{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T01:37:33Z","timestamp":1794533853915,"version":"4.9.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319488806","type":"print"},{"value":"9783319488813","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-48881-3_58","type":"book-chapter","created":{"date-parts":[[2016,11,2]],"date-time":"2016-11-02T09:19:08Z","timestamp":1478078348000},"page":"883-899","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["GeThR-Net: A Generalized Temporally Hybrid Recurrent Neural Network for Multimodal Information Fusion"],"prefix":"10.1007","author":[{"given":"Ankit","family":"Gandhi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arjun","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arijit","family":"Biswas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Om","family":"Deshmukh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,11,3]]},"reference":[{"issue":"6","key":"58_CR1","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","volume":"16","author":"PK Atrey","year":"2010","unstructured":"Atrey, P.K., Hossain, M.A., El Saddik, A., Kankanhalli, M.S.: Multimodal fusion for multimedia analysis: a survey. Multimedia Syst. 16(6), 345\u2013379 (2010)","journal-title":"Multimedia Syst."},{"key":"58_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","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)"},{"key":"58_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Jin, Q.: Multi-modal dimensional emotion recognition using recurrent neural networks. In: Proceedings of the 5th International Workshop on Audio\/Visual Emotion Challenge, pp. 49\u201356. ACM (2015)","DOI":"10.1145\/2808196.2811638"},{"key":"58_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., C., L.Z.: Mind\u2019s eye: a recurrent visual representation for image caption generation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"58_CR5","doi-asserted-by":"crossref","unstructured":"Escalera, S., Gonz\u00e0lez, J., Bar\u00f3, X., Reyes, M., Lopes, O., Guyon, I., Athitsos, V., Escalante, H.: Multi-modal gesture recognition challenge 2013: dataset and results. In: Proceedings of the 15th ACM on International Conference on Multimodal Interaction, pp. 445\u2013452. ACM (2013)","DOI":"10.1145\/2522848.2532595"},{"key":"58_CR6","doi-asserted-by":"crossref","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: ICML (2014)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"58_CR7","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. In: ICASSP. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"58_CR8","unstructured":"Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: NIPS (2009)"},{"key":"58_CR9","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, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"1","key":"58_CR10","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s00138-013-0567-0","volume":"25","author":"IH Jhuo","year":"2014","unstructured":"Jhuo, I.H., Ye, G., Gao, S., Liu, D., Jiang, Y.G., Lee, D.T., Chang, S.F.: Discovering joint audio-visual codewords for video event detection. Mach. Vis. Appl. 25(1), 33\u201347 (2014)","journal-title":"Mach. Vis. Appl."},{"key":"58_CR11","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"58_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, W., Cotton, C., Chang, S.F., Ellis, D., Loui, A.: Short-term audio-visual atoms for generic video concept classification. In: Proceedings of the 17th ACM International Conference on Multimedia, pp. 5\u201314. ACM (2009)","DOI":"10.1145\/1631272.1631277"},{"key":"58_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, Y.G., Ye, G., Chang, S.F., Ellis, D., Loui, A.C.: Consumer video understanding: a benchmark database and an evaluation of human and machine performance. In: Proceedings of the 1st ACM International Conference on Multimedia Retrieval, p. 29. ACM (2011)","DOI":"10.1145\/1991996.1992025"},{"key":"58_CR14","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)"},{"key":"58_CR15","doi-asserted-by":"crossref","unstructured":"Liu, D., Lai, K.T., Ye, G., Chen, M.S., Chang, S.F.: Sample-specific late fusion for visual category recognition. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)","DOI":"10.1109\/CVPR.2013.109"},{"key":"58_CR16","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s11263-014-0723-7","volume":"109","author":"AJ Ma","year":"2014","unstructured":"Ma, A.J., Yuen, P.C.: Reduced analytic dependency modeling: robust fusion for visual recognition. Int. J. Comput. Vis. 109, 233\u2013251 (2014)","journal-title":"Int. J. Comput. Vis."},{"key":"58_CR17","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-rnn). In: ICLR (2015)"},{"key":"58_CR18","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.L.: Explain images with multimodal recurrent neural networks. arXiv preprint arXiv:1410.1090 (2014)"},{"key":"58_CR19","unstructured":"Ng, J.Y., Hausknecht, M.J., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, 7\u201312 June, 2015"},{"key":"58_CR20","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 689\u2013696 (2011)"},{"key":"58_CR21","unstructured":"Van den Oord, A., Dieleman, S., Schrauwen, B.: Deep content-based music recommendation. In: Advances in Neural Information Processing Systems, pp. 2643\u20132651 (2013)"},{"key":"58_CR22","doi-asserted-by":"crossref","unstructured":"Paleari, M., Lisetti, C.L.: Toward multimodal fusion of affective cues. In: Proceedings of the 1st ACM International Workshop on Human-Centered Multimedia, pp. 99\u2013108. ACM (2006)","DOI":"10.1145\/1178745.1178762"},{"key":"58_CR23","unstructured":"Peng, X., Wang, L., Wang, X., Qiao, Y.: Bag of visual words and fusion methods for action recognition: comprehensive study and good practice. CoRR (2014)"},{"key":"58_CR24","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568\u2013576 (2014)"},{"key":"58_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"58_CR26","doi-asserted-by":"crossref","unstructured":"Snoek, C.G., Worring, M., Smeulders, A.W.: Early versus late fusion in semantic video analysis. In: Proceedings of the 13th Annual ACM International Conference on Multimedia, pp. 399\u2013402. ACM (2005)","DOI":"10.1145\/1101149.1101236"},{"key":"58_CR27","unstructured":"Sohn, K., Shang, W., Lee, H.: Improved multimodal deep learning with variation of information. In: Advances in Neural Information Processing Systems, pp. 2141\u20132149 (2014)"},{"key":"58_CR28","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"58_CR29","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Multimodal learning with deep boltzmann machines. In: Advances in Neural Information Processing Systems, pp. 2222\u20132230 (2012)"},{"issue":"1","key":"58_CR30","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.heares.2009.03.012","volume":"258","author":"BE Stein","year":"2009","unstructured":"Stein, B.E., Stanford, T.R., Rowland, B.A.: The neural basis of multisensory integration in the midbrain: its organization and maturation. Hear. Res. 258(1), 4\u201315 (2009)","journal-title":"Hear. Res."},{"key":"58_CR31","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":"58_CR32","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: The IEEE International Conference on Computer Vision (ICCV), December 2013","DOI":"10.1109\/ICCV.2013.441"},{"key":"58_CR33","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: CVPR, pp. 4305\u20134314 (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"58_CR34","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y.: Towards good practices for very deep two-stream convnets. CoRR (2015)"},{"key":"58_CR35","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1162\/neco.1989.1.2.270","volume":"1","author":"RJ Williams","year":"1989","unstructured":"Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1, 263\u2013269 (1989)","journal-title":"Neural Comput."},{"key":"58_CR36","doi-asserted-by":"crossref","unstructured":"Wu, D., Shao, L.: Multimodal dynamic networks for gesture recognition. In: Proceedings of the ACM International Conference on Multimedia, pp. 945\u2013948. ACM (2014)","DOI":"10.1145\/2647868.2654969"},{"key":"58_CR37","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chang, E.Y., Chang, K.C.C., Smith, J.R.: Optimal multimodal fusion for multimedia data analysis. In: Proceedings of the 12th Annual ACM International Conference on Multimedia, pp. 572\u2013579. ACM (2004)","DOI":"10.1145\/1027527.1027665"},{"key":"58_CR38","doi-asserted-by":"crossref","unstructured":"Wu, Z., Jiang, Y.G., Wang, J., Pu, J., Xue, X.: Exploring inter-feature and inter-class relationships with deep neural networks for video classification. In: Proceedings of the ACM International Conference on Multimedia, pp. 167\u2013176. ACM (2014)","DOI":"10.1145\/2647868.2654931"},{"key":"58_CR39","doi-asserted-by":"crossref","unstructured":"Wu, Z., Jiang, Y.G., Wang, J., Pu, J., Xue, X.: Exploring inter-feature and inter-class relationships with deep neural networks for video classification. In: Proceedings of the 22nd ACM International Conference on Multimedia, MM 2014 (2014)","DOI":"10.1145\/2647868.2654931"},{"key":"58_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wang, X., Jiang, Y.G., Ye, H., Xue, X.: Modeling spatial-temporal clues in a hybrid deep learning framework for video classification. In: Proceedings of the 23rd Annual ACM Conference on Multimedia Conference, pp. 461\u2013470. ACM (2015)","DOI":"10.1145\/2733373.2806222"},{"key":"58_CR41","doi-asserted-by":"crossref","unstructured":"Xie, Z., Guan, L.: Multimodal information fusion of audiovisual emotion recognition using novel information theoretic tools. In: 2013 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2013)","DOI":"10.4018\/ijmdem.2013100101"},{"key":"58_CR42","doi-asserted-by":"crossref","unstructured":"Xu, Z., Yang, Y., Tsang, I., Sebe, N., Hauptmann, A.G.: Feature weighting via optimal thresholding for video analysis. In: 2013 IEEE International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1109\/ICCV.2013.427"},{"key":"58_CR43","doi-asserted-by":"crossref","unstructured":"Yang, X., Tian, Y.: Eigenjoints-based action recognition using naive-bayes-nearest-neighbor. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 14\u201319. IEEE (2012)","DOI":"10.1109\/CVPRW.2012.6239232"},{"key":"58_CR44","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"58_CR45","doi-asserted-by":"crossref","unstructured":"Ye, G., Liu, D., Jhuo, I.H., Chang, S.F., et al.: Robust late fusion with rank minimization. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3021\u20133028. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248032"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-48881-3_58","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T19:24:20Z","timestamp":1749669860000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-48881-3_58"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319488806","9783319488813"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-48881-3_58","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-319-48881-3","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"3 November 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}