{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T11:38:13Z","timestamp":1769859493668,"version":"3.49.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,3,11]],"date-time":"2015-03-11T00:00:00Z","timestamp":1426032000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2016,2]]},"DOI":"10.1007\/s00521-015-1846-7","type":"journal-article","created":{"date-parts":[[2015,3,10]],"date-time":"2015-03-10T06:16:09Z","timestamp":1425968169000},"page":"335-348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Main objects interaction activity recognition in real images"],"prefix":"10.1007","volume":"27","author":[{"given":"Lin","family":"Bai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianmeng","family":"Pei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,3,11]]},"reference":[{"key":"1846_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka M, Sigal L (2012) Human context: modeling human-human interactions for monocular 3d pose estimation. In: Perales FJ, Fisher RB, Moeslund TB (eds) Articulated motion and deformable objects, Springer, Berlin, Heidelberg, pp 260\u2013272","DOI":"10.1007\/978-3-642-31567-1_26"},{"key":"1846_CR2","doi-asserted-by":"crossref","unstructured":"Desai C, Ramanan D (2012) Detecting actions, poses, and objects with relational phraselets. In: Fitzgibbon A, Lazebnik S, Perona P, Sato Y, Schmid C (eds) Computer vision-ECCV 2012, Springer, Berlin, Heidelberg, pp 158\u2013172","DOI":"10.1007\/978-3-642-33765-9_12"},{"key":"1846_CR3","doi-asserted-by":"crossref","unstructured":"Desai C, Ramanan D, Fowlkes C (2010) Discriminative models for static human-object interactions. In: Computer vision and pattern recognition workshops (CVPRW), 2010 IEEE computer society conference on, pp 9\u201316","DOI":"10.1109\/CVPRW.2010.5543176"},{"issue":"1","key":"1846_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-011-0439-x","volume":"95","author":"C Desai","year":"2011","unstructured":"Desai C, Ramanan D, Fowlkes CC (2011) Discriminative models for multi-class object layout. Int J Comput Vis 95(1):1\u201312","journal-title":"Int J Comput Vis"},{"key":"1846_CR5","unstructured":"Faccin M, Migda\u0142 P, Johnson T, Biamonte J. Bergholm V (2013) Community detection in quantum complex networks. arXiv preprint arXiv:1310.6638"},{"key":"1846_CR6","doi-asserted-by":"crossref","unstructured":"Franc V, Sonnenburg S (2008) Optimized cutting plane algorithm for support vector machines. In: Proceedings of the 25th international conference on machine learning, ACM, pp 320\u2013327","DOI":"10.1145\/1390156.1390197"},{"key":"1846_CR7","unstructured":"George D (2008) How the brain might work: a hierarchical and temporal model for learning and recognition. Ph.D. thesis, Stanford University"},{"key":"1846_CR8","unstructured":"Guerra-Filho G, Fermuller C, Aloimonos Y (2005) Discovering a language for human activity. In: Proceedings of the AAAI 2005 fall symposium on anticipatory cognitive embodied systems, Washington, DC"},{"issue":"10","key":"1846_CR9","doi-asserted-by":"crossref","first-page":"3343","DOI":"10.1016\/j.patcog.2014.04.018","volume":"47","author":"G Guo","year":"2014","unstructured":"Guo G, Lai A (2014) A survey on still image based human action recognition. Pattern Recognit 47(10):3343\u20133361","journal-title":"Pattern Recognit"},{"issue":"10","key":"1846_CR10","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"Gupta A, Kembhavi A, Davis LS (2009) Observing human-object interactions: using spatial and functional compatibility for recognition. IEEE Trans Pattern Anal Mach Intell 31(10):1775\u20131789","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1846_CR11","doi-asserted-by":"crossref","unstructured":"Gupta A, Mannem P (2012) From image annotation to image description. In: Huang T, Zeng Z, Li C, Leung CS (eds) Neural information processing, Springer, Berlin, Heidelberg, pp 196\u2013204","DOI":"10.1007\/978-3-642-34500-5_24"},{"key":"1846_CR12","doi-asserted-by":"crossref","unstructured":"Gupta A, Srinivasan P, Shi J, Davis LS (2009) Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009. pp 2012\u20132019","DOI":"10.1109\/CVPR.2009.5206492"},{"key":"1846_CR13","volume-title":"Hierarchical temporal memory: concepts, theory and terminology","author":"J Hawkins","year":"2006","unstructured":"Hawkins J, George D (2006) Hierarchical temporal memory: concepts, theory and terminology. Numenta Inc, Whitepaper"},{"issue":"5786","key":"1846_CR14","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"issue":"3","key":"1846_CR15","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1007\/s11263-010-0400-4","volume":"91","author":"D Hoiem","year":"2011","unstructured":"Hoiem D, Efros AA, Hebert M (2011) Recovering occlusion boundaries from an image. Int J Comput Vis 91(3):328\u2013346","journal-title":"Int J Comput Vis"},{"key":"1846_CR16","doi-asserted-by":"crossref","unstructured":"Hu JF, Zheng WS, Lai J, Gong S, Xiang T (2013) Recognising human-object interaction via exemplar based modelling. In: 2013 IEEE international conference on computer vision (ICCV), pp 3144\u20133151","DOI":"10.1109\/ICCV.2013.390"},{"key":"1846_CR17","unstructured":"Hussein ME, Torki M, Gowayyed MA, El-Saban M (2013) Human action recognition using a temporal hierarchy of covariance descriptors on 3d joint locations. In: Rossi F (ed) Proceedings of the twenty-third international joint conference on artificial intelligence, AAAI Press, California, pp 2466\u20132472"},{"issue":"6","key":"1846_CR18","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1016\/S0896-6273(03)00524-5","volume":"39","author":"SH Johnson-Frey","year":"2003","unstructured":"Johnson-Frey SH, Maloof FR, Newman-Norlund R, Farrer C, Inati S, Grafton ST (2003) Actions or hand-object interactions: human inferior frontal cortex and action observation. Neuron 39(6):1053\u20131058","journal-title":"Neuron"},{"key":"1846_CR19","unstructured":"Karpathy A, Joulin A, Li FFF (2014) Deep fragment embeddings for bidirectional image sentence mapping. In: Advances in neural information processing systems, pp 1889\u20131897"},{"key":"1846_CR20","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"issue":"12","key":"1846_CR21","doi-asserted-by":"crossref","first-page":"2443","DOI":"10.1016\/j.physa.2010.02.014","volume":"389","author":"D Lai","year":"2010","unstructured":"Lai D, Lu H, Nardini C (2010) Finding communities in directed networks by pagerank random walk induced network embedding. Physica A: Stat Mech Appl 389(12):2443\u20132454","journal-title":"Physica A: Stat Mech Appl"},{"key":"1846_CR22","unstructured":"Li LJ, Socher R, Fei-Fei L (2009) Towards total scene understanding: classification, annotation and segmentation in an automatic framework. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009, pp 2036\u20132043"},{"key":"1846_CR23","unstructured":"Memisevic R, Zach C, Pollefeys M, Hinton GE (2010) Gated softmax classification. In: Advances in neural information processing systems, pp 1603\u20131611"},{"issue":"2","key":"1846_CR24","doi-asserted-by":"crossref","first-page":"022,817","DOI":"10.1103\/PhysRevE.87.022817","volume":"87","author":"E Mones","year":"2013","unstructured":"Mones E (2013) Hierarchy in directed random networks. Phys Rev E 87(2):022,817","journal-title":"Phys Rev E"},{"issue":"4","key":"1846_CR25","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1109\/TPAMI.2012.175","volume":"35","author":"A Prest","year":"2013","unstructured":"Prest A, Ferrari V, Schmid C (2013) Explicit modeling of human-object interactions in realistic videos. IEEE Trans Pattern Anal Mach Intell 35(4):835\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1846_CR26","unstructured":"Ratliff N, Bagnell JA, Zinkevich M (2006) Subgradient methods for maximum margin structured learning. In: ICML workshop on learning in structured output spaces, vol. 46. Citeseer"},{"key":"1846_CR27","doi-asserted-by":"crossref","unstructured":"Rohrbach M, Qiu W, Titov I, Thater S, Pinkal M, Schiele B (2013) Translating video content to natural language descriptions. In: 2013 IEEE international conference on computer vision (ICCV), pp 433\u2013440","DOI":"10.1109\/ICCV.2013.61"},{"key":"1846_CR28","doi-asserted-by":"crossref","unstructured":"Sadeghi MA, Farhadi A (2011) Recognition using visual phrases. In: 2011 IEEE conference on computer vision and pattern recognition (CVPR), pp 1745\u20131752","DOI":"10.1109\/CVPR.2011.5995711"},{"issue":"15","key":"1846_CR29","doi-asserted-by":"crossref","first-page":"6424","DOI":"10.1073\/pnas.0700622104","volume":"104","author":"T Serre","year":"2007","unstructured":"Serre T, Oliva A, Poggio T (2007) A feedforward architecture accounts for rapid categorization. Proc Natl Acad Sci 104(15):6424\u20136429","journal-title":"Proc Natl Acad Sci"},{"key":"1846_CR30","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9266.001.0001","volume-title":"Discovering the human connectome","author":"O Sporns","year":"2012","unstructured":"Sporns O (2012) Discovering the human connectome. MIT Press, Cambridge"},{"key":"1846_CR31","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going deeper with convolutions. arXiv preprint arXiv:1409.4842"},{"key":"1846_CR32","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2014) Show and tell: A neural image caption generator. arXiv preprint arXiv:1411.4555"},{"key":"1846_CR33","doi-asserted-by":"crossref","unstructured":"Wei P, Zhao Y, Zheng N, Zhu SC (2013) Modeling 4d human-object interactions for event and object recognition. In: 2013 IEEE international conference on computer vision (ICCV), pp 3272\u20133279","DOI":"10.1109\/ICCV.2013.406"},{"key":"1846_CR34","doi-asserted-by":"crossref","unstructured":"Wisuttirungseurai P, Kawewong A, Patanukhom K (2014) Object categorization using co-occurrence and spatial relationship with human interaction. In: International conference on 2014 information science and applications (ICISA), pp 1\u20134","DOI":"10.1109\/ICISA.2014.6847439"},{"key":"1846_CR35","doi-asserted-by":"crossref","unstructured":"Yao B, Fei-Fei L (2010) Grouplet: a structured image representation for recognizing human and object interactions. In: IEEE conference on computer vision and pattern recognition (CVPR), 2010, pp 9\u201316","DOI":"10.1109\/CVPR.2010.5540234"},{"issue":"9","key":"1846_CR36","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1109\/TPAMI.2012.67","volume":"34","author":"B Yao","year":"2012","unstructured":"Yao B, Fei-Fei L (2012) Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses. IEEE Trans Pattern Anal Mach Intell 34(9):1691\u20131703","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-015-1846-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-015-1846-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-015-1846-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T20:32:16Z","timestamp":1566419536000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-015-1846-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,3,11]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["1846"],"URL":"https:\/\/doi.org\/10.1007\/s00521-015-1846-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,3,11]]}}}