{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:25:23Z","timestamp":1726763123178},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031200670"},{"type":"electronic","value":"9783031200687"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20068-7_20","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T08:06:38Z","timestamp":1668067598000},"page":"346-362","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["PoseScript: 3D Human Poses from\u00a0Natural Language"],"prefix":"10.1007","author":[{"given":"Ginger","family":"Delmas","sequence":"first","affiliation":[]},{"given":"Philippe","family":"Weinzaepfel","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Lucas","sequence":"additional","affiliation":[]},{"given":"Francesc","family":"Moreno-Noguer","sequence":"additional","affiliation":[]},{"given":"Gr\u00e9gory","family":"Rogez","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Achlioptas, P., Fan, J., Hawkins, R., Goodman, N., Guibas, L.J.: ShapeGlot: learning language for shape differentiation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00903"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Ahn, H., Ha, T., Choi, Y., Yoo, H., Oh, S.: Text2Action: generative adversarial synthesis from language to action. In: ICRA (2018)","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Ahuja, C., Morency, L.P.: Language2Pose: natural language grounded pose forecasting. 3DV (2019)","DOI":"10.1109\/3DV.2019.00084"},{"key":"20_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep It SMPL: automatic estimation of 3D human pose and shape from a single image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3D human pose annotations. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"20_CR6","unstructured":"Briq, R., Kochar, P., Gall, J.: Towards better adversarial synthesis of human images from text. arXiv preprint arXiv:2107.01869 (2021)"},{"key":"20_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-030-58565-5_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"DZ Chen","year":"2020","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 202\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_13"},{"key":"20_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-030-20893-6_7","volume-title":"Computer Vision \u2013 ACCV 2018","author":"K Chen","year":"2019","unstructured":"Chen, K., Choy, C.B., Savva, M., Chang, A.X., Funkhouser, T., Savarese, S.: Text2Shape: generating shapes from natural language by learning joint embeddings. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 100\u2013116. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_7"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Feng, F., Wang, X., Li, R.: Cross-modal retrieval with correspondence autoencoder. In: ACMMM (2014)","DOI":"10.1145\/2647868.2654902"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Pirlea, S.C., Olaru, V., Sminchisescu, C.: AIFit: automatic 3D human-interpretable feedback models for fitness training. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00979"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Cheema, N., Oguz, C., Theobalt, C., Slusallek, P.: Synthesis of compositional animations from textual descriptions. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Guo, et al.: Action2Motion: conditioned generation of 3D human motions. In: ACMMM (2020)","DOI":"10.1145\/3394171.3413635"},{"key":"20_CR14","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. PAMI 36, 1325\u20131339 (2014)","journal-title":"IEEE Trans. PAMI"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Huang, Z., Pan, X., Loy, C.C., Liu, Z.: Talk-to-edit: fine-grained facial editing via dialog. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01354"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3D human model fitting towards in-the-wild 3D human pose estimation. In: 3DV (2020)","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Kim, H., Zala, A., Burri, G., Bansal, M.: FixMyPose: pose correctional captioning and retrieval. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i14.17555"},{"key":"20_CR19","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Yang, W., Wang, X.: Identity-aware textual-visual matching with latent co-attention. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.209"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, Z., Liu, Z.: Action recognition based on a bag of 3D points. In: CVPR Workshops (2010)","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"20_CR22","unstructured":"Lin, A.S., Wu, L., Corona, R., Tai, K.W.H., Huang, Q., Mooney, R.J.: Generating animated videos of human activities from natural language descriptions. In: NeurIPS workshops (2018)"},{"key":"20_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Lucas, T., Baradel, F., Weinzaepfel, P., Rogez, G.: PoseGPT: quantization-based 3D human motion generation and forecasting. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20068-7_24"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Muralidhar Jayanthi, S., Pruthi, D., Neubig, G.: NeuSpell: a neural spelling correction toolkit. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-demos.21"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Daniilidis, K.: Ordinal depth supervision for 3D human pose estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00763"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"20_CR31","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1089\/big.2016.0028","volume":"4","author":"M Plappert","year":"2016","unstructured":"Plappert, M., Mandery, C., Asfour, T.: The kit motion-language dataset. Big Data 4, 236\u2013252 (2016)","journal-title":"Big Data"},{"key":"20_CR32","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.robot.2018.07.006","volume":"109","author":"M Plappert","year":"2018","unstructured":"Plappert, M., Mandery, C., Asfour, T.: Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks. Robot. Auton. Syst. 109, 13\u201326 (2018)","journal-title":"Robot. Auton. Syst."},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Pons-Moll, G., Fleet, D.J., Rosenhahn, B.: Posebits for monocular human pose estimation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.300"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Punnakkal, A.R., Chandrasekaran, A., Athanasiou, N., Quiros-Ramirez, A., Black, M.J.: BABEL: bodies, action and behavior with English labels. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"20_CR35","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"20_CR36","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. In: SIGGRAPH Asia (2017)","DOI":"10.1145\/3130800.3130883"},{"key":"20_CR38","unstructured":"Rybkin, O., Daniilidis, K., Levine, S.: Simple and effective VAE training with calibrated decoders. In: ICML (2021)"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"20_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925981","volume":"35","author":"S Streuber","year":"2016","unstructured":"Streuber, S., et al.: Body talk: crowdshaping realistic 3D avatars with words. ACM TOG 35, 1\u201314 (2016)","journal-title":"ACM TOG"},{"key":"20_CR41","doi-asserted-by":"publisher","first-page":"109","DOI":"10.5539\/jel.v7n3p109","volume":"7","author":"C Suveren-Erdogan","year":"2018","unstructured":"Suveren-Erdogan, C., Suveren, S.: Teaching of basic posture skills in visually impaired individuals and its implementation under aggravated conditions. J. Educ. Learn. 7, 109\u2013116 (2018)","journal-title":"J. Educ. Learn."},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Vo, N., et al.: Composing text and image for image retrieval-an empirical odyssey. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00660"},{"key":"20_CR44","first-page":"3441","volume":"3","author":"T Yamada","year":"2018","unstructured":"Yamada, T., Matsunaga, H., Ogata, T.: Paired recurrent autoencoders for bidirectional translation between robot actions and linguistic descriptions. IEEE RAL 3, 3441\u20133448 (2018)","journal-title":"IEEE RAL"},{"key":"20_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/978-3-030-71278-5_11","volume-title":"Pattern Recognition","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Briq, R., Tanke, J., Gall, J.: Adversarial synthesis of human pose from text. In: Akata, Z., Geiger, A., Sattler, T. (eds.) DAGM GCPR 2020. LNCS, vol. 12544, pp. 145\u2013158. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-71278-5_11"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00589"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20068-7_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T18:25:55Z","timestamp":1678559155000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20068-7_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200670","9783031200687"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20068-7_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","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)"}}]}}