{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T01:37:48Z","timestamp":1794533868977,"version":"4.9.1"},"publisher-location":"Cham","reference-count":39,"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_11","type":"book-chapter","created":{"date-parts":[[2016,11,2]],"date-time":"2016-11-02T09:19:08Z","timestamp":1478078348000},"page":"146-161","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Automatic Video Captioning via Multi-channel Sequential Encoding"],"prefix":"10.1007","author":[{"given":"Chenyang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingli","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,11,3]]},"reference":[{"key":"11_CR1","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, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11_CR2","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)"},{"issue":"8","key":"11_CR3","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. IEEE PAMI 35(8), 1915\u20131929 (2013)","journal-title":"IEEE PAMI"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Le, Q.V., Zou, W.Y., Yeung, S.Y., Ng, A.Y.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: CVPR, pp. 3361\u20133368. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: ICCV, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"issue":"8","key":"11_CR7","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1109\/JPROC.2010.2050411","volume":"98","author":"BZ Yao","year":"2010","unstructured":"Yao, B.Z., Yang, X., Lin, L., Lee, M.W., Zhu, S.C.: I2t: Image parsing to text description. Proc. IEEE 98(8), 1485\u20131508 (2010)","journal-title":"Proc. IEEE"},{"key":"11_CR8","unstructured":"Chen, X., Fang, H., Lin, T.Y., Vedantam, R., Gupta, S., Dollar, P., Zitnick, C.L.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"11_CR9","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":"11_CR10","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. arXiv preprint arXiv:1412.2306 (2014)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. arXiv preprint arXiv:1411.4555 (2014)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Chen, X., Zitnick, C.L.: Learning a recurrent visual representation for image caption generation. arXiv preprint arXiv:1411.5654 (2014)","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: NAACL-HLT (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"11_CR14","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: ICCV, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence - video to text. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Aradhye, H., Toderici, G., Yagnik, J.: Video2text: learning to annotate video content. In: ICDM Workshop on Internet Multimedia Mining (2009)","DOI":"10.1109\/ICDMW.2009.79"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., Krishnamoorthy, N., Malkarnenkar, G., Venugopalan, S., Mooney, R., Darrell, T., Saenko, K.: Youtube2text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: ICCV, pp. 2712\u20132719. IEEE (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy, N., Malkarnenkar, G., Mooney, R., Saenko, K., Guadarrama, S.: Generating natural-language video descriptions using text-mined knowledge. In: NAACL HLT 2013, p. 10 (2013)","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"11_CR19","unstructured":"Thomason, J., Venugopalan, S., Guadarrama, S., Saenko, K., Mooney, R.: Integrating language and vision to generate natural language descriptions of videos in the wild. In: COLING (2014)"},{"key":"11_CR20","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1007\/978-3-642-12900-1_14","volume-title":"Video Search and Mining","author":"N Morsillo","year":"2010","unstructured":"Morsillo, N., Mann, G., Pal, C.: YouTube scale, large vocabulary video annotation. In: Schonfeld, D., Shan, C., Tao, D., Wang, L. (eds.) Video Search and Mining. SCI, vol. 287, pp. 357\u2013386. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-12900-1_14"},{"key":"11_CR21","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/978-3-642-35795-4_21","volume-title":"Trustworthy Computing and Services","author":"H Huang","year":"2013","unstructured":"Huang, H., Lu, Y., Zhang, F., Sun, S.: A multi-modal clustering method for web videos. In: Yuan, Y., Wu, X., Lu, Y. (eds.) ISCTCS 2012. CCIS, vol. 320, pp. 163\u2013169. Springer, Heidelberg (2013). doi: 10.1007\/978-3-642-35795-4_21"},{"issue":"8","key":"11_CR22","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1109\/TKDE.2009.145","volume":"22","author":"S Wei","year":"2010","unstructured":"Wei, S., Zhao, Y., Zhu, Z., Liu, N.: Multimodal fusion for video search reranking. IEEE Trans. Knowl. Data Eng. 22(8), 1191\u20131199 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"11_CR23","unstructured":"Xu, K., Ba, J., Kiros, R., Courville, A., Salakhutdinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. arXiv preprint arXiv:1502.03044 (2015)"},{"issue":"3","key":"11_CR24","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1353\/sls.2006.0019","volume":"6","author":"MA Karchmer","year":"2006","unstructured":"Karchmer, M.A., Bachleda, B., Mitchell, R.E., Young, T.A.: How many people use asl in the united states? why estimates need updating. Sign Lang. Stud. 6(3), 306\u2013335 (2006)","journal-title":"Sign Lang. Stud."},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Vogler, C., Metaxas, D.: Parallel hidden markov models for american sign language recognition. In: ICCV, vol. 1, pp. 116\u2013122. IEEE (1999)","DOI":"10.1109\/ICCV.1999.791206"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Starner, T., Pentland, A.: Real-time american sign language recognition from video using hidden markov models. In: Motion-Based Recognition, pp. 227\u2013243. Springer (1997)","DOI":"10.1007\/978-94-015-8935-2_10"},{"key":"11_CR27","unstructured":"Metaxas, D.N., Liu, B., Yang, F., Yang, P., Michael, N., Neidle, C.: Recognition of nonmanual markers in american sign language (asl) using non-parametric adaptive 2d\u20133d face tracking. In: LREC, pp. 2414\u20132420. Citeseer (2012)"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, B., Zhang, S., Yang, F., Yang, P., Metaxas, D.N., Neidle, C.: Recognizing eyebrow and periodic head gestures using crfs for non-manual grammatical marker detection in asl. In: FGR, pp. 1\u20136. IEEE (2013)","DOI":"10.1109\/FG.2013.6553781"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Pugeault, N., Bowden, R.: Spelling it out: Real-time asl fingerspelling recognition. In: ICCV Workshops, pp. 1114\u20131119. IEEE (2011)","DOI":"10.1109\/ICCVW.2011.6130290"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Fok, K.Y., Ganganath, N., Cheng, C.T., Tse, C.K.: A real-time asl recognition system using leap motion sensors. In: CyberC, pp. 411\u2013414. IEEE (2015)","DOI":"10.1109\/CyberC.2015.81"},{"key":"11_CR31","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"issue":"2","key":"11_CR32","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157\u2013166 (1994)","journal-title":"IEEE Trans. Neural Netw."},{"key":"11_CR33","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"11_CR35","unstructured":"Torabi, A., Pal, C., Larochelle, H., Courville, A.: Using descriptive video services to create a large data source for video annotation research. arXiv preprint arXiv:1503.01070 (2015)"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the EACL 2014 Workshop on Statistical Machine Translation, vol. 6 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"11_CR38","unstructured":"Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: a matlab-like environment for machine learning. In: BigLearn, NIPS Workshop. Number EPFL-CONF-192376 (2011)"},{"key":"11_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/978-3-319-24947-6_17","volume-title":"Pattern Recognition","author":"A Rohrbach","year":"2015","unstructured":"Rohrbach, A., Rohrbach, M., Schiele, B.: The long-short story of movie description. In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 209\u2013221. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-24947-6_17"}],"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_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T21:44:02Z","timestamp":1657575842000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-48881-3_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319488806","9783319488813"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-48881-3_11","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"}]}}