{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:19:14Z","timestamp":1757312354053,"version":"3.40.3"},"publisher-location":"Cham","reference-count":95,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726699"},{"type":"electronic","value":"9783031726705"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72670-5_16","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"277-295","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Nonverbal Interaction Detection"],"prefix":"10.1007","author":[{"given":"Jianan","family":"Wei","sequence":"first","affiliation":[]},{"given":"Tianfei","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Admoni, H., Scassellati, B.: Data-driven model of nonverbal behavior for socially assistive human-robot interactions. In: ICMI (2014)","DOI":"10.1145\/2663204.2663263"},{"issue":"8","key":"16_CR2","doi-asserted-by":"publisher","first-page":"1707","DOI":"10.1109\/TPAMI.2015.2496269","volume":"38","author":"X Alameda-Pineda","year":"2015","unstructured":"Alameda-Pineda, X., et al.: SALSA: a novel dataset for multimodal group behavior analysis. IEEE TPAMI 38(8), 1707\u20131720 (2015)","journal-title":"IEEE TPAMI"},{"key":"16_CR3","unstructured":"Albrecht, K.: Social intelligence: the new science of success (2006)"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Andrist, S., Tan, X.Z., Gleicher, M., Mutlu, B.: Conversational gaze aversion for humanlike robots. In: HRI, pp. 25\u201332 (2014)","DOI":"10.1145\/2559636.2559666"},{"issue":"6111","key":"16_CR5","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1126\/science.1224313","volume":"338","author":"H Aviezer","year":"2012","unstructured":"Aviezer, H., Trope, Y., Todorov, A.: Body cues, not facial expressions, discriminate between intense positive and negative emotions. Science 338(6111), 1225\u20131229 (2012)","journal-title":"Science"},{"key":"16_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107637","volume":"110","author":"S Bai","year":"2021","unstructured":"Bai, S., Zhang, F., Torr, P.H.: Hypergraph convolution and hypergraph attention. Pattern Recogn. 110, 107637 (2021)","journal-title":"Pattern Recogn."},{"issue":"7","key":"16_CR7","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1038\/s41562-018-0298-3","volume":"2","author":"R Bliege Bird","year":"2018","unstructured":"Bliege Bird, R., Ready, E., Power, E.A.: The social significance of subtle signals. Nat. Hum. Behav. 2(7), 452\u2013457 (2018)","journal-title":"Nat. Hum. Behav."},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Burgoon, J.K., Manusov, V., Guerrero, L.K.: Nonverbal Communication. Routledge (2021)","DOI":"10.4324\/9781003095552"},{"key":"16_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: WACV (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Chen, M., Liao, Y., Liu, S., Chen, Z., Wang, F., Qian, C.: Reformulating hoi detection as adaptive set prediction. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Huang, S., Wang, F., Qian, C., Lu, F.: A coarse-to-fine adaptive network for appearance-based gaze estimation. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6636"},{"key":"16_CR13","first-page":"5259","volume":"29","author":"Y Cheng","year":"2020","unstructured":"Cheng, Y., Zhang, X., Lu, F., Sato, Y.: Gaze estimation by exploring two-eye asymmetry. IEEE TIP 29, 5259\u20135272 (2020)","journal-title":"IEEE TIP"},{"issue":"6","key":"16_CR14","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1016\/S0149-7634(00)00025-7","volume":"24","author":"NJ Emery","year":"2000","unstructured":"Emery, N.J.: The eyes have it: the neuroethology, function and evolution of social gaze. Neurosci. Biobehav. Rev. 24(6), 581\u2013604 (2000)","journal-title":"Neurosci. Biobehav. Rev."},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Fan, L., Chen, Y., Wei, P., Wang, W., Zhu, S.C.: Inferring shared attention in social scene videos. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00676"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Fan, L., Wang, W., Huang, S., Tang, X., Zhu, S.C.: Understanding human gaze communication by spatio-temporal graph reasoning. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00582"},{"issue":"6","key":"16_CR17","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1111\/1467-9280.00292","volume":"11","author":"N Fay","year":"2000","unstructured":"Fay, N., Garrod, S., Carletta, J.: Group discussion as interactive dialogue or as serial monologue: the influence of group size. Psychol. Sci. 11(6), 481\u2013486 (2000)","journal-title":"Psychol. Sci."},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Feng, Y., You, H., Zhang, Z., Ji, R., Gao, Y.: Hypergraph neural networks. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Funes\u00a0Mora, K.A., Monay, F., Odobez, J.M.: Eyediap: a database for the development and evaluation of gaze estimation algorithms from RGB and RGB-D cameras. In: Proceedings of the Symposium on Eye Tracking Research and Applications (2014)","DOI":"10.1145\/2578153.2578190"},{"key":"16_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1007\/978-3-030-58610-2_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Gao","year":"2020","unstructured":"Gao, C., Xu, J., Zou, Y., Huang, J.-B.: DRG: dual relation graph for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 696\u2013712. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_41"},{"key":"16_CR21","unstructured":"Gao, C., Zou, Y., Huang, J.B.: ICAN: instance-centric attention network for human-object interaction detection. In: BMVC (2018)"},{"issue":"3","key":"16_CR22","doi-asserted-by":"publisher","first-page":"3181","DOI":"10.1109\/TPAMI.2022.3182052","volume":"45","author":"Y Gao","year":"2022","unstructured":"Gao, Y., Feng, Y., Ji, S., Ji, R.: Hgnn+: general hypergraph neural networks. IEEE TPAMI 45(3), 3181\u20133199 (2022)","journal-title":"IEEE TPAMI"},{"issue":"5","key":"16_CR23","first-page":"2548","volume":"44","author":"Y Gao","year":"2020","unstructured":"Gao, Y., Zhang, Z., Lin, H., Zhao, X., Du, S., Zou, C.: Hypergraph learning: methods and practices. IEEE TPAMI 44(5), 2548\u20132566 (2020)","journal-title":"IEEE TPAMI"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Doll\u00e1r, P., He, K.: Detecting and recognizing human-object interactions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00872"},{"key":"16_CR25","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"16_CR26","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1146\/annurev-psych-010418-103145","volume":"70","author":"JA Hall","year":"2019","unstructured":"Hall, J.A., Horgan, T.G., Murphy, N.A.: Nonverbal communication. Annu. Rev. Psychol. 70, 271\u2013294 (2019)","journal-title":"Annu. Rev. Psychol."},{"issue":"2","key":"16_CR27","first-page":"47","volume":"20","author":"A Hans","year":"2015","unstructured":"Hans, A., Hans, E.: Kinesics, haptics and proxemics: aspects of non-verbal communication. IOSR J. Hum. Soc. Sci. (IOSR-JHSS) 20(2), 47\u201352 (2015)","journal-title":"IOSR J. Hum. Soc. Sci. (IOSR-JHSS)"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Huang, B., Ju, J., Li, Z., Wang, Y.: Reconstructing groups of people with hypergraph relational reasoning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01366"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Iftekhar, A., Chen, H., Kundu, K., Li, X., Tighe, J., Modolo, D.: What to look at and where: Semantic and spatial refined transformer for detecting human-object interactions. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, J., Wei, Y., Feng, Y., Cao, J., Gao, Y.: Dynamic hypergraph neural networks. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/366"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Joo, H., Simon, T., Cikara, M., Sheikh, Y.: Towards social artificial intelligence: nonverbal social signal prediction in a triadic interaction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01113"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Kellnhofer, P., Recasens, A., Stent, S., Matusik, W., Torralba, A.: Gaze360: physically unconstrained gaze estimation in the wild. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00701"},{"key":"16_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-030-58555-6_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Kim","year":"2020","unstructured":"Kim, B., Choi, T., Kang, J., Kim, H.J.: UnionDet: union-level detector towards real-time human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 498\u2013514. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_30"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, J., Kang, J., Kim, E.S., Kim, H.J.: HOTR: end-to-end human-object interaction detection with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"16_CR36","unstructured":"Knapp, M.L., Hall, J.A., Horgan, T.G.: Nonverbal communication in human interaction. Cengage Learn. (2013)"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Li, S., Deng, W., Du, J.: Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.277"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, Z., Liu, Z.: Action recognition based on a bag of 3D points. In: CVPRW (2010)","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Liao, Y., Liu, S., Wang, F., Chen, Y., Qian, C., Feng, J.: PPDM: parallel point detection and matching for real-time human-object interaction detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Liao, Y., Zhang, A., Lu, M., Wang, Y., Li, X., Liu, S.: GEN-VLKT: simplify association and enhance interaction understanding for hoi detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Liu, D., Zhang, L., Wu, Y.: LD-CONGR: a large RGB-D video dataset for long-distance continuous gesture recognition. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00330"},{"issue":"9","key":"16_CR42","first-page":"4987","volume":"44","author":"S Liu","year":"2021","unstructured":"Liu, S., et al.: Human-centric relation segmentation: dataset and solution. IEEE TPAMI 44(9), 4987\u20135001 (2021)","journal-title":"IEEE TPAMI"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, Y.L., Lu, C.: Highlighting object category immunity for the generalization of human-object interaction detection. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i2.20075"},{"key":"16_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/978-3-030-58568-6_15","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Chen, Q., Zisserman, A.: Amplifying key cues for human-object-interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 248\u2013265. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_15"},{"key":"16_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Lucey, P., Cohn, J.F., Kanade, T., Saragih, J., Ambadar, Z., Matthews, I.: The extended cohn-kanade dataset (CK+): a complete dataset for action unit and emotion-specified expression. In: CVPRW (2010)","DOI":"10.1109\/CVPRW.2010.5543262"},{"issue":"45","key":"16_CR47","doi-asserted-by":"publisher","first-page":"16518","DOI":"10.1073\/pnas.0507650102","volume":"102","author":"HK Meeren","year":"2005","unstructured":"Meeren, H.K., van Heijnsbergen, C.C., de Gelder, B.: Rapid perceptual integration of facial expression and emotional body language. Proc. Natl. Acad. Sci. 102(45), 16518\u201316523 (2005)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"3","key":"16_CR48","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1037\/h0024648","volume":"31","author":"A Mehrabian","year":"1967","unstructured":"Mehrabian, A., Ferris, S.R.: Inference of attitudes from nonverbal communication in two channels. J. Consult. Psychol. 31(3), 248 (1967)","journal-title":"J. Consult. Psychol."},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Misra, I., Lawrence\u00a0Zitnick, C., Mitchell, M., Girshick, R.: Seeing through the human reporting bias: visual classifiers from noisy human-centric labels. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.320"},{"issue":"1","key":"16_CR50","first-page":"18","volume":"10","author":"A Mollahosseini","year":"2017","unstructured":"Mollahosseini, A., Hasani, B., Mahoor, M.H.: AffectNet: a database for facial expression, valence, and arousal computing in the wild. IEEE TAC 10(1), 18\u201331 (2017)","journal-title":"IEEE TAC"},{"issue":"4","key":"16_CR51","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1006\/drev.1994.1014","volume":"14","author":"C Moore","year":"1994","unstructured":"Moore, C., Corkum, V.: Social understanding at the end of the first year of life. Dev. Rev. 14(4), 349\u2013372 (1994)","journal-title":"Dev. Rev."},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Narayana, P., Beveridge, R., Draper, B.A.: Gesture recognition: focus on the hands. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00549"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"Ning, S., Qiu, L., Liu, Y., He, X.: Hoiclip: efficient knowledge transfer for hoi detection with vision-language models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"16_CR54","unstructured":"Park, H., Jain, E., Sheikh, Y.: 3D social saliency from head-mounted cameras. In: NeurIPS (2012)"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Pentland, A.: Honest Signals: How they Shape Our World. MIT Press (2010)","DOI":"10.1145\/2072298.2072374"},{"key":"16_CR56","unstructured":"Philpott, J.S.: The relative contribution to meaning of verbal and nonverbal channels of communication: a meta-analysis. Unpublished master\u2019s thesis, University of Nebraska, Lincoln (1983)"},{"key":"16_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/978-3-030-01240-3_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Qi","year":"2018","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.-C.: Learning Human-Object Interactions by Graph Parsing Neural Networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 407\u2013423. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_25"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Qu, X., Ding, C., Li, X., Zhong, X., Tao, D.: Distillation using oracle queries for transformer-based human-object interaction detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"16_CR59","unstructured":"Richmond, V.P.: Nonverbal behavior in interpersonal relations (2008)"},{"key":"16_CR60","unstructured":"Sapir, E.: The unconscious patterning of behavior in society. In: Selected Writings of Edward Sapir in Language, Culture, and Personality (1949)"},{"issue":"9","key":"16_CR61","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1016\/j.neunet.2008.05.003","volume":"21","author":"K Schindler","year":"2008","unstructured":"Schindler, K., Van Gool, L., De Gelder, B.: Recognizing emotions expressed by body pose: a biologically inspired neural model. Neural Netw. 21(9), 1238\u20131246 (2008)","journal-title":"Neural Netw."},{"issue":"4","key":"16_CR62","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/j.tics.2018.02.004","volume":"22","author":"LB Smith","year":"2018","unstructured":"Smith, L.B., Jayaraman, S., Clerkin, E., Yu, C.: The developing infant creates a curriculum for statistical learning. Trends Cogn. Sci. 22(4), 325\u2013336 (2018)","journal-title":"Trends Cogn. Sci."},{"key":"16_CR63","doi-asserted-by":"crossref","unstructured":"Strabala, K., Lee, M.K., Dragan, A., Forlizzi, J., Srinivasa, S.S.: Learning the communication of intent prior to physical collaboration. In: IEEE RO-MAN (2012)","DOI":"10.1109\/ROMAN.2012.6343875"},{"key":"16_CR64","doi-asserted-by":"crossref","unstructured":"Tamura, M., Ohashi, H., Yoshinaga, T.: QPIC: query-based pairwise human-object interaction detection with image-wide contextual information. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"16_CR65","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H.: Unbiased scene graph generation from biased training. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"16_CR66","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/BF00987202","volume":"10","author":"S Thayer","year":"1986","unstructured":"Thayer, S.: History and strategies of research on social touch. J. Nonverbal Behav. 10, 12\u201328 (1986)","journal-title":"J. Nonverbal Behav."},{"issue":"2","key":"16_CR67","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/34.908962","volume":"23","author":"YI Tian","year":"2001","unstructured":"Tian, Y.I., Kanade, T., Cohn, J.F.: Recognizing action units for facial expression analysis. IEEE TPAMI 23(2), 97\u2013115 (2001)","journal-title":"IEEE TPAMI"},{"key":"16_CR68","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/978-3-031-19772-7_6","volume-title":"ECCV 2022","author":"D Tu","year":"2022","unstructured":"Tu, D., Min, X., Duan, H., Guo, G., Zhai, G., Shen, W.: IWIN: human-object interaction detection via transformer with irregular windows. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13664, pp. 57\u2013103. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_6"},{"issue":"4","key":"16_CR69","first-page":"643","volume":"15","author":"P Uluer","year":"2023","unstructured":"Uluer, P., Kose, H., Gumuslu, E., Barkana, D.E.: Experience with an affective robot assistant for children with hearing disabilities. IJSR 15(4), 643\u2013660 (2023)","journal-title":"IJSR"},{"key":"16_CR70","doi-asserted-by":"crossref","unstructured":"Ulutan, O., Iftekhar, A., Manjunath, B.S.: VSGNet: spatial attention network for detecting human object interactions using graph convolutions. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"16_CR71","doi-asserted-by":"crossref","unstructured":"Vinciarelli, A., Salamin, H., Pantic, M.: Social signal processing: Understanding social interactions through nonverbal behavior analysis. In: CVPRW, pp. 42\u201349 (2009)","DOI":"10.1109\/CVPRW.2009.5204290"},{"key":"16_CR72","series-title":"LNCS","first-page":"654","volume-title":"ECCV 2022","author":"G Wang","year":"2022","unstructured":"Wang, G., Guo, Y., Wong, Y., Kankanhalli, M.: Chairs can be stood on: overcoming object bias in human-object interaction detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13684, pp. 654\u2013672. Springer, Cham (2022)"},{"key":"16_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/978-3-030-58520-4_15","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zheng, W., Yingbiao, L.: Contextual heterogeneous graph network for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 248\u2013264. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_15"},{"key":"16_CR74","doi-asserted-by":"crossref","unstructured":"Wang, S., Duan, Y., Ding, H., Tan, Y.P., Yap, K.H., Yuan, J.: Learning transferable human-object interaction detector with natural language supervision. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"16_CR75","unstructured":"Wang, W., Yang, Y., Pan, Y.: Visual knowledge in the big model era: retrospect and prospect. Front. Inf. Technol. Electron. Eng. (2024)"},{"key":"16_CR76","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhang, Z., Qi, S., Shen, J., Pang, Y., Shao, L.: Learning compositional neural information fusion for human parsing. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00580"},{"issue":"7","key":"16_CR77","first-page":"3508","volume":"44","author":"W Wang","year":"2021","unstructured":"Wang, W., Zhou, T., Qi, S., Shen, J., Zhu, S.C.: Hierarchical human semantic parsing with comprehensive part-relation modeling. IEEE TPAMI 44(7), 3508\u20133522 (2021)","journal-title":"IEEE TPAMI"},{"key":"16_CR78","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhu, H., Dai, J., Pang, Y., Shen, J., Shao, L.: Hierarchical human parsing with typed part-relation reasoning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00895"},{"key":"16_CR79","doi-asserted-by":"crossref","unstructured":"Wang, X., et\u00a0al.: Panda: a gigapixel-level human-centric video dataset. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00333"},{"key":"16_CR80","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Ferv39k: a large-scale multi-scene dataset for facial expression recognition in videos. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"16_CR81","doi-asserted-by":"crossref","unstructured":"Wu, X., Chen, Q., Li, W., Xiao, Y., Hu, B.: AdahGNN: adaptive hypergraph neural networks for multi-label image classification. In: ACM MM (2020)","DOI":"10.1145\/3394171.3414046"},{"key":"16_CR82","doi-asserted-by":"crossref","unstructured":"Xia, L., Chen, C.C., Aggarwal, J.K.: View invariant human action recognition using histograms of 3d joints. In: CVPRW (2012)","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"16_CR83","doi-asserted-by":"crossref","unstructured":"Xu, X., Zou, Q., Lin, X.: Adaptive hypergraph neural network for multi-person pose estimation. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20201"},{"key":"16_CR84","unstructured":"Yadati, N., Nimishakavi, M., Yadav, P., Nitin, V., Louis, A., Talukdar, P.: HyperGCN: a new method for training graph convolutional networks on hypergraphs. In: NeurIPS (2019)"},{"key":"16_CR85","doi-asserted-by":"crossref","unstructured":"Yang, L., Li, L., Xin, X., Sun, Y., Song, Q., Wang, W.: Large-scale person detection and localization using overhead fisheye cameras. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01827"},{"key":"16_CR86","doi-asserted-by":"crossref","unstructured":"Yuan, H., Jiang, J., Albanie, S., Feng, T., Huang, Z., Ni, D., Tang, M.: RLIP: relational language-image pre-training for human-object interaction detection. In: NeurIPS (2022)","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"16_CR87","unstructured":"Zhang, A., et al.: Mining the benefits of two-stage and one-stage hoi detection. In: NeurIPS (2021)"},{"key":"16_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Campbell, D., Gould, S.: Efficient two-stage detection of human-object interactions with a novel unary-pairwise transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01947"},{"issue":"5","key":"16_CR89","first-page":"1038","volume":"20","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., Cao, C., Cheng, J., Lu, H.: Egogesture: a new dataset and benchmark for egocentric hand gesture recognition. IEEE TMM 20(5), 1038\u20131050 (2018)","journal-title":"IEEE TMM"},{"key":"16_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Pan, Y., Yao, T., Huang, R., Mei, T., Chen, C.W.: Exploring structure-aware transformer over interaction proposals for human-object interaction detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01894"},{"issue":"9","key":"16_CR91","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1016\/j.imavis.2011.07.002","volume":"29","author":"G Zhao","year":"2011","unstructured":"Zhao, G., Huang, X., Taini, M., Li, S.Z., Pietik\u00e4Inen, M.: Facial expression recognition from near-infrared videos. Image Vis. Comput. 29(9), 607\u2013619 (2011)","journal-title":"Image Vis. Comput."},{"key":"16_CR92","doi-asserted-by":"crossref","unstructured":"Zhou, D., Huang, J., Sch\u00f6lkopf, B.: Learning with hypergraphs: Clustering, classification, and embedding. In: NeurIPS (2006)","DOI":"10.7551\/mitpress\/7503.003.0205"},{"issue":"6","key":"16_CR93","doi-asserted-by":"publisher","first-page":"2827","DOI":"10.1109\/TPAMI.2021.3049156","volume":"44","author":"T Zhou","year":"2021","unstructured":"Zhou, T., Qi, S., Wang, W., Shen, J., Zhu, S.C.: Cascaded parsing of human-object interaction recognition. IEEE TPAMI 44(6), 2827\u20132840 (2021)","journal-title":"IEEE TPAMI"},{"key":"16_CR94","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, W., Liu, S., Yang, Y., Van\u00a0Gool, L.: Differentiable multi-granularity human representation learning for instance-aware human semantic parsing. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00167"},{"issue":"7","key":"16_CR95","doi-asserted-by":"crossref","first-page":"8296","DOI":"10.1109\/TPAMI.2023.3236459","volume":"45","author":"T Zhou","year":"2023","unstructured":"Zhou, T., Yang, Y., Wang, W.: Cascaded parsing of human-object interaction recognition. IEEE TPAMI 45(7), 8296\u20138310 (2023)","journal-title":"IEEE TPAMI"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72670-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:21:15Z","timestamp":1727594475000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72670-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726699","9783031726705"],"references-count":95,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72670-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}