{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T22:51:42Z","timestamp":1787871102151,"version":"build-2784847793"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176141, 62176139, 61876098"],"award-info":[{"award-number":["62176141, 62176139, 61876098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Basic Research Project of Natural Science Foundation of Shandong Province","award":["ZR2021ZD15"],"award-info":[{"award-number":["ZR2021ZD15"]}]},{"DOI":"10.13039\/501100010040","name":"Taishan Scholar Project of Shandong Province","doi-asserted-by":"publisher","award":["tsqn202103088"],"award-info":[{"award-number":["tsqn202103088"]}],"id":[{"id":"10.13039\/501100010040","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shandong Provincial Natural Science Foundation for Distinguished Young Scholars","award":["ZR2021JQ26,ZR2021QF119"],"award-info":[{"award-number":["ZR2021JQ26,ZR2021QF119"]}]},{"name":"special funds for distinguished professors of Shandong Jianzhu University"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16691-1","type":"journal-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T03:27:18Z","timestamp":1695180438000},"page":"32191-32212","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A survey of micro-video analysis"],"prefix":"10.1007","volume":"83","author":[{"given":"Jie","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuling","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Xi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiushan","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilong","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,9,20]]},"reference":[{"key":"16691_CR1","doi-asserted-by":"crossref","first-page":"4272","DOI":"10.1109\/CVPR.2014.544","volume-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"M Redi","year":"2014","unstructured":"Redi M, O\u2019Hare N, Schifanella R, Trevisiol M, Jaimes A (2014) 6 seconds of sound and vision: creativity in micro-videos. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 4272\u20134279"},{"key":"16691_CR2","unstructured":"Nguyen PX, Rogez G, Fowlkes C, Ramanan D (2016) The open world of micro-videos. arXiv preprint arXiv:1603.09439"},{"issue":"19","key":"16691_CR3","doi-asserted-by":"crossref","first-page":"20341","DOI":"10.1007\/s11042-017-4781-z","volume":"76","author":"L Huang","year":"2017","unstructured":"Huang L, Luo B (2017) Tag refinement of micro-videos by learning from multiple data sources[J]. Multimed Tools Appl 76(19):20341\u201320358","journal-title":"Multimed Tools Appl"},{"key":"16691_CR4","doi-asserted-by":"crossref","first-page":"5182","DOI":"10.1109\/ICIP.2014.7026049","volume-title":"2014 IEEE International Conference on Image Processing (ICIP)","author":"S Sano","year":"2014","unstructured":"Sano S, Yamasaki T, Aizawa K (2014) Degree of loop assessment in micro-video. In: 2014 IEEE International Conference on Image Processing (ICIP). IEEE, pp 5182\u20135186"},{"key":"16691_CR5","first-page":"898","volume-title":"2016 ACM international conference on Multimedia (ACM MM)","author":"J Chen","year":"2016","unstructured":"Chen J, Song X, Nie L, Wang X, Zhang H, Chua T-S (2016) Micro tells macro: predicting the popularity of micro-videos via a transductive model. In: 2016 ACM international conference on Multimedia (ACM MM). ACM, pp 898\u2013907"},{"key":"16691_CR6","first-page":"1454","volume-title":"2016 ACM international conference on Multimedia (ACM MM)","author":"J Chen","year":"2016","unstructured":"Chen J (2016) Multi-modal learning: Study on a large-scale micro-video data collection. In: 2016 ACM international conference on Multimedia (ACM MM). ACM, pp 1454\u20131458"},{"key":"16691_CR7","first-page":"1415","volume-title":"2016 ACM international conference on Multimedia (ACM MM)","author":"J Zhang","year":"2016","unstructured":"Zhang J, Nie L, Wang X, He X, Huang X, Chua T-S (2016) Shorter-is-better: Venue category estimation from micro-video. In: 2016 ACM international conference on Multimedia (ACM MM). ACM, pp 1415\u20131424"},{"key":"16691_CR8","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1145\/3123266.3123313","volume-title":"2017 ACM international conference on Multimedia (ACM MM)","author":"L Nie","year":"2017","unstructured":"Nie L, Wang X, Zhang J, He X, Zhang H, Hong R, Tian Q (2017) Enhancing micro-video understanding by harnessing external sounds. In: 2017 ACM international conference on Multimedia (ACM MM). ACM, pp 1192\u20131200"},{"key":"16691_CR9","first-page":"327","volume-title":"2018 International Conference on Multimedia Modeling (MMM)","author":"J Chen","year":"2018","unstructured":"Chen J, He X, Song X, Zhang H, Nie L, Chua T-S (2018) Venue prediction for social images by exploiting rich temporal patterns in LBSNs. In: 2018 International Conference on Multimedia Modeling (MMM). Springer, pp 327\u2013339"},{"key":"16691_CR10","doi-asserted-by":"crossref","first-page":"77091","DOI":"10.1109\/ACCESS.2019.2922430","volume":"7","author":"W Liu","year":"2019","unstructured":"Liu W, Huang X, Cao G, Zhang J, Song G, Yang L (2019) Joint learning of nnextvlad, cnn and context gating for micro-video venue classification[J]. IEEE Access 7:77091\u201377099","journal-title":"IEEE Access"},{"key":"16691_CR11","first-page":"1437","volume-title":"2017 ACM international conference on Multimedia (ACM MM)","author":"Y Wei","year":"2019","unstructured":"Wei Y, Wang X, Nie L, He X, Hong R, Chua T-S (2019) MMGCN: Multi-modal graph convolution network for personalized recommendation of micro-video. In: 2017 ACM international conference on Multimedia (ACM MM). ACM, pp 1437\u20131445"},{"key":"16691_CR12","first-page":"1446","volume-title":"2019 ACM international conference on Multimedia (ACM MM)","author":"Y Wei","year":"2019","unstructured":"Wei Y, Cheng Z, Yu X, Zhao Z, Zhu L, Nie L (2019) Personalized hashtag recommendation for micro-videos. In: 2019 ACM international conference on Multimedia (ACM MM). ACM, pp 1446\u20131454"},{"key":"16691_CR13","first-page":"1464","volume-title":"2019 ACM international conference on Multimedia (ACM MM)","author":"Y Li","year":"2019","unstructured":"Li Y, Liu M, Yin J, Cui C, Xu X-S, Nie L (2019) Routing micro-videos via a temporal graph-guided recommendation system. In: 2019 ACM international conference on Multimedia (ACM MM). ACM, pp 1464\u20131472"},{"key":"16691_CR14","first-page":"1","volume-title":"2016 IEEE\/ACIS International Conference on Computer and Information Science (ICIS)","author":"S Shang","year":"2016","unstructured":"Shang S, Shi M, Shang W, Hong Z (2016) A micro-video recommendation system based on big data. In: 2016 IEEE\/ACIS International Conference on Computer and Information Science (ICIS). IEEE, pp 1\u20135"},{"key":"16691_CR15","first-page":"564","volume-title":"2017 the Pacific Rim Conference on Multimedia (PCM)","author":"L Huang","year":"2017","unstructured":"Huang L, Luo B (2017) Personalized micro-video recommendation via hierarchical user interest modeling. In: 2017 the Pacific Rim Conference on Multimedia (PCM). Springer, pp 564\u2013574"},{"key":"16691_CR16","first-page":"198","volume-title":"2018 SIAM International Conference on Data Mining (SDM). SIAM","author":"J Ding","year":"2018","unstructured":"Ding J, Li Y, Li Y, Jin D (2018) Click versus share: A feature-driven study of micro-video popularity and virality in social media. In: 2018 SIAM International Conference on Data Mining (SDM). SIAM, pp 198\u2013206"},{"key":"16691_CR17","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1145\/3240508.3240617","volume-title":"2018 ACM international conference on Multimedia (ACM MM)","author":"X Chen","year":"2018","unstructured":"Chen X, Dong L, Zha Z-J, Zhou W, Xiong Z, Li Y (2018) Temporal hierarchical attention at category-and item-level for micro-video click-through prediction. In: 2018 ACM international conference on Multimedia (ACM MM). ACM, pp 1146\u20131153"},{"issue":"3","key":"16691_CR18","doi-asserted-by":"crossref","first-page":"2991","DOI":"10.1007\/s11042-017-4827-2","volume":"77","author":"J Ma","year":"2018","unstructured":"Ma J, Li G, Zhong M, Zhao X, Zhu L, Li X (2018) Lga: latent genre aware micro-video recommendation on social media[J]. Multimed Tools Appl 77(3):2991\u20133008","journal-title":"Multimed Tools Appl"},{"key":"16691_CR19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIP.2019.2923608","volume":"29","author":"Y Wei","year":"2019","unstructured":"Wei Y, Wang X, Guan W, Nie L, Lin Z, Chen B (2019) Neural multimodal cooperative learning toward micro-video understanding[J]. IEEE Trans Image Process 29:1\u201314","journal-title":"IEEE Trans Image Process"},{"key":"16691_CR20","first-page":"526","volume-title":"2016 IEEE International Conference on Computer and Communications (ICCC)","author":"Z Liu","year":"2016","unstructured":"Liu Z, Yang N, Cao S (2016) Sentiment-analysis of review text for micro-video. In: 2016 IEEE International Conference on Computer and Communications (ICCC). IEEE, pp 526\u2013530"},{"key":"16691_CR21","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1145\/3123266.3123341","volume-title":"2017 ACM international conference on Multimedia (ACM MM)","author":"M Liu","year":"2017","unstructured":"Liu M, Nie L, Wang M, Chen B (2017) Towards micro-video understanding by joint sequential-sparse modeling. In: 2017 ACM international conference on Multimedia (ACM MM). ACM, pp 970\u2013978"},{"issue":"8","key":"16691_CR22","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1109\/TKDE.2017.2785784","volume":"30","author":"P Jing","year":"2017","unstructured":"Jing P, Yuting S, Liqiang Nie X, Bai JL, Wang M (2017) Low-rank multi-view embedding learning for micro-video popularity prediction[J]. IEEE Trans Knowl Data Eng 30(8):1519\u20131532","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"16691_CR23","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1109\/TIP.2018.2875363","volume":"28","author":"M Liu","year":"2018","unstructured":"Liu M, Nie L, XiangWang QT, Chen B (2018) Online data organizer: micro-video categorization by structure-guided multimodal dictionary learning[J]. IEEE Trans Image Process 28(3):1235\u20131247","journal-title":"IEEE Trans Image Process"},{"key":"16691_CR24","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.ins.2021.07.021","volume":"575","author":"S Yuting","year":"2021","unstructured":"Yuting S, Junyu X, Hong D, Fan F, Zhang J, Jing P (2021) Deep low-rank matrix factorization with latent correlation estimation for micro-video multi-label classification[J]. Inf Sci 575:587\u2013598","journal-title":"Inf Sci"},{"key":"16691_CR25","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1109\/TMM.2020.2978618","volume":"23","author":"X Chen","year":"2021","unstructured":"Chen X, Liu D, Xiong Z, Zha Z-J (2021) Learning and fusing multiple user interest representations for Micro-video and movie recommendations[J]. IEEE Trans Multimed 23:484\u2013496","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"16691_CR26","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s11280-020-00858-z","volume":"24","author":"Y Han","year":"2021","unstructured":"Han Y, Pan G, Gao W, Guandong X, Jian W (2021) Aspect-level sentiment capsule network for micro-video click-through rate prediction[J]. World Wide Web 24(4):1045\u20131064","journal-title":"World Wide Web"},{"key":"16691_CR27","first-page":"15945","volume-title":"2021 AAAI Conference on Artificial Intelligence (AAAI)","author":"Y Dong","year":"2021","unstructured":"Dong Y, Zhang S, Zhao Z, Fan W, Zhu J, He X, Fei W (2021) Modeling high-order interactions across multi-interests for micro-video recommendation (Student abstract). In: 2021 AAAI Conference on Artificial Intelligence (AAAI). AAAI, pp 15945\u201315946"},{"key":"16691_CR28","first-page":"4721","volume-title":"2021 ACM International Conference on Information and Knowledge Management (CIKM)","author":"L He","year":"2021","unstructured":"He L, Wang D, Wang H, Chen H, Guandong X (2021) TagPick: A system for bridging micro-video hashtags and e-commerce categories. In: 2021 ACM International Conference on Information and Knowledge Management (CIKM). ACM, pp 4721\u20134724"},{"key":"16691_CR29","first-page":"1099","volume-title":"2021 ACM International Conference on Information and Knowledge Management (CIKM)","author":"Y Liu","year":"2021","unstructured":"Liu Y, Liu Q, Yu T, Wang C, Niu Y, Yang S, Li C (2021) Concept-aware denoising graph neural network for micro-video recommendation. In: 2021 ACM International Conference on Information and Knowledge Management (CIKM). ACM, pp 1099\u20131108"},{"key":"16691_CR30","first-page":"3161","volume":"2021","author":"C Lei","year":"2021","unstructured":"Lei C, Liu Y, Zhang L, Wang G, Tang H, Li H, Miao C (2021) SEMI: a sequential multi-modal information transfer network for E-commerce Micro-video recommendations. In Proceedings of ACM SIGKDD conference 2021:3161\u20133171","journal-title":"In Proceedings of ACM SIGKDD conference"},{"key":"16691_CR31","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1109\/TMM.2021.3128254","volume":"25","author":"J Yi","year":"2021","unstructured":"Yi J, Zhu Y, Xie J, Chen Z (2021) Cross-modal variational auto-encoder for content-based Micro-video background music recommendation [J]. IEEE Trans Multimed 25:515\u2013528","journal-title":"IEEE Trans Multimed"},{"key":"16691_CR32","unstructured":"Lu Y, Huang Y, Zhang S, Han W, Chen H, Zhao Z, Wu F (2021) Multi-trends enhanced dynamic micro-video recommendation. arXiv:2110.03902v1"},{"key":"16691_CR33","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.ins.2020.05.064","volume":"543","author":"J Guo","year":"2021","unstructured":"Guo J, Nie X, Ma Y, Shaheed K, Ullah I, Yin Y (2021) Attention based consistent semantic learning for micro-video scene recognition [J]. Inf Sci 543:504\u2013516","journal-title":"Inf Sci"},{"key":"16691_CR34","doi-asserted-by":"crossref","first-page":"29518","DOI":"10.1109\/ACCESS.2020.2973240","volume":"8","author":"J Guo","year":"2020","unstructured":"Guo J, Nie X, Yin Y (2020) Mutual complementarity: multi-modal enhancement semantic learning for micro-video scene recognition [J]. IEEE Access 8:29518\u201329524","journal-title":"IEEE Access"},{"key":"16691_CR35","doi-asserted-by":"crossref","first-page":"78252","DOI":"10.1109\/ACCESS.2020.2989473","volume":"8","author":"C Yang","year":"2020","unstructured":"Yang C, Wang X, Jiang B (2020) Sentiment enhanced multi-modal hashtag recommendation for Micro-videos[J]. IEEE Access 8:78252\u201378264","journal-title":"IEEE Access"},{"key":"16691_CR36","doi-asserted-by":"crossref","first-page":"87266","DOI":"10.1109\/ACCESS.2020.2992436","volume":"8","author":"J Zhang","year":"2020","unstructured":"Zhang J, Yuting W, Liu J, Jing P, Yuting S (2020) Low-rank regularized multimodal representation for Micro-video event detection[J]. IEEE Access 8:87266\u201387274","journal-title":"IEEE Access"},{"key":"16691_CR37","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.neucom.2020.05.026","volume":"410","author":"G Xiaowei","year":"2020","unstructured":"Xiaowei G, Lu L, Qiu S, Zou Q, Yang Z (2020) Sentiment key frame extraction in user-generated micro-videos via low-rank and sparse representation[J]. Neurocomputing 410:441\u2013453","journal-title":"Neurocomputing"},{"key":"16691_CR38","doi-asserted-by":"crossref","first-page":"106114","DOI":"10.1016\/j.knosys.2020.106114","volume":"203","author":"D Cao","year":"2020","unstructured":"Cao D, Miao L, Rong H, Qin Z (2020) Liqiang Nie: hashtag our stories: hashtag recommendation for micro-videos via harnessing multiple modalities. Knowl [J] Based Syst 203:106114","journal-title":"Knowl [J] Based Syst"},{"issue":"5","key":"16691_CR39","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1007\/s00530-020-00660-x","volume":"26","author":"S Yuting","year":"2020","unstructured":"Yuting S, Yang Li X, Bai PJ (2020) Predicting the popularity of micro-videos via a feature-discrimination transductive model[J]. Multimed Syst 26(5):519\u2013534","journal-title":"Multimed Syst"},{"issue":"9-10","key":"16691_CR40","doi-asserted-by":"crossref","first-page":"6709","DOI":"10.1007\/s11042-019-08147-2","volume":"79","author":"W Liu","year":"2020","unstructured":"Liu W, Huang X, Cao G, Zhang J, Song G, Yang L (2020) Multi-modal sequence model with gated fully convolutional blocks for micro-video venue classification[J]. Multimed Tools Appl 79(9-10):6709\u20136726","journal-title":"Multimed Tools Appl"},{"key":"16691_CR41","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1109\/LSP.2020.2983831","volume":"27","author":"S Yuting","year":"2020","unstructured":"Yuting S, Hong D, Li Y, Jing P (2020) Low-rank regularized deep collaborative matrix factorization for Micro-video multi-label classification[J]. IEEE Signal Process Lett 27:740\u2013744","journal-title":"IEEE Signal Process Lett"},{"key":"16691_CR42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIP.2019.2923608","volume":"29","author":"Y Wei","year":"2020","unstructured":"Wei Y, Wang X, Guan W, Nie L, Lin Z, Chen B (2020) Neural multimodal cooperative learning toward Micro-video understanding[J]. IEEE Trans Image Process 29:1\u201314","journal-title":"IEEE Trans Image Process"},{"key":"16691_CR43","doi-asserted-by":"crossref","unstructured":"Liu S, Xie J, Zou C, Chen Z (2020) User conditional hashtag recommendation for Micro-videos. In Proceedings of IEEE International Conference on Multimedia and Expo. 1-6","DOI":"10.1109\/ICME46284.2020.9102824"},{"key":"16691_CR44","doi-asserted-by":"crossref","unstructured":"Hao Jiang, Wenjie Wang, Yinwei Wei, Zan Gao, Yinglong Wang, Liqiang Nie (2020 ) What aspect do you like: multi-scale time-aware user interest modeling for Micro-video recommendation. In Proceedings of ACM Conference on Multimedia 3487-3495","DOI":"10.1145\/3394171.3413653"},{"key":"16691_CR45","first-page":"2542","volume-title":"2020 International World Wide Web Conferences (WWW)","author":"J Xie","year":"2020","unstructured":"Xie J, Zhu Y, Zhang Z, Peng J, Yi J, Hu Y, Liu H, Chen Z (2020) A multimodal variational encoder-decoder framework for micro-video popularity prediction. In: 2020 International World Wide Web Conferences (WWW). W3C, pp 2542\u20132548"},{"key":"16691_CR46","unstructured":"Zhu Y, Xie J, Chen Z (2003) Predicting the popularity of micro-videos with multimodal variational encoder-decoder framework. arXiv:2003:12724v1"},{"key":"16691_CR47","doi-asserted-by":"crossref","unstructured":"Nie L, Liu M, Song X (2019) Multimodal learning toward micro-video understanding [M], San Rafael","DOI":"10.1007\/978-3-031-02255-5"},{"issue":"3","key":"16691_CR48","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1007\/s41019-019-00101-4","volume":"4","author":"J Ma","year":"2019","unstructured":"Ma J, Wen J, Zhong M, Chen W, Li X (2019) MMM: multi-source multi-net Micro-video recommendation with clustered hidden item representation learning[J]. Data Sci Eng 4(3):240\u2013253","journal-title":"Data Sci Eng"},{"issue":"17","key":"16691_CR49","doi-asserted-by":"crossref","first-page":"24539","DOI":"10.1007\/s11042-018-6999-9","volume":"78","author":"J Guo","year":"2019","unstructured":"Guo J, Nie X, Jian M, Yin Y (2019) binary feature representation learning for scene retrieval in micro-video. Multimed Tools Appl 78(17):24539\u201324552","journal-title":"Multimed Tools Appl"},{"key":"16691_CR50","doi-asserted-by":"crossref","unstructured":"Li M, Gan T, Liu M, Cheng Z, Yin J, Nie L (2019) Long-tail Hashtag Recommendation for Micro-videos with Graph Convolutional Network. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 509-518","DOI":"10.1145\/3357384.3357912"},{"key":"16691_CR51","doi-asserted-by":"crossref","unstructured":"Ma J, Wen J, Zhong M, Chen W, Zhou X, Indulska J (2019) Multi-source Multi-net Micro-video Recommendation with Hidden Item Category Discovery. In Proceedings of the 24th International Conference on Database Systems for Advanced Applications, 384-400","DOI":"10.1007\/978-3-030-18579-4_23"},{"key":"16691_CR52","first-page":"607","volume-title":"2019 International Conference on Image and Graphics (ICIG)","author":"Y Jin","year":"2019","unstructured":"Jin Y, Xu J, He X (2019) Personalized micro-video recommendation based on multi-modal features and user interest evolution. In: 2019 International Conference on Image and Graphics (ICIG). SPIE, pp 607\u2013618"},{"key":"16691_CR53","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1109\/ICME.2019.00086","volume-title":"2019 IEEE International Conference on Multimedia and Expo (ICME)","author":"S Liu","year":"2019","unstructured":"Liu S, Chen Z (2019) Sequential behavior modeling for next micro-video recommendation with collaborative transformer. In: 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE, pp 460\u2013465"},{"key":"16691_CR54","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1109\/ICME.2019.00088","volume-title":"2019 IEEE International Conference on Multimedia and Expo (ICME)","author":"S Ma","year":"2019","unstructured":"Ma S, Zha Z-J Wu F (2019) Knowing user better: jointly predicting click-through and playtime for micro-video. In: 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE, pp 472\u2013477"},{"key":"16691_CR55","first-page":"371","volume-title":"2019 International Conference on Knowledge Science, Engineering and Management (KSEM)","author":"J Chen","year":"2019","unstructured":"Chen J, Peng J, Qi L, Chen G, Zhang W (2019) Implicit rating methods based on interest preferences of categories for micro-video recommendation. In: 2019 International Conference on Knowledge Science, Engineering and Management (KSEM). Springer, pp 371\u2013381"},{"key":"16691_CR56","doi-asserted-by":"crossref","first-page":"3020","DOI":"10.1145\/3308558.3313513","volume-title":"2019 World Wide Web Conferences (WWW)","author":"S Liu","year":"2019","unstructured":"Liu S, Chen Z, Liu H, Hu X (2019) User-video co-attention network for personalized micro-video recommendation. In: 2019 World Wide Web Conferences (WWW). W3C, pp 3020\u20133026"},{"key":"16691_CR57","first-page":"721","volume-title":"2018 Pacific Rim Conference on Multimedia (PCM)","author":"J Guo","year":"2018","unstructured":"Guo J, Nie X, Cui C, Xi X, Ma Y, Yin Y (2018) Getting more from one attractive scene: venue retrieval in micro-videos. In: 2018 Pacific Rim Conference on Multimedia (PCM). Springer, pp 721\u2013733"},{"key":"16691_CR58","first-page":"705","volume-title":"2018 Pacific Rim Conference on Multimedia (PCM)","author":"W Liu","year":"2018","unstructured":"Liu W, Huang X, Cao G, Song G, Yang L (2018) Joint learning of LSTMs-CNN and prototype for micro-video venue classification. In: 2018 Pacific Rim Conference on Multimedia (PCM). Springer, pp 705\u2013715"},{"key":"16691_CR59","first-page":"73","volume-title":"2014 AAAI Conference on Artificial Intelligence (AAAI)","author":"Y Jiang","year":"2014","unstructured":"Jiang Y, Xu B, Xue X (2014) Predicting emotions in user-generated videos. In: 2014 AAAI Conference on Artificial Intelligence (AAAI). AAAI, pp 73\u201379"},{"issue":"2","key":"16691_CR60","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks [J]. Adv Neural Inf Proces Syst 25(2):1097\u20131105","journal-title":"Adv Neural Inf Proces Syst"},{"key":"16691_CR61","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/978-3-642-24797-2_4","volume-title":"Supervised sequence labelling with recurrent neural networks","author":"A Graves","year":"2012","unstructured":"Graves A, Graves A (2012) Long short-term memory [J]. In: Supervised sequence labelling with recurrent neural networks, 4th edn. Springer-Verlag, Berlin Heidelberg, pp 37\u201345","edition":"4"},{"key":"16691_CR62","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556"},{"key":"16691_CR63","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al. (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on Computer Vision & Pattern Recognition (CVPR). IEEE, pp 770-778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3","key":"16691_CR64","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3233\/JIFS-213191","volume":"43","author":"B Wang","year":"2022","unstructured":"Wang B, Huang X, Cao G et al (2022) Hybrid-attention and frame difference enhanced network for micro-video venue recognition [J]. J Intell Fuzzy Syst 43(3):3337\u20133353","journal-title":"J Intell Fuzzy Syst"},{"key":"16691_CR65","volume":"102","author":"B Wang","year":"2022","unstructured":"Wang B, Huang X, Cao G et al (2022) Attention-enhanced and trusted multimodal learning for micro-video venue recognition [J]. Comput Electr Eng 102:108127","journal-title":"Comput Electr Eng"},{"key":"16691_CR66","doi-asserted-by":"crossref","first-page":"114219","DOI":"10.1016\/j.eswa.2020.114219","volume":"168","author":"M Jian","year":"2021","unstructured":"Jian M, Wang J, Yu H et al (2021) Visual saliency detection by integrating spatial position prior of object with background cues[J]. Expert Syst Appl 168:114219","journal-title":"Expert Syst Appl"},{"key":"16691_CR67","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1016\/j.ins.2021.08.069","volume":"576","author":"M Jian","year":"2021","unstructured":"Jian M, Wang J, Yu H et al (2021) Integrating object proposal with attention networks for video saliency detection[J]. Inf Sci 576:819\u2013830","journal-title":"Inf Sci"},{"issue":"5","key":"16691_CR68","doi-asserted-by":"crossref","first-page":"1689","DOI":"10.1007\/s00530-022-00940-8","volume":"28","author":"X Lu","year":"2022","unstructured":"Lu X, Jian M, Wang X et al (2022) Visual saliency detection via combining center prior and U-net[J]. Multimedia Systems 28(5):1689\u20131698","journal-title":"Multimedia Systems"},{"key":"16691_CR69","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jvcir.2018.10.008","volume":"57","author":"M Jian","year":"2018","unstructured":"Jian M, Zhang W, Yu H et al (2018) Saliency detection based on directional patches extraction and principal local color contrast[J]. J Vis Commun Image Represent 57:1\u201311","journal-title":"J Vis Commun Image Represent"},{"key":"16691_CR70","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.neucom.2022.02.083","volume":"488","author":"W Wan","year":"2022","unstructured":"Wan W, Wang J, Zhang Y, Li J, Hui Y, Sun J (2022) A comprehensive survey on robust image watermarking. Neurocomputing 488:226\u2013247","journal-title":"Neurocomputing"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16691-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16691-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16691-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T06:53:04Z","timestamp":1709880784000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16691-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,20]]},"references-count":70,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["16691"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16691-1","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,20]]},"assertion":[{"value":"10 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}}]}}