{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T01:52:08Z","timestamp":1781833928213,"version":"3.54.5"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030007669","type":"print"},{"value":"9783030007676","type":"electronic"}],"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\/978-3-030-00767-6_32","type":"book-chapter","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T07:54:58Z","timestamp":1537257298000},"page":"340-350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["VAL: Visual-Attention Action Localizer"],"prefix":"10.1007","author":[{"given":"Xiaomeng","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yahong","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: ICCV, pp. 5277\u20135285 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Yang, Z.W., Han, Y.H., Wang, Z.: Catching the temporal regions-of-interest for video captioning. In: ACM MM, pp. 146\u2013153 (2017)","DOI":"10.1145\/3123266.3123327"},{"issue":"3","key":"32_CR4","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.1109\/TIP.2016.2514499","volume":"25","author":"Richang Hong","year":"2016","unstructured":"Hong, R., Zhang, L., Tao, D.: Unified photo enhancement by discovering aesthetic communities from Flickr. In: IEEE Transactions on Image Processing, pp. 1124\u20131135 (2016)","journal-title":"IEEE Transactions on Image Processing"},{"key":"32_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Wang, B., Xu, Y.J., Han, Y.H., Hong, R.C.: Movie question answering: remembering the textual cues for layered visual contents. In: AAAI. (2018)","DOI":"10.1609\/aaai.v32i1.12253"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: CVPR, pp. 1049\u20131058 (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: CVPR, pp. 6298\u20136306 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Du, T., 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":"32_CR10","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":"32_CR11","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1162\/tacl_a_00207","volume":"1","author":"M Regneri","year":"2013","unstructured":"Regneri, M., Rohrbach, M., Dominikus, W., Thater, S.: Grounding action descriptions in videos. TACL 1, 25\u201336 (2013)","journal-title":"TACL"},{"issue":"12","key":"32_CR12","doi-asserted-by":"publisher","first-page":"5814","DOI":"10.1109\/TIP.2016.2614132","volume":"25","author":"Richang Hong","year":"2016","unstructured":"Hong, R., Hu, Z., Wang, R., Wang, M., Tao, D.: Multi-view object retrieval via multi-scale topic models. In: IEEE Transactions on Image Processing, pp. 5814\u20135827 (2016)","journal-title":"IEEE Transactions on Image Processing"},{"key":"32_CR13","unstructured":"Kiros, R., et al.: Skip-thought vectors. In: NIPS, pp. 3294\u20133302 (2015)"},{"key":"32_CR14","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 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"32_CR15","doi-asserted-by":"publisher","first-page":"1555","DOI":"10.1109\/TMM.2016.2567071","volume":"18","author":"R Hong","year":"2016","unstructured":"Hong, R., Zhang, L., Zhang, C., Zimmermann, R.: Flickr circles: aesthetic tendency discovery by multi-view regularized topic modeling. IEEE Trans. Multimedia 18, 1555\u20131567 (2016)","journal-title":"IEEE Trans. Multimedia"},{"key":"32_CR16","doi-asserted-by":"publisher","first-page":"4933","DOI":"10.1109\/TIP.2018.2846664","volume":"27","author":"YJ Xu","year":"2018","unstructured":"Xu, Y.J., Han, Y.H., Hong, R.C., Tian, Q.: Sequential video VLAD: training the aggregation locally and temporally. IEEE Trans. Image Process. 27, 4933\u20134944 (2018)","journal-title":"IEEE Trans. Image Process."}],"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\/978-3-030-00767-6_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T18:24:37Z","timestamp":1751912677000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00767-6_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007669","9783030007676"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00767-6_32","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":"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"}}]}}