, and then leverage an inverted index for space-efficient and fast tag matching to filter out irrelevant videos. To avoid filtering out relevant videos for text queries due to inconsistent tags, we utilize contrastive learning to align video and text embeddings, which are then fed into a shared multi-tag head. Extensive experimental results demonstrate that our proposed method significantly accelerates the TVR process while maintaining high retrieval accuracy on various TVR datasets.<\/jats:p>","DOI":"10.1007\/s44267-025-00073-2","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T02:27:44Z","timestamp":1741228064000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Efficient text-to-video retrieval via multi-modal multi-tagger derived pre-screening"],"prefix":"10.1007","volume":"3","author":[{"given":"Yingjia","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengxia","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixin","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mang","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jorma","family":"Laaksonen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,6]]},"reference":[{"key":"73_CR1","first-page":"214","volume-title":"Proceedings of the 16th European conference on computer vision","author":"V. Gabeur","year":"2020","unstructured":"Gabeur, V., Sun, C., Alahari, K., & Schmid, C. (2020). Multi-modal transformer for video retrieval. In A. Vedaldi, H. Bischof, T. Brox, et al. (Eds.), Proceedings of the 16th European conference on computer vision (pp. 214\u2013229). Cham: Springer."},{"issue":"3","key":"73_CR2","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1109\/TPAMI.2013.142","volume":"36","author":"J. C. Pereira","year":"2013","unstructured":"Pereira, J. C., Coviello, E., Doyle, G., Rasiwasia, N., Lanckriet, G. R. G., Levy, R., et al. (2013). On the role of correlation and abstraction in cross-modal multimedia retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(3), 521\u2013535.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"73_CR3","first-page":"10638","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"S. Chen","year":"2020","unstructured":"Chen, S., Zhao, Y., Jin, Q., & Wu, Q. (2020). Fine-grained video-text retrieval with hierarchical graph reasoning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10638\u201310647). Piscataway: IEEE."},{"issue":"1","key":"73_CR4","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s11633-022-1369-5","volume":"20","author":"F.-L. Chen","year":"2023","unstructured":"Chen, F.-L., Zhang, D.-Z., Han, M.-L., Chen, X.-Y., Shi, J., Xu, S., et al. (2023). VLP: a survey on vision-language pre-training. Machine Intelligence Research, 20(1), 38\u201356.","journal-title":"Machine Intelligence Research"},{"key":"73_CR5","first-page":"15671","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"J. Yang","year":"2022","unstructured":"Yang, J., Duan, J., Tran, S., Xu, Y., Chanda, S., Chen, L., et al. (2022). Vision-language pre-training with triple contrastive learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 15671\u201315680). Piscataway: IEEE."},{"key":"73_CR6","first-page":"12888","volume-title":"Proceedings of the 39th international conference on machine learning","author":"J. Li","year":"2022","unstructured":"Li, J., Li, D., Xiong, C., & Hoi, S. C. H. (2022). BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In K. Chaudhuri, S. Jegelka, & L. Song (Eds.), Proceedings of the 39th international conference on machine learning (pp. 12888\u201312900). Retrieved July 17, 2024, from https:\/\/proceedings.mlr.press\/v162\/li22n.html."},{"key":"73_CR7","first-page":"1728","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"M. Bain","year":"2021","unstructured":"Bain, M., Nagrani, A., Varol, G., & Zisserman, A. (2021). Frozen in time: a joint video and image encoder for end-to-end retrieval. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1728\u20131738). Piscataway: IEEE."},{"key":"73_CR8","first-page":"7331","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"J. Lei","year":"2021","unstructured":"Lei, J., Li, L., Zhou, L., Gan, Z., Berg, T. L., Bansal, M., et al. (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). Piscataway: IEEE."},{"key":"73_CR9","first-page":"279","volume-title":"Proceedings of the 30th British machine vision conference","author":"Y. Liu","year":"2019","unstructured":"Liu, Y., Albanie, S., Nagrani, A., & Zisserman, A. (2019). Use what you have: video retrieval using representations from collaborative experts. In Proceedings of the 30th British machine vision conference (p.\u00a0279). Swansea: BMVA Press."},{"key":"73_CR10","doi-asserted-by":"publisher","first-page":"1786","DOI":"10.1145\/3343031.3350906","volume-title":"Proceedings of the 27th ACM international conference on multimedia","author":"X. Li","year":"2019","unstructured":"Li, X., Xu, C., Yang, G., Chen, Z., & Dong, J. (2019). W2VV++ fully deep learning for ad-hoc video search. In L. Amsaleg, B. Huet, M. A. Larson, et al. (Eds.), Proceedings of the 27th ACM international conference on multimedia (pp. 1786\u20131794). New York: ACM."},{"key":"73_CR11","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1145\/3397271.3401151","volume-title":"Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval","author":"X. Yang","year":"2020","unstructured":"Yang, X., Dong, J., Cao, Y., Wang, X., Wang, M., & Chua, T.-S. (2020). Tree-augmented cross-modal encoding for complex-query video retrieval. In J. X. Huang, Y. Chang, X. Cheng, et al. (Eds.), Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval (pp. 1339\u20131348). New York: ACM."},{"issue":"12","key":"73_CR12","doi-asserted-by":"publisher","first-page":"3377","DOI":"10.1109\/TMM.2018.2832602","volume":"20","author":"J. Dong","year":"2018","unstructured":"Dong, J., Li, X., & Snoek, C. G. M. (2018). Predicting visual features from text for image and video caption retrieval. IEEE Transactions on Multimedia, 20(12), 3377\u20133388.","journal-title":"IEEE Transactions on Multimedia"},{"issue":"1","key":"73_CR13","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1109\/TCSVT.2023.3285266","volume":"34","author":"Y. Huo","year":"2024","unstructured":"Huo, Y., Qin, Q., Dai, J., Wang, L., Zhang, W., Huang, L., et al. (2024). Deep semantic-aware proxy hashing for multi-label cross-modal retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 34(1), 576\u2013589.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"3","key":"73_CR14","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1007\/s12559-021-09847-4","volume":"14","author":"J. Yu","year":"2022","unstructured":"Yu, J., Wu, X.-J., & Zhang, D. (2022). Unsupervised multi-modal hashing for cross-modal retrieval. Cognitive Computation, 14(3), 1159\u20131171.","journal-title":"Cognitive Computation"},{"issue":"12","key":"73_CR15","doi-asserted-by":"publisher","first-page":"8822","DOI":"10.1109\/TCSVT.2022.3195874","volume":"32","author":"Y. Wang","year":"2022","unstructured":"Wang, Y., Chen, Z.-D., Luo, X., & Xu, X.-S. (2022). A high-dimensional sparse hashing framework for cross-modal retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 32(12), 8822\u20138836.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"73_CR16","doi-asserted-by":"publisher","first-page":"2265","DOI":"10.1007\/s11263-020-01331-0","volume":"128","author":"Z. Li","year":"2020","unstructured":"Li, Z., Tang, J., Zhang, L., & Yang, J. (2020). Weakly-supervised semantic guided hashing for social image retrieval. International Journal of Computer Vision, 128, 2265\u20132278.","journal-title":"International Journal of Computer Vision"},{"key":"73_CR17","doi-asserted-by":"publisher","first-page":"3036","DOI":"10.18653\/v1\/2022.findings-emnlp.221","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2022","author":"X. Wu","year":"2022","unstructured":"Wu, X., Gao, C., Lin, Z., Wang, Z., Han, J., & Hu, S. (2022). RaP: redundancy-aware video-language pre-training for text-video retrieval. In Y. Goldberg, Z. Kozareva, & Y. Zhang (Eds.), Findings of the Association for Computational Linguistics: EMNLP 2022 (pp. 3036\u20133047). Stroudsburg: ACL."},{"key":"73_CR18","doi-asserted-by":"crossref","unstructured":"Cao, M., Tang, H., Huang, J., Jin, P., Zhang, C., Liu, R., et\u00a0al. (2024). Efficient text-video retrieval with sparse-and-correlated adapter. arXiv preprint. arXiv:2405.19465.","DOI":"10.18653\/v1\/2024.findings-acl.427"},{"key":"73_CR19","first-page":"4100","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"P. Li","year":"2023","unstructured":"Li, P., Xie, C.-W., Zhao, L., Xie, H., Ge, J., Zheng, Y., et al. (2023). Progressive spatio-temporal prototype matching for text-video retrieval. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 4100\u20134110). Piscataway: IEEE."},{"key":"73_CR20","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1145\/3477495.3531950","volume-title":"Proceedings of the 45th international ACM SIGIR conference on research and development in information retrieval","author":"S. Zhao","year":"2022","unstructured":"Zhao, S., Zhu, L., Wang, X., & Yang, Y. (2022). Centerclip: token clustering for efficient text-video retrieval. In E. Amig\u00f3, P. Castells, J. Gonzalo, et al. (Eds.), Proceedings of the 45th international ACM SIGIR conference on research and development in information retrieval (pp. 970\u2013981). New York: ACM."},{"key":"73_CR21","first-page":"2816","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Z. Wang","year":"2023","unstructured":"Wang, Z., Sung, Y.-L., Cheng, F., Bertasius, G., & Bansal, M. (2023). Unified coarse-to-fine alignment for video-text retrieval. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2816\u20132827). Piscataway: IEEE."},{"key":"73_CR22","first-page":"5207","volume-title":"Proceedings of the AAAI conference on artificial intelligence","author":"K. Tian","year":"2024","unstructured":"Tian, K., Cheng, Y., Liu, Y., Hou, X., Chen, Q., & Li, H. (2024). Towards efficient and effective text-to-video retrieval with coarse-to-fine visual representation learning. In M. J. Wooldridge, J. G. Dy, & S. Natarajan (Eds.), Proceedings of the AAAI conference on artificial intelligence (pp. 5207\u20135214). Palo Alto: AAAI Press."},{"key":"73_CR23","first-page":"11915","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"S. Liu","year":"2021","unstructured":"Liu, S., Fan, H., Qian, S., Chen, Y., Ding, W., & Wang, Z. (2021). HIT: hierarchical transformer with momentum contrast for video-text retrieval. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 11915\u201311925). Piscataway: IEEE."},{"key":"73_CR24","first-page":"5288","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"J. Xu","year":"2016","unstructured":"Xu, J., Mei, T., Yao, T., & Rui, Y. (2016). MSR-VTT: a large video description dataset for bridging video and language. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5288\u20135296). Piscataway: IEEE."},{"key":"73_CR25","first-page":"3650","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"M. Wray","year":"2021","unstructured":"Wray, M., Doughty, H., & Damen, D. (2021). On semantic similarity in video retrieval. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3650\u20133660). Piscataway: IEEE."},{"key":"73_CR26","volume-title":"Proceedings of the 9th international conference on learning representations","author":"M. Patrick","year":"2021","unstructured":"Patrick, M., Huang, P.-Y., Asano, Y. M., Metze, F., Hauptmann, A. G., Henriques, J. F., & Vedaldi, A. (2021). Support-set bottlenecks for video-text representation learning. In Proceedings of the 9th international conference on learning representations. Retrieved May 3, 2024, from https:\/\/openreview.net\/forum?id=EqoXe2zmhrh."},{"key":"73_CR27","first-page":"450","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"M. Wray","year":"2019","unstructured":"Wray, M., Larlus, D., Csurka, G., & Damen, D. (2019). Fine-grained action retrieval through multiple parts-of-speech embeddings. In Proceedings of the IEEE international conference on computer vision (pp. 450\u2013459). Piscataway: IEEE."},{"key":"73_CR28","volume-title":"Introduction to information retrieval","author":"H. Sch\u00fctze","year":"2008","unstructured":"Sch\u00fctze, H., Manning, C. D., & Raghavan, P. (2008). Introduction to information retrieval. Cambridge: Cambridge University Press."},{"key":"73_CR29","volume-title":"Information retrieval: implementing and evaluating search engines","author":"S. B\u00fcttcher","year":"2016","unstructured":"B\u00fcttcher, S., Clarke, C. L. A., & Cormack, G. V. (2016). Information retrieval: implementing and evaluating search engines. Cambridge: MIT Press."},{"issue":"2","key":"73_CR30","doi-asserted-by":"publisher","DOI":"10.1145\/1132956.1132959","volume":"38","author":"J. Zobel","year":"2006","unstructured":"Zobel, J., & Moffat, A. (2006). Inverted files for text search engines. ACM Computing Surveys, 38(2), 6.","journal-title":"ACM Computing Surveys"},{"issue":"6","key":"73_CR31","doi-asserted-by":"publisher","first-page":"5132","DOI":"10.1109\/TCSVT.2023.3339489","volume":"34","author":"M. Cao","year":"2023","unstructured":"Cao, M., Bai, Y., Cao, Z., Nie, L., & Zhang, M. (2023). Efficient image-text retrieval via keyword-guided pre-screening. IEEE Transactions on Circuits and Systems for Video Technology, 34(6), 5132\u20135145.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"73_CR32","doi-asserted-by":"publisher","first-page":"6079","DOI":"10.1109\/TMM.2022.3204444","volume":"25","author":"X. Wang","year":"2022","unstructured":"Wang, X., Zhu, L., Zheng, Z., Xu, M., & Yang, Y. (2022). Align and tell: boosting text-video retrieval with local alignment and fine-grained supervision. IEEE Transactions on Multimedia, 25, 6079\u20136089.","journal-title":"IEEE Transactions on Multimedia"},{"issue":"16","key":"73_CR33","doi-asserted-by":"publisher","first-page":"24387","DOI":"10.1007\/s11042-023-14589-6","volume":"82","author":"X. Wu","year":"2023","unstructured":"Wu, X., Qian, J., & Wang, T. (2023). Text-video retrieval method based on enhanced self-attention and multi-task learning. Multimedia Tools and Applications, 82(16), 24387\u201324406.","journal-title":"Multimedia Tools and Applications"},{"key":"73_CR34","first-page":"3010","volume-title":"Proceedings of the IEEE international conference on acoustics, speech and signal processing","author":"M. Ge","year":"2024","unstructured":"Ge, M., Li, Y., Wu, H., & Li, M. (2024). JM-CLIP: a joint modal similarity contrastive learning model for video-text retrieval. In Proceedings of the IEEE international conference on acoustics, speech and signal processing (pp. 3010\u20133014). Piscataway: IEEE."},{"key":"73_CR35","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., et al. (2022). CLIP4Clip: an empirical study of CLIP for end-to-end video clip retrieval and captioning. Neurocomputing, 508, 293\u2013304.","journal-title":"Neurocomputing"},{"key":"73_CR36","first-page":"5006","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"S. K. Gorti","year":"2022","unstructured":"Gorti, S. K., Vouitsis, N., Ma, J., Golestan, K., Volkovs, M., Garg, A., et al. (2022). X-pool: cross-modal language-video attention for text-video retrieval. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5006\u20135015). Piscataway: IEEE."},{"key":"73_CR37","first-page":"19948","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"K. Li","year":"2023","unstructured":"Li, K., Wang, Y., Li, Y., Wang, Y., He, Y., Wang, L., et al. (2023). Unmasked teacher: towards training-efficient video foundation models. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 19948\u201319960). Piscataway: IEEE."},{"key":"73_CR38","first-page":"141","volume-title":"Proceedings of the 21st international conference on computational linguistics and 44th annual meeting of the Association for Computational Linguistics","author":"S. Bird","year":"2006","unstructured":"Bird, S. (2006). NLTK: the natural language toolkit. In N. Calzolari, C. Cardie, & P. Isabelle (Eds.), Proceedings of the 21st international conference on computational linguistics and 44th annual meeting of the Association for Computational Linguistics (pp. 141\u2013148). Stroudsburg: ACL."},{"key":"73_CR39","unstructured":"Bai, J., Bai, S., Chu, Y., Cui, Z., Dang, K., Deng, X., et\u00a0al. (2023). Qwen technical report. arXiv preprint. arXiv:2309.16609."},{"key":"73_CR40","volume-title":"Proceedings of the 9th international conference on learning representations","author":"A. Dosovitskiy","year":"2020","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., et al. (2020). An image is worth 16x16 words: transformers for image recognition at scale. In Proceedings of the 9th international conference on learning representations. Retrieved May 3, 2024, fromhttps:\/\/openreview.net\/forum?id=YicbFdNTTy."},{"key":"73_CR41","first-page":"82","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"T. Ridnik","year":"2021","unstructured":"Ridnik, T., Ben-Baruch, E., Zamir, N., Noy, A., Friedman, I., Protter, M., et al. (2021). Asymmetric loss for multi-label classification. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 82\u201391). Piscataway: IEEE."},{"key":"73_CR42","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/3122865.3122867","volume-title":"Frontiers of multimedia research","author":"Z. Wu","year":"2017","unstructured":"Wu, Z., Yao, T., Fu, Y., & Jiang, Y.-G. (2017). Deep learning for video classification and captioning. In Frontiers of multimedia research (pp. 3\u201329). New York: ACM."},{"key":"73_CR43","first-page":"4581","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"X. Wang","year":"2019","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.-F., & Wang, W. Y. (2019). Vatex: a large-scale, high-quality multilingual dataset for video-and-language research. In Proceedings of the IEEE international conference on computer vision (pp. 4581\u20134591). Piscataway: IEEE."},{"key":"73_CR44","first-page":"3202","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"A. Rohrbach","year":"2015","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., & Schiele, B. (2015). A dataset for movie description. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3202\u20133212). Piscataway: IEEE."},{"key":"73_CR45","first-page":"10704","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"W. Wu","year":"2023","unstructured":"Wu, W., Luo, H., Fang, B., Wang, J., & Ouyang, W. (2023). Cap4video: what can auxiliary captions do for text-video retrieval?. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10704\u201310713). Piscataway: IEEE."},{"key":"73_CR46","volume-title":"Proceedings of the 3rd international conference on learning representations","author":"D. P. Kingma","year":"2015","unstructured":"Kingma, D. P., & Ba, J. (2015). Adam: a method for stochastic optimization. In Y. Bengio & Y. LeCun (Eds.), Proceedings of the 3rd international conference on learning representations. Retrieved May 7, 2014, from http:\/\/arxiv.org\/abs\/1412.6980."},{"key":"73_CR47","first-page":"464","volume-title":"Proceedings of the IEEE winter conference on applications of computer vision","author":"L. N. Smith","year":"2017","unstructured":"Smith, L. N. (2017). Cyclical learning rates for training neural networks. In Proceedings of the IEEE winter conference on applications of computer vision (pp. 464\u2013472). Piscataway: IEEE."},{"key":"73_CR48","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1145\/3503161.3547910","volume-title":"Proceedings of the 30th ACM international conference on multimedia","author":"Y. Ma","year":"2022","unstructured":"Ma, Y., Xu, G., Sun, X., Yan, M., Zhang, J., & Ji, R. (2022). X-clip: end-to-end multi-grained contrastive learning for video-text retrieval. In J. Magalh\u00e3es, A. Del Bimbo, S. Satoh, et al. (Eds.), Proceedings of the 30th ACM international conference on multimedia (pp. 638\u2013647). New York: ACM."},{"key":"73_CR49","first-page":"2980","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"T.-Y. Lin","year":"2017","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision (pp. 2980\u20132988). Piscataway: IEEE."},{"key":"73_CR50","first-page":"6077","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"P. Anderson","year":"2018","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., et al. (2018). Bottom-up and top-down attention for image captioning and visual question answering. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6077\u20136086). Piscataway: IEEE."},{"key":"73_CR51","first-page":"5696","volume-title":"Proceedings of the 36th international conference on neural information processing systems","author":"J. Wang","year":"2022","unstructured":"Wang, J., Chen, D., Wu, Z., Luo, C., Zhou, L., Zhao, Y., et al. (2022). OmniVL: one foundation model for image-language and video-language tasks. In S. Koyejo, S. Mohamed, A. Agarwal, et al. (Eds.), Proceedings of the 36th international conference on neural information processing systems (pp. 5696\u20135710). Red Hook: Curran Associates."},{"key":"73_CR52","first-page":"14386","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"P. Papalampidi","year":"2024","unstructured":"Papalampidi, P., Koppula, S., Pathak, S., Chiu, J., Heyward, J., Patraucean, V., et al. (2024). A simple recipe for contrastively pre-training video-first encoders beyond 16 frames. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14386\u201314397). Piscataway: IEEE."}],"container-title":["Visual Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44267-025-00073-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44267-025-00073-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44267-025-00073-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T03:14:32Z","timestamp":1741230872000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44267-025-00073-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,6]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["73"],"URL":"https:\/\/doi.org\/10.1007\/s44267-025-00073-2","relation":{},"ISSN":["2097-3330","2731-9008"],"issn-type":[{"value":"2097-3330","type":"print"},{"value":"2731-9008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,6]]},"assertion":[{"value":"3 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 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 have no competing interests to declare that they are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2"}}