{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:58:55Z","timestamp":1783439935501,"version":"3.54.6"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012601","type":"print"},{"value":"9783030012618","type":"electronic"}],"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\/978-3-030-01261-8_7","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T16:14:51Z","timestamp":1539015291000},"page":"106-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":97,"title":["Object Level Visual Reasoning in Videos"],"prefix":"10.1007","author":[{"given":"Fabien","family":"Baradel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natalia","family":"Neverova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julien","family":"Mille","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Greg","family":"Mori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"7_CR1","unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: a large-scale video classification benchmark. arXiv preprint arxiv:1609.08675 (2016)"},{"key":"7_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/978-3-642-25446-8_4","volume-title":"Human Behavior Understanding","author":"M Baccouche","year":"2011","unstructured":"Baccouche, M., Mamalet, F., Wolf, C., Garcia, C., Baskurt, A.: Sequential deep learning for human action recognition. In: Salah, A.A., Lepri, B. (eds.) HBU 2011. LNCS, vol. 7065, pp. 29\u201339. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-25446-8_4"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Baradel, F., Wolf, C., Mille, J., Taylor, G.: Glimpse clouds: human activity recognition from unstructured feature points. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00056"},{"key":"7_CR4","unstructured":"Battaglia, P.W., Pascanu, R., Lai, M., Rezende, D.J., Kavukcuoglu, K.: Interaction networks for learning about objects, relations and physics. In: NIPS (2016)"},{"key":"7_CR5","series-title":"Lecture Notes in Computer Science","first-page":"831","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Bolei","year":"2018","unstructured":"Bolei, Z., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part I. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018)"},{"key":"7_CR6","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":"7_CR7","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Scaling egocentric vision: the epic-kitchens dataset. In: ECCV (2018, to appear)","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"7_CR9","unstructured":"Duke, B.: Lintel: Python video decoding (2018). https:\/\/github.com\/dukebw\/lintel"},{"issue":"43","key":"7_CR10","doi-asserted-by":"publisher","first-page":"17621","DOI":"10.1073\/pnas.1109168108","volume":"108","author":"F Fleuret","year":"2011","unstructured":"Fleuret, F., Li, T., Dubout, C., Wampler, E.K., Yantis, S., Geman, D.: Comparing machines and humans on a visual categorization test. Proc. Natl. Acad. Sci. U.S.A. 108(43), 17621\u20135 (2011)","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Fouhey, D.F., Kuo, W., Efros, A.A., Malik, J.: From lifestyle vlogs to everyday interactions. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00524"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. arXiv preprint arXiv:1705.08421 (2017)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"7_CR15","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"},{"issue":"8","key":"7_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"7_CR17","unstructured":"Hudson, D., Manning, C.: Compositional attention networks for machine reasoning. In: ICLR (2018)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Kim, J., Ricci, M., Serre, T.: Not-So-CLEVR: visual relations strain feedforward neural networks. arXiv preprint arXiv:1802.03390 (2018)","DOI":"10.1098\/rsfs.2018.0011"},{"key":"7_CR20","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICML (2015)"},{"key":"7_CR21","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. Int. J. Comput. Vis. (IJCV) 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Luc, P., Neverova, N., Couprie, C., Verbeek, J., LeCun, Y.: Predicting deeper into the future of semantic segmentation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.77"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Luvizon, D., Picard, D., Tabia, H.: 2D\/3D pose estimation and action recognition using multitask deep learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00539"},{"key":"7_CR24","unstructured":"Monfort, M., et al.: Moments in time dataset: one million videos for event understanding. arXiv preprint arXiv:1801.03150 (2018)"},{"key":"7_CR25","unstructured":"Perez, E., Vries, H.D., Strub, F., Dumoulin, V., Courville, A.: Learning visual reasoning without strong priors. In: ICML Machine Learning in Speech and Language Processing Workshop (2017)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Pickup, L.C., et al.: Seeing the arrow of time. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.262"},{"key":"7_CR27","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"issue":"3","key":"7_CR28","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":"7_CR29","unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: NIPS (2017)"},{"key":"7_CR30","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":"7_CR31","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. In: ICLR Workshop (2016)"},{"key":"7_CR32","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: AAAI (2016)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"7_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1007\/978-3-319-44781-0_45","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2016","author":"S Stabinger","year":"2016","unstructured":"Stabinger, S., Rodr\u00edguez-S\u00e1nchez, A., Piater, J.: 25\u00a0years of CNNs: can we compare to human abstraction capabilities? In: Villa, A.E.P., Masulli, P., Pons Rivero, A.J. (eds.) ICANN 2016. LNCS, vol. 9887, pp. 380\u2013387. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-44781-0_45"},{"key":"7_CR35","unstructured":"van Steenkiste, S., Chang, M., Greff, K., Schmidhuber, J.: Relational neural expectation maximization: unsupervised discovery of objects and their interactions. In: ICLR (2018)"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Chen, K., Yeung, D., Shi, B.E., Savarese, S.: Lattice long short-term memory for human action recognition. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.236"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"7_CR38","unstructured":"Velikovi, P., Cucurull, G., Casanova, A., Romero, A., Li , P., Bengio, Y.: Graph attention networks. In: ICLR (2018)"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Action Recognition by Dense Trajectories. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"7_CR40","unstructured":"Watters, N., Zoran, D., Weber, T., Battaglia, P., Pascanu, R., Tacchetti, A.: Visual interaction networks: learning a physics simulator from video. In: NIPS (2017)"},{"key":"7_CR41","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. arXiv preprint arxiv:1712.04851 (2017)"},{"key":"7_CR42","unstructured":"Yeung, S., Russakovsky, O., Jin, N., Andriluka, M., Mori, G., Fei-Fei, L.: Every moment counts: dense detailed labeling of actions in complex videos. arXiv preprint arXiv:1507.05738 (2015)"}],"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\/978-3-030-01261-8_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:33:25Z","timestamp":1665189205000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01261-8_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012601","9783030012618"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01261-8_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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"}]}}