{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:48:44Z","timestamp":1743133724221,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030007751"},{"type":"electronic","value":"9783030007768"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-030-00776-8_10","type":"book-chapter","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T08:14:58Z","timestamp":1537258498000},"page":"104-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Collaborative Detection and Caption Network"],"prefix":"10.1007","author":[{"given":"Tianyi","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jiang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"key":"10_CR1","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Zitnick, C.L.: Mind\u2019s eye: a recurrent visual representation for image caption generation, pp. 2422\u20132431 (2014)","DOI":"10.1109\/CVPR.2015.7298856"},{"issue":"11","key":"10_CR3","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1109\/TMM.2015.2477044","volume":"17","author":"K Cho","year":"2015","unstructured":"Cho, K., Courville, A., Bengio, Y.: Describing multimedia content using attention-based encoder-decoder networks. IEEE Trans. Multimed. 17(11), 1875\u20131886 (2015)","journal-title":"IEEE Trans. Multimed."},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: Language specific translation evaluation for any target language. In: The Workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"10_CR5","unstructured":"Du, T., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: C3d: generic features for video analysis. Eprint Arxiv (2014)"},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Fang, H., et al: From captions to visual concepts and back. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1473\u20131482 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298754","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"10_CR7","unstructured":"Flick, C.: ROUGE: a package for automatic evaluation of summaries. In: The Workshop on Text Summarization Branches Out, p. 10 (2004)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., et al.: YouTube2Text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: IEEE International Conference on Computer Vision, pp. 2712\u20132719 (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition, pp. 770\u2013778 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"10_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":"10_CR11","doi-asserted-by":"crossref","unstructured":"Kaufman, D., Levi, G., Hassner, T., Wolf, L.: Temporal tessellation: a unified approach for video analysis (2017). 2(9), II-II","DOI":"10.1109\/ICCV.2017.20"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics-Volume 1, pp. 423\u2013430. Association for Computational Linguistics (2003)","DOI":"10.3115\/1075096.1075150"},{"key":"10_CR13","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, no. 6, pp. 1029\u20131038 (2015)","DOI":"10.1109\/CVPR.2016.117"},{"key":"10_CR14","doi-asserted-by":"publisher","unstructured":"Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4594\u20134602, June 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.497","DOI":"10.1109\/CVPR.2016.497"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, H., Mei, T.: Video captioning with transferred semantic attributes (2016)","DOI":"10.1109\/CVPR.2017.111"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Meeting on Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"10_CR17","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: International Conference on Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., et al.: Movie description. Int. J. Comput. Vis. (2017). http:\/\/resources.mpi-inf.mpg.de\/publications\/D1\/2016\/2310198.pdf","DOI":"10.1007\/s11263-016-0987-1"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Song, J., Guo, Z., Gao, L., Liu, W., Zhang, D., Shen, H.T.: Hierarchical LSTM with adjusted temporal attention for video captioning (2017)","DOI":"10.24963\/ijcai.2017\/381"},{"key":"10_CR21","unstructured":"Torabi, A., Pal, C., Larochelle, H., Courville, A.: Using descriptive video services to create a large data source for video annotation research. Computer Science (2015)"},{"issue":"2","key":"10_CR22","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: Cider: consensus-based image description evaluation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence - video to text (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"10_CR25","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R.J., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. CoRR abs\/1412.4729 (2014). http:\/\/arxiv.org\/abs\/1412.4729"},{"key":"10_CR26","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Computer Science, pp. 2048\u20132057 (2015)"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Describing videos by exploiting temporal structure. In: IEEE International Conference on Computer Vision, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. In: Computer Vision and Pattern Recognition, pp. 4584\u20134593 (2016)","DOI":"10.1109\/CVPR.2016.496"},{"key":"10_CR30","unstructured":"Yu, Y., Ko, H., Choi, J., Kim, G.: Video captioning and retrieval models with semantic attention. arXiv preprint arXiv:1610.02947 (2016)"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing \u2013 PCM 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00776-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:21:49Z","timestamp":1710332509000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00776-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007751","9783030007768"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00776-8_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"19 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PCM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim Conference on Multimedia","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"21 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pcm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pcm2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}