{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:47:47Z","timestamp":1778082467212,"version":"3.51.4"},"publisher-location":"Cham","reference-count":47,"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_23","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T12:14:51Z","timestamp":1539000891000},"page":"385-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":119,"title":["Cross-Modal and Hierarchical Modeling of Video and Text"],"prefix":"10.1007","author":[{"given":"Bowen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hexiang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Sha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: ICCV, pp. 5804\u20135813 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: Vqa: Visual question answering. In: ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Chao, W.L., Hu, H., Sha, F.: Being negative but constructively: lessons learnt from creating better visual question answering datasets. In: NAACL-HLT, pp. 431\u2013441 (2018)","DOI":"10.18653\/v1\/N18-1040"},{"key":"23_CR4","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling (2014). arXiv preprint arXiv:1412.3555"},{"key":"23_CR5","unstructured":"Collell, G., Moens, M.F.: Is an image worth more than a thousand words? on the fine-grain semantic differences between visual and linguistic representations. In: COLING, pp. 2807\u20132817 (2016)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: CVPR, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"23_CR7","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Mikolov, T., et al.: Devise: a deep visual-semantic embedding model. In: NIPS, pp. 2121\u20132129 (2013)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR9","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, pp. 961\u2013970","DOI":"10.1109\/CVPR.2015.7298698"},{"issue":"8","key":"23_CR10","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":"23_CR11","doi-asserted-by":"crossref","unstructured":"Hu, H., Chao, W.L., Sha, F.: Learning answer embeddings for visual question answering. In: CVPR, pp. 5428\u20135436 (2018)","DOI":"10.1109\/CVPR.2018.00569"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"23_CR13","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, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"23_CR14","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et al.: The kinetics human action video dataset (2017). arXiv preprint arXiv:1705.06950"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Kiela, D., Bottou, L.: Learning Image Embeddings using Convolutional Neural Networks for Improved Multi-Modal Semantics. In: EMNLP, pp. 36\u201345 (2014)","DOI":"10.3115\/v1\/D14-1005"},{"key":"23_CR16","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models (2014). arXiv preprint arXiv:1411.2539"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: ICCV, pp. 706\u2013715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"23_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106\u20131114 (2012)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., Luong, M.T., Jurafsky, D.: A hierarchical neural autoencoder for paragraphs and documents. In: ACL, pp. 1106\u20131115 (2015)","DOI":"10.3115\/v1\/P15-1107"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Yao, T., Pan, Y., Chao, H., Mei, T.: Jointly localizing and describing events for dense video captioning. In: CVPR, pp. 7492\u20137500 (2018)","DOI":"10.1109\/CVPR.2018.00782"},{"key":"23_CR21","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Tsung-Yi Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context. In: ECCV, pp. 740\u2013755 (2014)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: EMNLP, pp. 1412\u20131421 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"23_CR23","first-page":"2579","volume":"9","author":"LVD Maaten","year":"2008","unstructured":"Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. JMLR 9, 2579\u20132605 (2008)","journal-title":"JMLR"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Niu, Z., Zhou, M., Wang, L., Gao, X., Hua, G.: Hierarchical multimodal lstm for dense visual-semantic embedding. In: ICCV, pp. 1899\u20131907 (2017)","DOI":"10.1109\/ICCV.2017.208"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Pan, P., Xu, Z., Yang, Y., Wu, F., Zhuang, Y.: Hierarchical recurrent neural encoder for video representation with application to captioning. In: CVPR, pp. 1029\u20131038 (2016)","DOI":"10.1109\/CVPR.2016.117"},{"key":"23_CR26","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: ICML, pp. 1310\u20131318 (2013)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Deep quantization: Encoding convolutional activations with deep generative model. In: CVPR, pp. 4085\u20134094 (2017)","DOI":"10.1109\/CVPR.2017.435"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: A unified embedding for face recognition and clustering. In: CVPR, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"23_CR30","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568\u2013576 (2014)"},{"key":"23_CR31","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: A dataset of 101 human actions classes from videos in the wild (2012). arXiv preprint arXiv:1212.0402"},{"key":"23_CR32","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS, pp. 3104\u20133112 (2014)"},{"key":"23_CR33","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"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Huang, L.K., Salakhutdinov, R.: Learning robust visual-semantic embeddings. In: ICCV, pp. 3591\u20133600 (2017)","DOI":"10.1109\/ICCV.2017.386"},{"key":"23_CR35","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, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"23_CR36","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, pp. 1494\u20131504 (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Temporal segment networks: Towards good practices for deep action recognition. In: ECCV, pp. 20\u201336 (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"23_CR39","unstructured":"Wang, L., et al.: Temporal segment networks for action recognition in videos (2017). arXiv preprint arXiv:1705.02953"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: CVPR, pp. 5005\u20135013 (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Zaheer, M., Hu, H., Manmatha, R., Smola, A.J., Kr\u00e4henb\u00fchl, P.: Compressed video action recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00631"},{"key":"23_CR42","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057 (2015)"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. In: CVPR, pp. 4584\u20134593 (2016)","DOI":"10.1109\/CVPR.2016.496"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with enhanced motion vector cnns. In: CVPR, pp. 2718\u20132726 (2016)","DOI":"10.1109\/CVPR.2016.297"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, K., Chao, W.L., Sha, F., Grauman, K.: Video summarization with long short-term memory. In: ECCV, pp. 766\u2013782 (2016)","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: ICCV, pp. 2933\u20132942 (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7w: Grounded question answering in images. In: CVPR, pp. 4995\u20135004 (2016)","DOI":"10.1109\/CVPR.2016.540"}],"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_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:58:54Z","timestamp":1775242734000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01261-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012601","9783030012618"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01261-8_23","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"}]}}