{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T07:48:23Z","timestamp":1747986503146,"version":"3.40.3"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031263156"},{"type":"electronic","value":"9783031263163"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26316-3_27","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:02:32Z","timestamp":1677657752000},"page":"451-468","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ConTra: (Con)text (Tra)nsformer for\u00a0Cross-Modal Video Retrieval"],"prefix":"10.1007","author":[{"given":"Adriano","family":"Fragomeni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Wray","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dima","family":"Damen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"27_CR1","unstructured":"Akbari, H., et al.: VATT: Transformers for multimodal self-supervised learning from raw video, audio and text. In: Conference on Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"27_CR2","unstructured":"Alayrac, J., et al.: Self-supervised multimodal versatile networks. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"27_CR3","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: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Beery, S., Wu, G., Rathod, V., Votel, R., Huang, J.: Context R-CNN: long term temporal context for per-camera object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01309"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Torresani, L.: Classifying, segmenting, and tracking object instances in video with mask propagation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Cartas, A., Radeva, P., Dimiccoli, M.: Modeling long-term interactions to enhance action recognition. In: International Conference on Pattern Recognition (ICPR) (2021)","DOI":"10.1109\/ICPR48806.2021.9412148"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Multimodal clustering networks for self-supervised learning from unlabeled videos. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00791"},{"key":"27_CR8","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Association for Computational Linguistics (ACL\/IJCNLP) (2011)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., Wu, Q.: Fine-grained video-text retrieval with hierarchical graph reasoning. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Chun, S., Oh, S.J., de Rezende, R.S., Kalantidis, Y., Larlus, D.: Probabilistic embeddings for cross-modal retrieval. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Croitoru, I., et al.: TeachText: crossmodal generalized distillation for text-video retrieval. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"27_CR12","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Damen","year":"2021","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. Int. J. Comput. Vision (IJCV) 130, 33\u201355 (2021)","journal-title":"Int. J. Comput. Vision (IJCV)"},{"key":"27_CR13","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (NAACL-HLT) (2019)"},{"key":"27_CR14","unstructured":"Dong, J., Li, X., Snoek, C.G.: Word2visualvec: Image and video to sentence matching by visual feature prediction. CoRR, abs\/1604.06838 (2016)"},{"key":"27_CR15","first-page":"4065","volume":"44","author":"J Dong","year":"2021","unstructured":"Dong, J., et al.: Dual encoding for video retrieval by text. Trans. Pattern Anal. Mach. Intell. (TPAMI) 44, 4065\u20134080 (2021)","journal-title":"Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"27_CR16","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"27_CR17","unstructured":"El-Nouby, A., Neverova, N., Laptev, I., J\u00e9gou, H.: Training vision transformers for image retrieval. CoRR (2021)"},{"key":"27_CR18","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: British Machine Vision Conference (BMVC) (2018)"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Furnari, A., Farinella, G.M.: What would you expect? Anticipating egocentric actions with rolling-unrolling LSTMS and modality attention. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00635"},{"key":"27_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-030-58548-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Gabeur","year":"2020","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 214\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_13"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"27_CR22","unstructured":"Ging, S., Zolfaghari, M., Pirsiavash, H., Brox, T.: COOT: cooperative hierarchical transformer for video-text representation learning. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Guo, X., Guo, X., Lu, Y.: SSAN: separable self-attention network for video representation learning. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01243"},{"key":"27_CR24","first-page":"1","volume":"13","author":"M Gutmann","year":"2012","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics. J. Mach. Learn. Res. 13, 1\u201355 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.C.: Localizing moments in video with temporal language. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2018)","DOI":"10.18653\/v1\/D18-1168"},{"key":"27_CR28","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"27_CR29","unstructured":"J\u00f3zefowicz, R., Vinyals, O., Schuster, M., Shazeer, N., Wu, Y.: Exploring the limits of language modeling. CoRR, abs\/1602.02410 (2016)"},{"key":"27_CR30","unstructured":"Kazakos, E., Huh, J., Nagrani, A., Zisserman, A., Damen, D.: With a little help from my temporal context: Multimodal egocentric action recognition. In: British Machine Vision Conference (BMVC) (2021)"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Kazakos, E., Nagrani, A., Zisserman, A., Damen, D.: Epic-fusion: audio-visual temporal binding for egocentric action recognition. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00559"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Klein, B., Lev, G., Sadeh, G., Wolf, L.: Associating neural word embeddings with deep image representations using fisher vectors. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: Clipbert for video-and-language learning via sparse sampling. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Liu, S., Fan, H., Qian, S., Chen, Y., Ding, W., Wang, Z.: Hit: hierarchical transformer with momentum contrast for video-text retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"27_CR36","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: Video retrieval using representations from collaborative experts. In: British Machine Vision Conference (BMVC) (2019)"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, Q., Albanie, S.: Adaptive cross-modal prototypes for cross-domain visual-language retrieval. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01471"},{"key":"27_CR38","unstructured":"Luo, H., et al.: UNIVILM: a unified video and language pre-training model for multimodal understanding and generation. CoRR, abs\/2002.06353 (2020)"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J., Laptev, I., Sivic, J., Zisserman, A.: Thinking fast and slow: Efficient text-to-visual retrieval with transformers. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"27_CR41","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learning a text-video embedding from incomplete and heterogeneous data. CoRR, abs\/1804.02516 (2018)"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J., Tapaswi, M., Laptev, I., Sivic, J.: How to 100 m: learning a text-video embedding by watching hundred million narrated video clips. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Li, J., Metze, F., Roy-Chowdhury, A.K.: Learning joint embedding with multimodal cues for cross-modal video-text retrieval. In: International Conference on Multimedia Retrieval (ICMR) (2018)","DOI":"10.1145\/3206025.3206064"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Oncescu, A., Henriques, J.F., Liu, Y., Zisserman, A., Albanie, S.: QUERYD: a video dataset with high-quality text and audio narrations. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2021)","DOI":"10.1109\/ICASSP39728.2021.9414640"},{"key":"27_CR45","unstructured":"Patrick, M., et al.: Multi-modal self-supervision from generalized data transformations. In: International Conference on Computer Vision (ICCV) (2021)"},{"key":"27_CR46","unstructured":"Patrick, M., et al.: Support-set bottlenecks for video-text representation learning. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"27_CR47","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"27_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-030-58517-4_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Sener","year":"2020","unstructured":"Sener, F., Singhania, D., Yao, A.: Temporal aggregate representations for long-range video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 154\u2013171. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_10"},{"key":"27_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-030-01240-3_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Shao","year":"2018","unstructured":"Shao, D., Xiong, Yu., Zhao, Y., Huang, Q., Qiao, Yu., Lin, D.: Find and focus: retrieve and localize video events with natural language queries. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 202\u2013218. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_13"},{"key":"27_CR50","doi-asserted-by":"crossref","unstructured":"Shao, J., Wen, X., Zhao, B., Xue, X.: Temporal context aggregation for video retrieval with contrastive learning. In: Winter Conference on Applications of Computer Vision (WACV) (2021)","DOI":"10.1109\/WACV48630.2021.00331"},{"key":"27_CR51","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: A joint model for video and language representation learning. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"27_CR52","doi-asserted-by":"crossref","unstructured":"Tang, Z., Lei, J., Bansal, M.: DecemBERT: learning from noisy instructional videos via dense captions and entropy minimization. In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (2021)","DOI":"10.18653\/v1\/2021.naacl-main.193"},{"key":"27_CR53","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"27_CR54","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Learning fine-grained image similarity with deep ranking. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.180"},{"key":"27_CR55","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. Trans. Pattern Anal. Mach. Intell. (TPAMI) 41, 394\u2013407 (2018)","journal-title":"Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"27_CR56","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"27_CR57","unstructured":"Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: International Conference on Machine Learning (ICML) (2020)"},{"key":"27_CR58","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, L., Yang, Y.: T2VLAD: global-local sequence alignment for text-video retrieval. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"27_CR59","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y., Wang, W.Y.: VATEX: a large-scale, high-quality multilingual dataset for video-and-language research. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"27_CR60","doi-asserted-by":"crossref","unstructured":"Wei, J., Xu, X., Yang, Y., Ji, Y., Wang, Z., Shen, H.T.: Universal weighting metric learning for cross-modal matching. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"27_CR61","doi-asserted-by":"crossref","unstructured":"Wray, M., Csurka, G., Larlus, D., Damen, D.: Fine-grained action retrieval through multiple parts-of-speech embeddings. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00054"},{"key":"27_CR62","doi-asserted-by":"crossref","unstructured":"Wu, C., Feichtenhofer, C., Fan, H., He, K., Kr\u00e4henb\u00fchl, P., Girshick, R.B.: Long-term feature banks for detailed video understanding. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"27_CR63","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"27_CR64","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: VLM: task-agnostic video-language model pre-training for video understanding. In: Association for Computational Linguistics (ACL\/IJCNLP) (2021)","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"key":"27_CR65","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: VideoCLIP: contrastive pre-training for zero-shot video-text understanding. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"27_CR66","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: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"27_CR67","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-030-01261-8_23","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhang","year":"2018","unstructured":"Zhang, B., Hu, H., Sha, F.: Cross-modal and hierarchical modeling of video and text. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 385\u2013401. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_23"},{"key":"27_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"27_CR69","doi-asserted-by":"publisher","first-page":"8265","DOI":"10.1109\/TIP.2021.3113791","volume":"30","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Han, X., Song, X., Yan, Y., Nie, L.: Multi-modal interaction graph convolutional network for temporal language localization in videos. IEEE Trans. Image Process. 30, 8265\u20138277 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR70","unstructured":"Zhou, L., Liu, J., Cheng, Y., Gan, Z., Zhang, L.: CUPID: adaptive curation of pre-training data for video-and-language representation learning. CoRR, abs\/2104.00285 (2021)"},{"key":"27_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. In: Conference on Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"27_CR72","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yang, Y.: ActBERT: learning global-local video-text representations. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00877"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26316-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:32:03Z","timestamp":1677659523000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26316-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263156","9783031263163"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26316-3_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 March 2023","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":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"277","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}