{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:52:04Z","timestamp":1743033124947,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031250712"},{"type":"electronic","value":"9783031250729"}],"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\/978-3-031-25072-9_49","type":"book-chapter","created":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T08:40:04Z","timestamp":1676623204000},"page":"738-754","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Video in\u00a010 Bits: Few-Bit VideoQA for\u00a0Efficiency and\u00a0Privacy"],"prefix":"10.1007","author":[{"given":"Shiyuan","family":"Huang","sequence":"first","affiliation":[]},{"given":"Robinson","family":"Piramuthu","sequence":"additional","affiliation":[]},{"given":"Shih-Fu","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Gunnar A.","family":"Sigurdsson","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,18]]},"reference":[{"key":"49_CR1","doi-asserted-by":"crossref","unstructured":"Abadi, M., et al.: Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (2016)","DOI":"10.1145\/2976749.2978318"},{"key":"49_CR2","unstructured":"Cambridge, A.L.: The orl database. https:\/\/www.cl.cam.ac.uk\/research\/dtg\/ attarchive\/facedatabase.html"},{"key":"49_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"49_CR4","doi-asserted-by":"crossref","unstructured":"Chadha, A., Andreopoulos, Y.: Deep perceptual preprocessing for video coding. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01461"},{"key":"49_CR5","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv (2015)"},{"key":"49_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-030-58565-5_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Choi","year":"2020","unstructured":"Choi, J., Han, B.: Task-aware quantization network for JPEG image compression. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 309\u2013324. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_19"},{"key":"49_CR7","doi-asserted-by":"crossref","unstructured":"Djelouah, A., Campos, J., Schaub-Meyer, S., Schroers, C.: Neural inter-frame compression for video coding. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00652"},{"key":"49_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"49_CR9","doi-asserted-by":"crossref","unstructured":"Feng, R., Wu, Y., Guo, Z., Zhang, Z., Chen, Z.: Learned video compression with feature-level residuals. In: CVPR Workshops (2020)","DOI":"10.1109\/CVPRW50498.2020.00068"},{"key":"49_CR10","doi-asserted-by":"crossref","unstructured":"Fredrikson, M., Jha, S., Ristenpart, T.: Model inversion attacks that exploit confidence information and basic countermeasures. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security (2015)","DOI":"10.1145\/2810103.2813677"},{"key":"49_CR11","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR, July 2017","DOI":"10.1109\/CVPR.2017.670"},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"He, T., Sun, S., Guo, Z., Chen, Z.: Beyond coding: detection-driven image compression with semantically structured bit-stream. In: PCS (2019)","DOI":"10.1109\/PCS48520.2019.8954525"},{"key":"49_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-3-030-58536-5_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Hu","year":"2020","unstructured":"Hu, Z., Chen, Z., Xu, D., Lu, G., Ouyang, W., Gu, S.: Improving deep video compression by\u00a0resolution-adaptive flow coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 193\u2013209. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_12"},{"key":"49_CR14","doi-asserted-by":"crossref","unstructured":"Hu, Z., Lu, G., Xu, D.: FVC: a new framework towards deep video compression in feature space. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"49_CR15","doi-asserted-by":"crossref","unstructured":"Huang, D., Chen, P., Zeng, R., Du, Q., Tan, M., Gan, C.: Location-aware graph convolutional networks for video question answering. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"49_CR16","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"49_CR17","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: TGIF-QA: toward spatio-temporal reasoning in visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"49_CR18","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV 123, 32\u201373 (2017)","journal-title":"IJCV"},{"key":"49_CR19","doi-asserted-by":"crossref","unstructured":"Le, T.M., Le, V., Venkatesh, S., Tran, T.: Hierarchical conditional relation networks for video question answering. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"49_CR20","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: ClipBERT for video-and-language learning via sparse sampling. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"49_CR21","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. arXiv preprint arXiv:1809.01696 (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"49_CR22","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, Y.C., Cheng, Y., Gan, Z., Yu, L., Liu, J.: Hero: Hierarchical encoder for video+language omni-representation pre-training. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"49_CR23","doi-asserted-by":"crossref","unstructured":"Li, L., Pal, B., Ali, J., Sullivan, N., Chatterjee, R., Ristenpart, T.: Protocols for checking compromised credentials. In: Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security (2019)","DOI":"10.1145\/3319535.3354229"},{"key":"49_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., Liu, D., Li, H., Wu, F.: M-LVC: multiple frames prediction for learned video compression. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"49_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: ECCV (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"49_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"49_CR27","doi-asserted-by":"crossref","unstructured":"Lu, G., Ouyang, W., Xu, D., Zhang, X., Cai, C., Gao, Z.: DVC: an end-to-end deep video compression framework. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01126"},{"key":"49_CR28","doi-asserted-by":"crossref","unstructured":"Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"49_CR29","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"49_CR30","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"49_CR31","unstructured":"Minderer, M., Sun, C., Villegas, R., Cole, F., Murphy, K., Lee, H.: Unsupervised learning of object structure and dynamics from videos. arXiv preprint arXiv:1906.07889 (2019)"},{"issue":"3","key":"49_CR32","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"49_CR33","unstructured":"Samarati, P., Sweeney, L.: Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression (1998)"},{"key":"49_CR34","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.74"},{"issue":"12","key":"49_CR35","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","volume":"22","author":"GJ Sullivan","year":"2012","unstructured":"Sullivan, G.J., Ohm, J.R., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circ. Syst. Video Technol. 22(12), 1649\u20131668 (2012)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"49_CR36","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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"49_CR37","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"49_CR38","unstructured":"Toderici, G., et al.: Variable rate image compression with recurrent neural networks. arXiv preprint arXiv:1511.06085 (2015)"},{"key":"49_CR39","doi-asserted-by":"crossref","unstructured":"Toderici, G., et al.: Full resolution image compression with recurrent neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.577"},{"key":"49_CR40","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"49_CR41","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/30.125072","volume":"38","author":"GK Wallace","year":"1992","unstructured":"Wallace, G.K.: The JPEG still picture compression standard. IEEE Trans. Consum. Electron. 38, 18\u201334 (1992)","journal-title":"IEEE Trans. Consum. Electron."},{"key":"49_CR42","doi-asserted-by":"crossref","unstructured":"Wiegand, T., Sullivan, G.J., Bjontegaard, G., Luthra, A.: Overview of the H.264\/AVC video coding standard. IEEE Trans. Circ. Syst. Video Technol. 13, 560\u2013576 (2003)","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"49_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/978-3-030-01237-3_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C-Y Wu","year":"2018","unstructured":"Wu, C.-Y., Singhal, N., Kr\u00e4henb\u00fchl, P.: Video compression through image interpolation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 425\u2013440. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_26"},{"key":"49_CR44","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: ACM MM (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"49_CR45","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/s11263-017-1033-7","volume":"124","author":"L Zhu","year":"2017","unstructured":"Zhu, L., Xu, Z., Yang, Y., Hauptmann, A.: Uncovering the temporal context for video question answering. IJCV 124, 409\u2013421 (2017)","journal-title":"IJCV"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25072-9_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:52:10Z","timestamp":1710258730000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25072-9_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250712","9783031250729"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25072-9_49","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":"18 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","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":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}