{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:07:07Z","timestamp":1743145627286,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012519"},{"type":"electronic","value":"9783030012526"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01252-6_21","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T13:48:05Z","timestamp":1538747285000},"page":"352-369","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Liquid Pouring Monitoring via Rich Sensory Inputs"],"prefix":"10.1007","author":[{"given":"Tz-Ying","family":"Wu","sequence":"first","affiliation":[]},{"given":"Juan-Ting","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Tsun-Hsuang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chan-Wei","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Juan Carlos","family":"Niebles","sequence":"additional","affiliation":[]},{"given":"Min","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"21_CR1","unstructured":"Kubricht, J., Jiang, C., Zhu, Y., Zhu, S.C., Terzopoulos, D., Lu, H.: Probabilistic simulation predicts human performance on viscous fluid-pouring problem. In: CogSci (2016)"},{"key":"21_CR2","unstructured":"Bates, C.J., Yildirim, I., Tenenbaum, J.B., Battaglia, P.W.: Humans predict liquid dynamics using probabilistic simulation. In: CogSci (2015)"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Edmonds, M., et al.: Feeling the force: integrating force and pose for fluent discovery through imitation learning to open medicine bottles. In: IROS (2017)","DOI":"10.1109\/IROS.2017.8206196"},{"key":"21_CR4","unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: a large-scale video classification benchmark. arXiv:1609.08675 (2016)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: Activitynet: a large-scale video benchmark for human activity understanding. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., Sivic, J., Laptev, I., Lacoste-Julien, S.: Joint discovery of object states and manipulating actions. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.234"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Schenck, C., Fox, D., Farhadi, A.: See the glass half full: Reasoning about liquid containers, their volume and content. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.207"},{"key":"21_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1007\/978-3-319-29451-3_54","volume-title":"Image and Video Technology","author":"N Nishida","year":"2016","unstructured":"Nishida, N., Nakayama, H.: Multimodal gesture recognition using multi-stream recurrent neural network. In: Br\u00e4unl, T., McCane, B., Rivera, M., Yu, X. (eds.) PSIVT 2015. LNCS, vol. 9431, pp. 682\u2013694. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-29451-3_54"},{"key":"21_CR9","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402 (2012)"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Ch\u00e9ron, G., Laptev, I., Schmid, C.: P-CNN: pose-based CNN features for action recognition. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.368"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"21_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-319-10602-1_28","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-H Vu","year":"2014","unstructured":"Vu, T.-H., Olsson, C., Laptev, I., Oliva, A., Sivic, J.: Predicting actions from static scenes. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 421\u2013436. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_28"},{"key":"21_CR16","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.aasri.2014.05.016","volume":"6","author":"Yifei Zhang","year":"2014","unstructured":"Zhang, Y., Qu, W., Wang, D.: Action-scene model for human action recognition from videos (2014)","journal-title":"AASRI Procedia"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Moore, D.J., Essa, I.A., Hayes, M.H.: Exploiting human actions and object context for recognition tasks. In: ICCV (1999)","DOI":"10.1109\/ICCV.1999.791201"},{"key":"21_CR18","unstructured":"Delaitre, V., Sivic, J., Laptev, I.: Learning person-object interactions for action recognition in still images. In: NIPS (2011)"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Gupta, A., Kembhavi, A., Davis, L.S.: Observing human-object interactions: using spatial and functional compatibility for recognition. In: TPAMI (2009)","DOI":"10.1109\/TPAMI.2009.83"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Gupta, A., Davis, L.S.: Objects in action: an approach for combining action understanding and object perception. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383331"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Fathi, A., Rehg, J.M.: Modeling actions through state changes. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.333"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Bambach, S., Lee, S., Crandall, D.J., Yu, C.: Lending a hand: detecting hands and recognizing activities in complex egocentric interactions. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.226"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Ma, M., Fan, H., Kitani, K.M.: Going deeper into first-person activity recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.209"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Hu, J.F., Zheng, W.S., Lai, J., Zhang, J.: Jointly learning heterogeneous features for RGB-D activity recognition. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299172"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Lei, J., Ren, X., Fox, D.: Fine-grained kitchen activity recognition using RGB-D. In: UbiComp (2012)","DOI":"10.1145\/2370216.2370248"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Song, S., Cheung, N.M., Chandrasekhar, V., Mandal, B., Liri, J.: Egocentric activity recognition with multimodal fisher vector. In: Acoustics, Speech and Signal Processing (ICASSP). IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472171"},{"key":"21_CR27","unstructured":"de la Torre, F., Hodgins, J.K., Montano, J., Valcarcel, S.: Detailed human data acquisition of kitchen activities: the cmu-multimodal activity database (cmu-mmac). In: CHI Workshop (2009)"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Roggen, D., et al.: Collecting complex activity datasets in highly rich networked sensor environments. In: INSS. IEEE (2010)","DOI":"10.1109\/INSS.2010.5573462"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Ni, B., Hong, R., Wang, M., Tian, Q.: Interaction part mining: a mid-level approach for fine-grained action recognition. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298953"},{"key":"21_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1007\/978-3-319-10593-2_32","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Zhou","year":"2014","unstructured":"Zhou, Y., Ni, B., Yan, S., Moulin, P., Tian, Q.: Pipelining localized semantic features for fine-grained action recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 481\u2013496. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_32"},{"key":"21_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-319-10602-1_38","volume-title":"Computer Vision \u2013 ECCV 2014","author":"X Peng","year":"2014","unstructured":"Peng, X., Zou, C., Qiao, Y., Peng, Q.: Action recognition with stacked fisher vectors. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 581\u2013595. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_38"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Sun, S., Kuang, Z., Sheng, L., Ouyang, W., Zhang, W.: Optical flow guided feature: a fast and robust motion representation for video action recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00151"},{"key":"21_CR33","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":"21_CR34","unstructured":"Schenck, C., Fox, D.: Detection and tracking of liquids with fully convolutional networks. In: RSS workshop (2016)"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Lynch, C., Hsu, J., Levine, S.: Time-contrastive networks: Self-supervised learning from multi-view observation. arXiv:1704.06888 (2017)","DOI":"10.1109\/CVPRW.2017.69"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Yamaguchi, A., Atkeson, C.G.: Stereo vision of liquid and particle flow for robot pouring. In: Humanoids (2016)","DOI":"10.1109\/HUMANOIDS.2016.7803419"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Tamosiunaite, M., Nemec, B., Ude, A., Wrgtter, F.: Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives. In: IEEE-RAS (2011)","DOI":"10.1016\/j.robot.2011.07.004"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Rozo, L., Jimnez, P., Torras, C.: Force-based robot learning of pouring skills using parametric hidden markov models. In: 9th International Workshop on Robot Motion and Control (2013)","DOI":"10.1109\/RoMoCo.2013.6614613"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Brandi, S., Kroemer, O., Peters, J.: Generalizing pouring actions between objects using warped parameters. In: Humanoids (2014)","DOI":"10.1109\/HUMANOIDS.2014.7041426"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Schenck, C., Fox, D.: Visual closed-loop control for pouring liquids. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989307"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Yamaguchi, A., Atkeson, C.G.: Differential dynamic programming with temporally decomposed dynamics. In: IEEE-RAS (2015)","DOI":"10.1109\/HUMANOIDS.2015.7363430"},{"key":"21_CR42","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1016\/j.artint.2014.12.004","volume":"247","author":"Lars Kunze","year":"2017","unstructured":"Kunze, L., Beetz, M.: Envisioning the qualitative effects of robot manipulation actions using simulation-based projections. Artif. Intell. 247, 352\u2013380 (2017)","journal-title":"Artificial Intelligence"},{"key":"21_CR43","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":"21_CR44","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01252-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T01:08:17Z","timestamp":1664932097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01252-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012519","9783030012526"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01252-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}