{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:13:36Z","timestamp":1778080416096,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":66,"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_22","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:26:21Z","timestamp":1733513181000},"page":"384-402","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Every Shot Counts: Using Exemplars for\u00a0Repetition Counting in\u00a0Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5207-1551","authenticated-orcid":false,"given":"Saptarshi","family":"Sinha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4706-4231","authenticated-orcid":false,"given":"Alexandros","family":"Stergiou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8804-6238","authenticated-orcid":false,"given":"Dima","family":"Damen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"22_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: Advances in Neural Information Processing Systems (NeurIPS). pp. 23716\u201323736 (2022)"},{"issue":"1","key":"22_CR2","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.patcog.2007.03.013","volume":"41","author":"AB Albu","year":"2008","unstructured":"Albu, A.B., Bergevin, R., Quirion, S.: Generic Temporal Segmentation of Cyclic Human Motion. Pattern Recogn. 41(1), 6\u201321 (2008)","journal-title":"Pattern Recogn."},{"key":"22_CR3","unstructured":"Amini-Naieni, N., Amini-Naieni, K., Han, T., Zisserman, A.: Open-world Text-specified Object Counting. In: British Machine Vision Conference (BMVC). p.\u00a0510 (2023)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Arteta, C., Lempitsky, V., Zisserman, A.: Counting in the Wild. In: European Conference on Computer Vision (ECCV). pp. 483\u2013498 (2016)","DOI":"10.1007\/978-3-319-46478-7_30"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Azy, O., Ahuja, N.: Segmentation of Periodically Moving Objects. In: International Conference on Pattern Recognition (ICPR). pp.\u00a01\u20134 (2008)","DOI":"10.1109\/ICPR.2008.4760949"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Bacharidis, K., Argyros, A.: Repetition-aware Image Sequence Sampling for Recognizing Repetitive Human Actions. In: International Conference on Computer Vision Workshops (ICCVw). pp. 1878\u20131887 (2023)","DOI":"10.1109\/ICCVW60793.2023.00202"},{"issue":"7","key":"22_CR7","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.1109\/TPAMI.2007.1042","volume":"29","author":"A Briassouli","year":"2007","unstructured":"Briassouli, A., Ahuja, N.: Extraction and Analysis of Multiple Periodic Motions in Video Sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 29(7), 1244\u20131261 (2007)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the Faster R-CNN Architecture for Temporal Action Localization. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1130\u20131139 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Chattopadhyay, P., Vedantam, R., Selvaraju, R.R., Batra, D., Parikh, D.: Counting Everyday Objects in Everyday Scenes. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1135\u20131144 (2017)","DOI":"10.1109\/CVPR.2017.471"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Cholakkal, H., Sun, G., Khan, F.S., Shao, L.: Object Counting and Instance Segmentation with Image-level Supervision. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 12397\u201312405 (2019)","DOI":"10.1109\/CVPR.2019.01268"},{"issue":"8","key":"22_CR12","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1109\/34.868681","volume":"22","author":"R Cutler","year":"2000","unstructured":"Cutler, R., Davis, L.S.: Robust Real-Time Periodic Motion Detection, Analysis, and Applications. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 22(8), 781\u2013796 (2000)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Destro, M., Gygli, M.: CycleCL: Self-supervised Learning for Periodic Videos. In: Winter Conference on Applications of Computer Vision (WACV). pp. 2861\u20132870 (2024)","DOI":"10.1109\/WACV57701.2024.00284"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., Zisserman, A.: Counting Out Time: Class Agnostic Video Repetition Counting in the Wild. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 10387\u201310396 (2020)","DOI":"10.1109\/CVPR42600.2020.01040"},{"key":"22_CR15","unstructured":"Feichtenhofer, C., Li, Y., He, K., et\u00a0al.: Masked Autoencoders as Spatiotemporal Learners. In: Advances in Neural Information Processing Systems (NeurIPS). pp. 35946\u201335958 (2022)"},{"issue":"11","key":"22_CR16","doi-asserted-by":"publisher","first-page":"2782","DOI":"10.1109\/TPAMI.2013.65","volume":"35","author":"A Gaidon","year":"2013","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Temporal Localization of Actions with Actoms. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 35(11), 2782\u20132795 (2013)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Hsieh, M.R., Lin, Y.L., Hsu, W.H.: Drone-based Object Counting by Spatially Regularized Regional Proposal Network. In: International Conference on Computer Vision (ICCV). pp. 4145\u20134153 (2017)","DOI":"10.1109\/ICCV.2017.446"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Hu, H., Dong, S., Zhao, Y., Lian, D., Li, Z., Gao, S.: TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 19013\u201319022 (2022)","DOI":"10.1109\/CVPR52688.2022.01843"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Huang, J., Li, Y., Feng, J., Wu, X., Sun, X., Ji, R.: Clover: Towards A Unified Video-Language Alignment and Fusion Model. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 14856\u201314866 (2023)","DOI":"10.1109\/CVPR52729.2023.01427"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Jain, M., Ghodrati, A., Snoek, C.G.: ActionBytes: Learning From Trimmed Videos to Localize Actions. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1171\u20131180 (2020)","DOI":"10.1109\/CVPR42600.2020.00125"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, R., Liu, L., Chen, C.: CLIP-Count: Towards Text-Guided Zero-Shot Object Counting. In: ACM International Conference on Multimedia (MM). pp. 4535\u20134545 (2023)","DOI":"10.1145\/3581783.3611789"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Laptev, I., Belongie, S.J., P\u00e9rez, P., Wills, J.: Periodic Motion Detection and Segmentation via Approximate Sequence Alignment. In: International Conference on Computer Vision (ICCV). pp. 816\u2013823 (2005)","DOI":"10.1109\/ICCV.2005.188"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Laradji, I.H., Rostamzadeh, N., Pinheiro, P.O., Vazquez, D., Schmidt, M.: Where are the Blobs: Counting by Localization with Point Supervision. In: European Conference on Computer Vision (ECCV). pp. 547\u2013562 (2018)","DOI":"10.1007\/978-3-030-01216-8_34"},{"key":"22_CR24","unstructured":"Lempitsky, V., Zisserman, A.: Learning to Count Objects in Images. In: Advances in Neural Information Processing Systems (NeurIPS) (2010)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Levy, O., Wolf, L.: Live Repetition Counting. In: International Conference on Computer Vision (ICCV). pp. 3020\u20133028 (2015)","DOI":"10.1109\/ICCV.2015.346"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Li, M., Zhang, Z., Huang, K., Tan, T.: Estimating the Number of People in Crowded Scenes by MID Based Foreground Segmentation and Head-shoulder Detection. In: International Conference on Pattern Recognition (ICPR). pp.\u00a01\u20134 (2008)","DOI":"10.1109\/ICPR.2008.4761705"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Li, X., Xu, H.: Repetitive Action Counting With Motion Feature Learning. In: Winter Conference on Applications of Computer Vision (WACV). pp. 6499\u20136508 (2024)","DOI":"10.1109\/WACV57701.2024.00637"},{"key":"22_CR28","unstructured":"Li, Z., Ma, X., Shang, Q., Zhu, W., Ci, H., Qiao, Y., Wang, Y.: Efficient action counting with dynamic queries. arXiv preprint arXiv:2403.01543 (2024)"},{"key":"22_CR29","unstructured":"Lin, H., Hong, X., Wang, Y.: Object Counting: You Only Need to Look at One. arXiv preprint arXiv:2112.05993 (2021)"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Lin, K.Q., Zhang, P., Chen, J., Pramanick, S., Gao, D., Wang, A.J., Yan, R., Shou, M.Z.: UniVTG: Towards Unified Video-Language Temporal Grounding. In: International Conference on Computer Vision (ICCV). pp. 2794\u20132804 (2023)","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: Boundary Sensitive Network for Temporal Action Proposal Generation. In: European conference on computer vision (ECCV). pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"22_CR32","unstructured":"Liu, C., Zhong, Y., Zisserman, A., Xie, W.: Countr: Transformer-based generalised visual counting. In: British Machine Vision Conference (BMVC). p.\u00a0370 (2022)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Liu, C., Weng, X., Mu, Y.: Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1217\u20131226 (2019)","DOI":"10.1109\/CVPR.2019.00131"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video Swin Transformer. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Gaussian Temporal Awareness Networks for Action Localization. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 344\u2013353 (2019)","DOI":"10.1109\/CVPR.2019.00043"},{"issue":"2","key":"22_CR36","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1109\/TPAMI.2004.1262196","volume":"26","author":"C Lu","year":"2004","unstructured":"Lu, C., Ferrier, N.J.: Repetitive Motion Analysis: Segmentation and Event Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 26(2), 258\u2013263 (2004)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Lu, E., Xie, W., Zisserman, A.: Class-agnostic Counting. In: Asian Conference on Computer Vision (ACCV). pp. 669\u2013684 (2019)","DOI":"10.1007\/978-3-030-20893-6_42"},{"key":"22_CR38","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Pirsiavash, H., Favaro, P.: Representation Learning by Learning to Count. In: International Conference on Computer Vision (ICCV). pp. 5898\u20135906 (2017)","DOI":"10.1109\/ICCV.2017.628"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"O\u00f1oro-Rubio, D., L\u00f3pez-Sastre, R.J.: Towards perspective-free object counting with deep learning. In: European Conference on Computer Vision (ECCV). pp. 615\u2013629 (2016)","DOI":"10.1007\/978-3-319-46478-7_38"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Panagiotakis, C., Karvounas, G., Argyros, A.: Unsupervised Detection of Periodic Segments in Videos. In: International Conference on Image Processing (ICIP). pp. 923\u2013927 (2018)","DOI":"10.1109\/ICIP.2018.8451336"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Pogalin, E., Smeulders, A.W., Thean, A.H.: Visual Quasi-Periodicity. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp.\u00a01\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587509"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Pramanick, S., Song, Y., Nag, S., Lin, K.Q., Shah, H., Shou, M.Z., Chellappa, R., Zhang, P.: EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone. In: International Conference on Computer Vision (ICCV). pp. 5285\u20135297 (2023)","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Ramakrishnan, S.K., Al-Halah, Z., Grauman, K.: NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory Supplementary Materials. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 6694\u20136703 (2023)","DOI":"10.1109\/CVPR52729.2023.00647"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Runia, T.F., Snoek, C.G., Smeulders, A.W.: Real-World Repetition Estimation by Div, Grad and Curl. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 9009\u20139017 (2018)","DOI":"10.1109\/CVPR.2018.00939"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Segu\u00ed, S., Pujol, O., Vitria, J.: Learning to Count with Deep Object Features. In: Conference on Computer Vision and Pattern Recognition Workshops (CVPRw). pp. 90\u201396 (2015)","DOI":"10.1109\/CVPRW.2015.7301276"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Shi, M., Lu, H., Feng, C., Liu, C., Cao, Z.: Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 9529\u20139538 (2022)","DOI":"10.1109\/CVPR52688.2022.00931"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1049\u20131058 (2016)","DOI":"10.1109\/CVPR.2016.119"},{"issue":"1720","key":"22_CR49","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.1098\/rspb.2010.2602","volume":"278","author":"V Slaughter","year":"2011","unstructured":"Slaughter, V., Itakura, S., Kutsuki, A., Siegal, M.: Learning to Count Begins in Infancy: Evidence from 18 Month Olds\u2019 Visual Preferences. Proceedings of the Royal Society B: Biological Sciences 278(1720), 2979\u20132984 (2011)","journal-title":"Proceedings of the Royal Society B: Biological Sciences"},{"key":"22_CR50","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"22_CR51","doi-asserted-by":"crossref","unstructured":"Thangali, A., Sclaroff, S.: Periodic motion detection and estimation via space-time sampling. In: Workshop on Applications of Computer Vision (WACV). pp. 176\u2013182 (2005)","DOI":"10.1109\/ACVMOT.2005.91"},{"issue":"6","key":"22_CR52","doi-asserted-by":"publisher","DOI":"10.1111\/desc.12805","volume":"22","author":"J Wang","year":"2019","unstructured":"Wang, J., Feigenson, L.: Infants Recognize Counting as Numerically Relevant. Dev. Sci. 22(6), e12805 (2019)","journal-title":"Dev. Sci."},{"issue":"2","key":"22_CR53","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1111\/infa.12512","volume":"28","author":"J Wang","year":"2023","unstructured":"Wang, J., Feigenson, L.: What Aspects of Counting Help Infants Attend to Numerosity? Infancy 28(2), 218\u2013239 (2023)","journal-title":"Infancy"},{"key":"22_CR54","doi-asserted-by":"crossref","unstructured":"Wang, L., Yung, N.H.: Crowd Counting and Segmentation in Visual Surveillance. In: International Conference on Image Processing (ICIP). pp. 2573\u20132576 (2009)","DOI":"10.1109\/ICIP.2009.5413919"},{"key":"22_CR55","unstructured":"Wang, Y., Li, K., Li, Y., He, Y., Huang, B., Zhao, Z., Zhang, H., Xu, J., Liu, Y., Wang, Z., et\u00a0al.: InternVideo: General Video Foundation Models via Generative and Discriminative Learning. arXiv preprint arXiv:2212.03191 (2022)"},{"key":"22_CR56","doi-asserted-by":"crossref","unstructured":"Weinland, D., Boyer, E.: Action Recognition using Exemplar-based Embedding. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp.\u00a01\u20137 (2008)","DOI":"10.1109\/CVPR.2008.4587731"},{"key":"22_CR57","unstructured":"Willems, G., Becker, J.H., Tuytelaars, T., Van\u00a0Gool, L.: Exemplar-based Action Recognition in Video. In: British Machine Vision Conference (BMVC). pp.\u00a03\u20137 (2009)"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Wu, G., Lin, J., Silva, C.T.: IntentVizor: Towards Generic Query Guided Interactive Video Summarization. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 10503\u201310512 (2022)","DOI":"10.1109\/CVPR52688.2022.01025"},{"key":"22_CR59","doi-asserted-by":"crossref","unstructured":"Xiong, H., Lu, H., Liu, C., Liu, L., Cao, Z., Shen, C.: From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer. In: International Conference on Computer Vision (ICCV). pp. 8362\u20138371 (2019)","DOI":"10.1109\/ICCV.2019.00845"},{"key":"22_CR60","doi-asserted-by":"crossref","unstructured":"Xu, J., Le, H., Nguyen, V., Ranjan, V., Samaras, D.: Zero-Shot Object Counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 15548\u201315557 (2023)","DOI":"10.1109\/CVPR52729.2023.01492"},{"key":"22_CR61","unstructured":"Yao, Z., Cheng, X., Zou, Y.: PoseRAC: Pose Saliency Transformer for Repetitive Action Counting. arXiv preprint arXiv:2303.08450 (2023)"},{"key":"22_CR62","doi-asserted-by":"crossref","unstructured":"Ye, Q., Xu, G., Yan, M., Xu, H., Qian, Q., Zhang, J., Huang, F.: HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training Supplementary Material. In: International Conference on Computer Vision (ICCV). pp. 15405\u201315416 (2023)","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"22_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, X., Han, G., He, S.: Context-Aware and Scale-Insensitive Temporal Repetition Counting. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 670\u2013678 (2020)","DOI":"10.1109\/CVPR42600.2020.00075"},{"key":"22_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-Image Crowd Counting via Multi-Column Convolutional Neural Network. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 589\u2013597 (2016)","DOI":"10.1109\/CVPR.2016.70"},{"key":"22_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Shao, L., Snoek, C.G.: Repetitive Activity Counting by Sight and Sound. In: Conference on Computer Vision and Pattern Recognition (CVPR). pp. 14070\u201314079 (2021)","DOI":"10.1109\/CVPR46437.2021.01385"},{"key":"22_CR66","unstructured":"Zhao, Z., Huang, X., Zhou, H., Yao, K., Ding, E., Wang, J., Wang, X., Liu, W., Feng, B.: Skim then focus: Integrating contextual and fine-grained views for repetitive action counting. arXiv preprint arXiv:2406.08814 (2024)"}],"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_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:15:45Z","timestamp":1733516145000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0908-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609079","9789819609086"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0908-6_22","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"}}]}}