{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:44:56Z","timestamp":1729665896010,"version":"3.28.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1109\/dicta52665.2021.9647213","type":"proceedings-article","created":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T18:04:18Z","timestamp":1640282658000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Semantic Attribute Enriched Storytelling from a Sequence of Images"],"prefix":"10.1109","author":[{"given":"Zainy M.","family":"Malakan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ghulam Mubashar","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad A. A. K.","family":"Jalwana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nayyer","family":"Aafaq","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Glac net: Glocal attention cascading networks for multi-image cued story generation","author":"kim","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref38","first-page":"1993","article-title":"Ranking and retrieval of image sequences from multiple paragraph queries","author":"kim","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref33","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural IPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref37","first-page":"73","article-title":"Expressing an image stream with a sequence of natural sentences","author":"park","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33894-7_30"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref28","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref29","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref1","article-title":"Let your photos talk: Generating narrative paragraph for photo stream via bidirectional attention recurrent neural networks","author":"liu","year":"0","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref22","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-021-10438-5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394955"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350918"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6305"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-020-00543-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018465"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref13","article-title":"Empirical autopsy of deep video captioning frameworks","author":"nayyer","year":"2019","journal-title":"Preprint"},{"key":"ref14","article-title":"Show, reward and tell: Automatic generation of narrative paragraph from photo stream by adversarial training","author":"wang","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref15","first-page":"5356","article-title":"Knowl-edgeable storyteller: A commonsense-driven generative model for visual storytelling","author":"yang","year":"2019","journal-title":"IJCAI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1083"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"11 213","DOI":"10.1609\/aaai.v34i07.6780","article-title":"Hide-and-tell: learning to bridge photo streams for visual storytelling","volume":"34","author":"jung","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"journal-title":"Evolution of YOLO algorithm and YOLOv5 the state-of-the-art object detection algorithm","year":"2021","author":"thuan","key":"ref18"},{"key":"ref19","article-title":"Mogrifier lstm","author":"melis","year":"0","journal-title":"Proceedings of the ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988435"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref9","first-page":"1","article-title":"Sibnet: Sibling convolutional encoder for video captioning","author":"liu","year":"2020","journal-title":"IEEE Trans on Pattern Analysis and Machine Intelligence"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/NCCC49330.2021.9428808"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083769"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01606"},{"key":"ref42","first-page":"304","article-title":"A hierarchical approach for visual storytelling using image description","volume":"11869","author":"harrison","year":"2019","journal-title":"Interactive Storytelling 12th International Conference on Interactive Digital Storytelling ICIDS 2019"},{"journal-title":"Contextualise attend modulate and tell Visual storytelling","year":"2021","author":"malakan","key":"ref41"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"3022","DOI":"10.1609\/aaai.v35i4.16410","article-title":"Imagine, reason and write: Visual storytelling with graph knowledge and relational reasoning","volume":"35","author":"xu","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref43","article-title":"Commonsense knowledge aware concept selection for diverse and informative visual storytelling","author":"chen","year":"2021","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 Digital Image Computing: Techniques and Applications (DICTA)","start":{"date-parts":[[2021,11,29]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2021,12,1]]}},"container-title":["2021 Digital Image Computing: Techniques and Applications (DICTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9647036\/9647042\/09647213.pdf?arnumber=9647213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T03:54:28Z","timestamp":1674186868000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9647213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/dicta52665.2021.9647213","relation":{},"subject":[],"published":{"date-parts":[[2021,11]]}}}