{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T21:49:24Z","timestamp":1789163364829,"version":"build-2803163510"},"publisher-location":"Singapore","reference-count":64,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609079","type":"print"},{"value":"9789819609086","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0908-6_2","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:24:07Z","timestamp":1733513047000},"page":"25-43","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Beyond Coarse-Grained Matching in\u00a0Video-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Aozhu","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hazel","family":"Doughty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xirong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"2_CR1","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et\u00a0al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Anne\u00a0Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bagad, P., Tapaswi, M., Snoek, C.G.: Test of time: Instilling video-language models with a sense of time. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00247"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: A joint video and image encoder for end-to-end retrieval. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"2_CR5","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: A clip-hitchhiker\u2019s guide to long video retrieval. arXiv preprint arXiv:2205.08508 (2022)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Buch, S., Eyzaguirre, C., Gaidon, A., Wu, J., Fei-Fei, L., Niebles, J.C.: Revisiting the\" video\" in video-language understanding. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Chan, D.M., Myers, A., Vijayanarasimhan, S., Ross, D.A., Seybold, B., Canny, J.F.: What\u2019s in a caption? dataset-specific linguistic diversity and its effect on visual description models and metrics. In: CVPR (2022)","DOI":"10.1109\/CVPRW56347.2022.00520"},{"key":"2_CR8","unstructured":"Chen, D., Dolan, W.: Collecting highly parallel data for paraphrase evaluation. In: CVPR (2011)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., Wu, Q.: Fine-grained video-text retrieval with hierarchical graph reasoning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., Wu, Q.: Fine-grained video-text retrieval with hierarchical graph reasoning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Li, L., Yu, L., El\u00a0Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., Liu, J.: Uniter: Universal image-text representation learning. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Wei, F., Bao, J., Chen, D., Zhang, W.: Cico: Domain-aware sign language retrieval via cross-lingual contrastive learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01823"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Croitoru, I., Bogolin, S.V., Leordeanu, M., Jin, H., Zisserman, A., Albanie, S., Liu, Y.: Teachtext: Crossmodal generalized distillation for text-video retrieval. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Dong, J., Li, X., Xu, C., Yang, X., Yang, G., Wang, X.: Dual encoding for video retrieval by text. TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Doughty, H., Laptev, I., Mayol-Cuevas, W., Damen, D.: Action modifiers: Learning from adverbs in instructional videos. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00095"},{"key":"2_CR16","volume-title":"How Do You Do It?","author":"H Doughty","year":"2022","unstructured":"Doughty, H., Snoek, C.G.M.: How Do You Do It? CVPR, Fine-Grained Action Understanding with Pseudo-Adverbs. In (2022)"},{"key":"2_CR17","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: BMVC (2018)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Fan, Z., Wei, Z., Li, Z., Wang, S., Fan, J.: Negative sample is negative in its own way: Tailoring negative sentences for image-text retrieval. In: NAACL (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.204"},{"key":"2_CR19","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Gou, Y., Ko, T., Yang, H., Kwok, J., Zhang, Y., Wang, M.: Leveraging per image-token consistency for vision-language pre-training. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01836"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Nematzadeh, A.: Probing image-language transformers for verb understanding. In: ACL (2021)","DOI":"10.18653\/v1\/2021.findings-acl.318"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Hu, F., Chen, A., Wang, Z., Zhou, F., Dong, J., Li, X.: Lightweight attentional feature fusion: A new baseline for text-to-video retrieval. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19781-9_26"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual prompt tuning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"2_CR24","unstructured":"Jiang, H., Zhang, J., Huang, R., Ge, C., Ni, Z., Lu, J., Zhou, J., Song, S., Huang, G.: Cross-modal adapter for text-video retrieval. arXiv preprint arXiv:2211.09623 (2022)"},{"key":"2_CR25","unstructured":"Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. In: NeurIPS (2020)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos\u00a0Niebles, J.: Dense-captioning events in videos. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Lei, J., Li, L., Zhou, L., Gan, Z., Berg, T.L., Bansal, M., Liu, J.: Less is more: Clipbert for video-and-language learning via sparse sampling. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Li, X., Xu, C., Yang, G., Chen, Z., Dong, J.: W2VV++: Fully deep learning for ad-hoc video search. In: ACMMM (2019)","DOI":"10.1145\/3343031.3350906"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., Song, Y., Cao, L., Tetreault, J.R., Goldberg, L., Jaimes, A., Luo, J.: TGIF: A new dataset and benchmark on animated gif description. In: CVPR (2015)","DOI":"10.1109\/CVPR.2016.502"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xiong, P., Xu, L., Cao, S., Jin, Q.: Ts2-net: Token shift and selection transformer for text-video retrieval. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"2_CR32","unstructured":"Lu, H., Huo, Y., Yang, G., Lu, Z., Zhan, W., Tomizuka, M., Ding, M.: Uniadapter: Unified parameter-efficient transfer learning for cross-modal modeling. In: ICLR (2024)"},{"key":"2_CR33","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 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Ma, Y., Xu, G., Sun, X., Yan, M., Zhang, J., Ji, R.: X-clip: End-to-end multi-grained contrastive learning for video-text retrieval. In: ACMMM (2022)","DOI":"10.1145\/3503161.3547910"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Madasu, A., Lal, V.: ICSVR: Investigating compositional and syntactic understanding in video retrieval models. In: CVPR (2024)","DOI":"10.1109\/CVPRW63382.2024.00180"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Messina, N., Amato, G., Esuli, A., Falchi, F., Gennaro, C., Marchand-Maillet, S.: Fine-grained visual textual alignment for cross-modal retrieval using transformer encoders. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 17(4), 1\u201323 (2021)","DOI":"10.1145\/3451390"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Momeni, L., Caron, M., Nagrani, A., Zisserman, A., Schmid, C.: Verbs in action: Improving verb understanding in video-language models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"2_CR38","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. In: ICML (2021)"},{"key":"2_CR39","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"2_CR40","unstructured":"Robinson, J., Chuang, C.Y., Sra, S., Jegelka, S.: Contrastive learning with hard negative samples. In: ICLR (2020)"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Shekhar, R., Pezzelle, S., Klimovich, Y., Herbelot, A., Nabi, M., Sangineto, E., Bernardi, R.: Foil it! find one mismatch between image and language caption. In: ACL (2017)","DOI":"10.18653\/v1\/P17-1024"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Shu, F., Chen, B., Liao, Y., Wang, J., Liu, S.: Mac: Masked contrastive pre-training for efficient video-text retrieval. IEEE Transactions on Multimedia (2024)","DOI":"10.1109\/TMM.2024.3402613"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Tian, K., Zhao, R., Xin, Z., Lan, B., Li, X.: Holistic features are almost sufficient for text-to-video retrieval. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01622"},{"key":"2_CR45","unstructured":"Torabi, A., Tandon, N., Sigal, L.: Learning language-visual embedding for movie understanding with natural-language. arXiv preprint arXiv:1609.08124 (2016)"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Changpinyo, S., Pont-Tuset, J., Soricut, R., Ferrari, V.: Connecting Vision and Language with Video Localized Narratives. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00243"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, L., Yang, Y.: T2vlad: global-local sequence alignment for text-video retrieval. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.F., Wang, W.Y.: VATEX: A large-scale, high-quality multilingual dataset for video-and-language research. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shi, P.: Video-text retrieval by supervised multi-space multi-grained alignment. CoRR (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.46"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Z., Sung, Y.L., Cheng, F., Bertasius, G., Bansal, M.: Unified coarse-to-fine alignment for video-text retrieval. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, A., Hu, F., Li, X.: Learn to understand negation in video retrieval. In: ACM MM (2022)","DOI":"10.1145\/3503161.3547968"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Wray, M., Doughty, H., Damen, D.: On semantic similarity in video retrieval. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00365"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Wray, M., Larlus, D., Csurka, G., Damen, D.: Fine-grained action retrieval through multiple parts-of-speech embeddings. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00054"},{"key":"2_CR54","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: A large video description dataset for bridging video and language. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Yang, J., Bisk, Y., Gao, J.: Taco: Token-aware cascade contrastive learning for video-text alignment. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"2_CR56","unstructured":"Yao, L., Huang, R., Hou, L., Lu, G., Niu, M., Xu, H., Liang, X., Li, Z., Jiang, X., Xu, C.: Filip: Fine-grained interactive language-image pre-training. In: ICLR (2022)"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"2_CR58","unstructured":"Yu, Y., Ko, H., Choi, J., Kim, G.: Video captioning and retrieval models with semantic attention. arXiv preprint arXiv:1610.02947 (2016)"},{"key":"2_CR59","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? In: ICLR (2023)"},{"key":"2_CR60","doi-asserted-by":"crossref","unstructured":"Zellers, R., Lu, J., Lu, X., Yu, Y., Zhao, Y., Salehi, M., Kusupati, A., Hessel, J., Farhadi, A., Choi, Y.: Merlot reserve: Neural script knowledge through vision and language and sound. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"2_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, B., Zhang, P., Dong, X., Zang, Y., Wang, J.: Long-clip: Unlocking the long-text capability of clip. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"2_CR62","doi-asserted-by":"crossref","unstructured":"Zhao, T., Zhang, T., Zhu, M., Shen, H., Lee, K., Lu, X., Yin, J.: Vl-checklist: Evaluating pre-trained vision-language models with objects, attributes and relations. arXiv preprint arXiv:2207.00221 (2022)","DOI":"10.18653\/v1\/2022.emnlp-demos.4"},{"key":"2_CR63","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Procnets: Learning to segment procedures in untrimmed and unconstrained videos. In: AAAI (2018)"},{"key":"2_CR64","unstructured":"Zou, X., Wu, C., Cheng, L., Wang, Z.: Tokenflow: Rethinking fine-grained cross-modal alignment in vision-language retrieval. arXiv preprint arXiv:2209.13822 (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0908-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:09:08Z","timestamp":1733515748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0908-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609079","9789819609086"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0908-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}