{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:28:06Z","timestamp":1740122886396,"version":"3.37.3"},"reference-count":83,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,11,11]],"date-time":"2021-11-11T00:00:00Z","timestamp":1636588800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,11,11]],"date-time":"2021-11-11T00:00:00Z","timestamp":1636588800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s11042-021-11634-0","type":"journal-article","created":{"date-parts":[[2021,11,11]],"date-time":"2021-11-11T07:04:53Z","timestamp":1636614293000},"page":"2979-3003","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["User-centric multimodal feature extraction for personalized retrieval of tumblr posts"],"prefix":"10.1007","volume":"81","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3217-3662","authenticated-orcid":false,"given":"Kazuma","family":"Ohtomo","sequence":"first","affiliation":[]},{"given":"Ryosuke","family":"Harakawa","sequence":"additional","affiliation":[]},{"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[]},{"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[]},{"given":"Masahiro","family":"Iwahashi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,11,11]]},"reference":[{"key":"11634_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed A, Jalal A, Kim K (2020) Rgb-d images for object segmentation, localization and recognition in indoor scenes using feature descriptor and hough voting. In: 2020 17th international Bhurban conference on applied sciences and technology (IBCAST), pp 290\u2013295","DOI":"10.1109\/IBCAST47879.2020.9044545"},{"key":"11634_CR2","doi-asserted-by":"crossref","unstructured":"Ai Q, Zhang Y, Bi K, Chen X, Croft WB (2017) Learning a hierarchical embedding model for personalized product search. In: Proc. international ACM SIGIR conf. research and development in information retrieval, pp 645\u2013654","DOI":"10.1145\/3077136.3080813"},{"key":"11634_CR3","doi-asserted-by":"crossref","unstructured":"Alam F, Imran M, Ofli F (2017) Image4act: Online social media image processing for disaster response. In: Proc. conf. advances in social networks analysis and mining 2017, pp 601\u2013604","DOI":"10.1145\/3110025.3110164"},{"key":"11634_CR4","doi-asserted-by":"crossref","unstructured":"Almatarneh S, Gamallo P, Pena FJR (2019) CiTIUS-COLE at semeval-2019 task 5: Combining linguistic features to identify hate speech against immigrants and women on multilingual tweets. In: Proc. workshop on semantic evaluation, pp 387\u2013390","DOI":"10.18653\/v1\/S19-2068"},{"key":"11634_CR5","doi-asserted-by":"crossref","unstructured":"Badar ud din Tahir S, Jalal A, Batool M (2020) Wearable sensors for activity analysis using smo-based random forest over smart home and sports datasets. In: 2020 3rd International conference on advancements in computational sciences (ICACS), pp 1\u20136","DOI":"10.1109\/ICACS47775.2020.9055944"},{"issue":"1","key":"11634_CR6","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1145\/2674026.2674030","volume":"16","author":"Y Chang","year":"2014","unstructured":"Chang Y, Tang L, Inagaki Y, Liu Y (2014) What is Tumblr: A statistical overview and comparison. SIGKDD Explor. Newsl. 16(1):21\u201329","journal-title":"SIGKDD Explor. Newsl."},{"key":"11634_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y, Wang N, Zhang Z (2018) Darkrank: Accelerating deep metric learning via cross sample similarities transfer. In: Thirty-second AAAI conf. artificial intelligence","DOI":"10.1609\/aaai.v32i1.11783"},{"key":"11634_CR8","doi-asserted-by":"crossref","unstructured":"Cheng Z, Jialie, S, Hoi SC (2016) On effective personalized music retrieval by exploring online user behaviors. In: Proc. international ACM SIGIR conf. on research and development in information Retrieval, pp 125\u2013134","DOI":"10.1145\/2911451.2911491"},{"key":"11634_CR9","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"11634_CR10","unstructured":"Farooq A, Jalal A, Kamal S (2015) Dense rgb-d map-based human tracking and activity recognition using skin joints features and self-organizing map. KSII transactions on internet and information systems (TIIS) 5, 5"},{"key":"11634_CR11","doi-asserted-by":"crossref","unstructured":"Ge W (2018) Deep metric learning with hierarchical triplet loss. In: Proc. european conf. computer vision (ECCV), pp 269\u2013285","DOI":"10.1007\/978-3-030-01231-1_17"},{"key":"11634_CR12","doi-asserted-by":"crossref","unstructured":"Gordo A, Almaz\u00e1n J, Revaud J, Larlus D (2016) Deep image retrieval: Learning global representations for image search. In: Proc. european conf. computer vision\u00a0(ECCV). Springer, pp 241\u2013257","DOI":"10.1007\/978-3-319-46466-4_15"},{"issue":"1","key":"11634_CR13","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3169\/mta.4.49","volume":"4","author":"R Harakawa","year":"2016","unstructured":"Harakawa R, Ogawa T, Haseyama M (2016) Accurate and efficient extraction of hierarchical structure of web communities for web video retrieval. ITE Trans. Media Technology and Applications 4(1):49\u201359","journal-title":"ITE Trans. Media Technology and Applications"},{"issue":"14","key":"11634_CR14","doi-asserted-by":"publisher","first-page":"18741","DOI":"10.1007\/s11042-018-5876-x","volume":"77","author":"R Harakawa","year":"2018","unstructured":"Harakawa R, Takehara D, Ogawa T, Haseyama M (2018) Sentiment-aware personalized tweet recommendation through multimodal FFM. Multimedia Tools and Applications 77(14):18741\u201318759","journal-title":"Multimedia Tools and Applications"},{"key":"11634_CR15","doi-asserted-by":"publisher","first-page":"116207","DOI":"10.1109\/ACCESS.2019.2936404","volume":"7","author":"R Harakawa","year":"2019","unstructured":"Harakawa R, Takimura S, Ogawa T, Haseyama M, Iwahashi M (2019) Consensus clustering of tweet networks via semantic and sentiment similarity estimation. IEEE Access 7:116207\u2013116217","journal-title":"IEEE Access"},{"key":"11634_CR16","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun, J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conf. computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"10","key":"11634_CR17","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1145\/1562764.1562800","volume":"52","author":"N Hu","year":"2009","unstructured":"Hu N, Zhang J, Pavlou PA (2009) Overcoming the j-shaped distribution of product reviews. Commun. ACM 52(10):144\u2013147","journal-title":"Commun. ACM"},{"key":"11634_CR18","doi-asserted-by":"crossref","unstructured":"Jalal A, Kamal S, Kim D (2014) Depth map-based human activity tracking and recognition using body joints features and self-organized map. In: Fifth international conference on computing, communications and networking technologies (ICCCNT), pp 1\u20136","DOI":"10.1109\/ICCCNT.2014.6963013"},{"issue":"7","key":"11634_CR19","doi-asserted-by":"publisher","first-page":"11735","DOI":"10.3390\/s140711735","volume":"14","author":"A Jalal","year":"2014","unstructured":"Jalal A, Kamal S, Kim D (2014) A depth video sensor-based life-logging human activity recognition system for elderly care in smart indoor environments. Sensors 14(7):11735\u201311759","journal-title":"Sensors"},{"key":"11634_CR20","doi-asserted-by":"crossref","unstructured":"Jalal A, Kamal S, Kim, D (2015) Depth silhouettes context: A new robust feature for human tracking and activity recognition based on embedded hmms. In: 2015 12th International conference on ubiquitous robots and ambient intelligence (URAI), pp 294\u2013299","DOI":"10.1109\/URAI.2015.7358957"},{"key":"11634_CR21","doi-asserted-by":"crossref","unstructured":"Jalal A, Kamal S, Kim, D (2015) Shape and motion features approach for activity tracking and recognition from kinect video camera. In: 2015 IEEE 29th International conference on advanced information networking and applications workshops, pp 445\u2013450","DOI":"10.1109\/WAINA.2015.38"},{"key":"11634_CR22","doi-asserted-by":"publisher","first-page":"8087545","DOI":"10.1155\/2016\/8087545","volume":"2016","author":"A Jalal","year":"2016","unstructured":"Jalal A, Kamal S, Kim D (2016) Human Depth Sensors-Based Activity Recognition Using Spatiotemporal Features and Hidden Markov Model for Smart Environments. Journal of Computer Networks and Communications 2016:8087545","journal-title":"Journal of Computer Networks and Communications"},{"key":"11634_CR23","unstructured":"Jalal A, Kim J, Kim, T-H (2012) Development of a life logging system via depth imaging-based human activity recognition for smart homes. Proceedings of the international symposium on sustainable healthy buildings, pp 91\u201395"},{"key":"11634_CR24","doi-asserted-by":"crossref","unstructured":"Jalal A, Kim Y (2014) Dense depth maps-based human pose tracking and recognition in dynamic scenes using ridge data. In: 2014 11th IEEE international conference on advanced video and signal based surveillance (AVSS), pp 19\u2013124","DOI":"10.1109\/AVSS.2014.6918654"},{"key":"11634_CR25","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/j.patcog.2016.08.003","volume":"61","author":"A Jalal","year":"2017","unstructured":"Jalal A, Kim Y-H, Kim Y-J, Kamal S, Kim D (2017) Robust human activity recognition from depth video using spatiotemporal multi-fused features. Pattern Recognition 61:295\u2013308","journal-title":"Pattern Recognition"},{"issue":"4","key":"11634_CR26","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1007\/s42835-019-00187-w","volume":"14","author":"A Jalal","year":"2019","unstructured":"Jalal A, Quaid MAK, Kim K (2019) A Wrist Worn Acceleration Based Human Motion Analysis and Classification for Ambient Smart Home System. Journal of Electrical Engineering & Technology 14(4):1733\u20131739","journal-title":"Journal of Electrical Engineering & Technology"},{"key":"11634_CR27","doi-asserted-by":"crossref","unstructured":"Jalal A, Sharif N, Kim J, Kim T-S (2013) Human activity recognition via recognized body parts of human depth silhouettes for residents monitoring services at smart home. Indoor and built environment 22 , pp 271\u2013279","DOI":"10.1177\/1420326X12469714"},{"key":"11634_CR28","doi-asserted-by":"crossref","unstructured":"Jin Z, Cao J, Guo H, Zhang Y, Wang Y, Luo, J (2017) Detection and analysis of 2016 US presidential election related rumors on Twitter. In: Proc. conf. SBP-BRiMS. Springer, pp 14\u201324","DOI":"10.1007\/978-3-319-60240-0_2"},{"issue":"3","key":"11634_CR29","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1007\/s13369-015-1955-8","volume":"41","author":"S Kamal","year":"2016","unstructured":"Kamal S, Jalal A (2016) A Hybrid Feature Extraction Approach for Human Detection, Tracking and Activity Recognition Using Depth Sensors. Arabian Journal for Science and Engineering 41(3):1043\u20131051","journal-title":"Arabian Journal for Science and Engineering"},{"key":"11634_CR30","doi-asserted-by":"crossref","unstructured":"Kamal S, Jalal A, Kim D (2016) Depth images-based human detection, tracking and activity recognition using spatiotemporal features and modified hmm. J Electric Eng Technol 6. https:\/\/doi.org\/10.5370\/JEET.2016.11.6.1857","DOI":"10.5370\/JEET.2016.11.6.1857"},{"issue":"9","key":"11634_CR31","doi-asserted-by":"publisher","first-page":"1066:1","DOI":"10.3390\/sym11091066","volume":"11","author":"M Kaya","year":"2019","unstructured":"Kaya M, Bilge H (2019) Deep metric learning: A survey. Symmetry 11(9):1066:1-1066:26","journal-title":"Symmetry"},{"key":"11634_CR32","doi-asserted-by":"crossref","unstructured":"Khalid S, Khalil T, Nasreen S (2014) A survey of feature selection and feature extraction techniques in machine learning. In: 2014 Science and information conference, pp 372\u2013378","DOI":"10.1109\/SAI.2014.6918213"},{"issue":"6","key":"11634_CR33","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.1007\/s42835-019-00278-8","volume":"14","author":"K Kim","year":"2019","unstructured":"Kim K, Jalal A, Mahmood M (2019) Vision-Based Human Activity Recognition System Using Depth Silhouettes: A Smart Home System for Monitoring the Residents. Journal of Electrical Engineering & Technology 14(6):2567\u20132573","journal-title":"Journal of Electrical Engineering & Technology"},{"key":"11634_CR34","doi-asserted-by":"crossref","unstructured":"Kim W, Goyal B, Chawla K, Lee J, Kwon, K (2018) Attention-based ensemble for deep metric learning. In: Proc. european conf. computer vision (ECCV), pp 736\u2013751","DOI":"10.1007\/978-3-030-01246-5_45"},{"key":"11634_CR35","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv:1412.6980"},{"key":"11634_CR36","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv:1312.6114"},{"key":"11634_CR37","unstructured":"Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: Proc. conf. machine learning, pp 1188\u20131196"},{"key":"11634_CR38","doi-asserted-by":"crossref","unstructured":"Lee J, Abu-El-Haija S, Varadarajan B, Natsev A (2018) Collaborative deep metric learning for video understanding. In: Proc. ACM special interest group on knowledge discovery in data\u00a0(SIGKDD), pp 481\u2013490","DOI":"10.1145\/3219819.3219856"},{"key":"11634_CR39","unstructured":"Li W, Zhang Y, Sun Y, Wang W, Li M, Zhang W, Lin, X (2019) Approximate nearest neighbor search on high dimensional data-experiments, analyses, and improvement. IEEE Trans Knowl Data Eng :1\u201314"},{"key":"11634_CR40","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.patcog.2017.02.032","volume":"75","author":"J Liang","year":"2018","unstructured":"Liang J, Hu Q, Zhu P, Wang W (2018) Efficient multi-modal geometric mean metric learning. Pattern Recognition 75:188\u2013198","journal-title":"Pattern Recognition"},{"key":"11634_CR41","doi-asserted-by":"crossref","unstructured":"Liao L, He X, Zhao B, Ngo C-W, Chua T-S (2018) Interpretable multimodal retrieval for fashion products. MM \u201918, Association for Computing Machinery, pp 1571\u20131579","DOI":"10.1145\/3240508.3240646"},{"key":"11634_CR42","doi-asserted-by":"crossref","unstructured":"Lin X, Duan Y, Dong Q, Lu J, Zhou J (2018) Deep variational metric learning. In: Proc. european conf. computer vision (ECCV), pp 689\u2013704","DOI":"10.1109\/CVPR.2018.00294"},{"issue":"6","key":"11634_CR43","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1109\/TMM.2016.2646180","volume":"19","author":"VE Liong","year":"2016","unstructured":"Liong VE, Lu Tan, Tan Y, Zhou J (2016) Deep coupled metric learning for cross-modal matching. IEEE Trans. Multimedia 19(6):1234\u20131244","journal-title":"IEEE Trans. Multimedia"},{"issue":"11","key":"11634_CR44","doi-asserted-by":"publisher","first-page":"6919","DOI":"10.1007\/s11042-019-08527-8","volume":"79","author":"M Mahmood","year":"2020","unstructured":"Mahmood M, Jalal A, Kim K (2020) WHITE STAG model: wise human interaction tracking and estimation (WHITE) using spatio-temporal and angular-geometric (STAG) descriptors. Multimedia Tools and Applications 79(11):6919\u20136950","journal-title":"Multimedia Tools and Applications"},{"key":"11634_CR45","doi-asserted-by":"crossref","unstructured":"Mekala D, Gupta V, Paranjape B, Karnick H (2016) SCDV: Sparse composite document vectors using soft clustering over distributional representations. arXiv preprint arXiv:1612.06778","DOI":"10.18653\/v1\/D17-1069"},{"key":"11634_CR46","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean, J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems(NeurIPS), pp 3111\u20133119"},{"key":"11634_CR47","doi-asserted-by":"crossref","unstructured":"Nadeem A, Jalal A, Kim K (2020) Human actions tracking and recognition based on body parts detection via artificial neural network. In: 2020 3rd International conference on advancements in computational sciences (ICACS), pp 1\u20136","DOI":"10.1109\/ICACS47775.2020.9055951"},{"key":"11634_CR48","first-page":"2949","volume":"15","author":"S Nitish","year":"2014","unstructured":"Nitish S, Ruslan S (2014) Multimodal learning with deep boltzmann machines. J. Mach. Learn. Res. 15:2949\u20132980","journal-title":"J. Mach. Learn. Res."},{"key":"11634_CR49","doi-asserted-by":"crossref","unstructured":"Oh\u00a0Song H, Jegelka S, Rathod, V, Murphy K (2017) Deep metric learning via facility location. In: Proc. IEEE conf. on computer vision and pattern recognition\u00a0(CVPR), pp 5382\u20135390","DOI":"10.1109\/CVPR.2017.237"},{"key":"11634_CR50","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1504\/IJHM.2019.098951","volume":"2","author":"S Osterland","year":"2019","unstructured":"Osterland S, Weber J (2019) Analytical analysis of single-stage pressure relief valves. International Journal of Hydromechatronics 2:32","journal-title":"International Journal of Hydromechatronics"},{"key":"11634_CR51","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.patrec.2019.11.041","volume":"131","author":"N Passalis","year":"2020","unstructured":"Passalis N, Iosifidis A, Gabbouj M, Tefas A (2020) Variance-preserving deep metric learning for content-based image retrieval. Pattern Recognition Letters 131:8\u201314","journal-title":"Pattern Recognition Letters"},{"issue":"9","key":"11634_CR52","doi-asserted-by":"publisher","first-page":"6061","DOI":"10.1007\/s11042-019-08463-7","volume":"79","author":"MAK Quaid","year":"2020","unstructured":"Quaid MAK, Jalal A (2020) Wearable sensors based human behavioral pattern recognition using statistical features and reweighted genetic algorithm. Multimedia Tools and Applications 79(9):6061\u20136083","journal-title":"Multimedia Tools and Applications"},{"key":"11634_CR53","unstructured":"Ramachandran P, Zoph B, Le QV (2017) Searching for activation functions. arXiv:1710.05941"},{"key":"11634_CR54","doi-asserted-by":"crossref","unstructured":"Rizwan SA, Jalal A, Kim, K (2020) An accurate facial expression detector using multi-landmarks selection and local transform features. In: 2020 3rd International conference on advancements in computational sciences (ICACS), pp 1\u20136","DOI":"10.1109\/ICACS47775.2020.9055954"},{"issue":"6","key":"11634_CR55","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.3233\/IDA-163196","volume":"21","author":"SM Roostaiyan","year":"2017","unstructured":"Roostaiyan SM, Imani E, Baghshah MS (2017) Multi-modal deep distance metric learning. Intelligent Data Analysis 21(6):1351\u20131369","journal-title":"Intelligent Data Analysis"},{"key":"11634_CR56","doi-asserted-by":"crossref","unstructured":"Roy A, Paul A, Pirsiavash H, Pan, S (2017) Automated detection of substance use-related social media posts based on image and text analysis. In: 2017 IEEE 29th International conf. tools with artificial intelligence (ICTAI). IEEE, pp 72\u2013779","DOI":"10.1109\/ICTAI.2017.00122"},{"key":"11634_CR57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44671-3","volume-title":"User-centric social multimedia computing","author":"J Sang","year":"2014","unstructured":"Sang J (2014) User-centric social multimedia computing. Springer, New York"},{"issue":"2","key":"11634_CR58","doi-asserted-by":"publisher","first-page":"4187","DOI":"10.1007\/s10586-018-1731-0","volume":"22","author":"RR Saritha","year":"2019","unstructured":"Saritha RR, Paul V, Kumar PG (2019) Content based image retrieval using deep learning process. Cluster Computing 22(2):4187\u20134200","journal-title":"Cluster Computing"},{"key":"11634_CR59","doi-asserted-by":"crossref","unstructured":"Seyedin S, Ahadi SM (2009) Robust mvdr-based feature extraction for speech recognition. In: 2009 7th International conference on information, communications and signal processing (ICICS), pp 1\u20135","DOI":"10.1109\/ICICS.2009.5397503"},{"key":"11634_CR60","unstructured":"Shi Y, Siddharth N, Paige B, Torr P (2019) Variational mixture-of-experts autoencoders for multi-modal deep generative models. In: Proc. advances in neural information processing system\u00a0(NeurIPS), pp 15692\u201315703"},{"key":"11634_CR61","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1504\/IJHM.2019.104386","volume":"2","author":"M Shokri","year":"2019","unstructured":"Shokri M, Tavakoli K (2019) A review on the artificial neural network approach to analysis and prediction of seismic damage in infrastructure. International Journal of Hydromechatronics 2:178","journal-title":"International Journal of Hydromechatronics"},{"key":"11634_CR62","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"11634_CR63","unstructured":"S\u00f8nderby,C, R T, M L, S\u00f8nderby S, WO (2016) How to train deep variational autoencoders and probabilistic ladder networks. In: Proc. int. conf. machine learning (ICML), pp 1\u20139"},{"key":"11634_CR64","doi-asserted-by":"crossref","unstructured":"Sparling EI, Sen S (2011) Rating: How difficult is it? In: Proceedings of the fifth ACM conference on recommender systems , RecSys \u201911, Association for Computing Machinery, pp 149\u2013156","DOI":"10.1145\/2043932.2043961"},{"issue":"2","key":"11634_CR65","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1049\/trit.2019.0002","volume":"4","author":"S Susan","year":"2019","unstructured":"Susan S, Agrawal P, Mittal M, Bansal S (2019) New shape descriptor in the context of edge continuity. CAAI Transactions on Intelligence Technology 4(2):101\u2013109","journal-title":"CAAI Transactions on Intelligence Technology"},{"key":"11634_CR66","unstructured":"Suzuki M, Nakayama K, Matsuo Y (2016) Joint multimodal learning with deep generative models. arXiv:1611.01891"},{"key":"11634_CR67","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proc. conf. computer vision and pattern recognition (CVPR), pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"4","key":"11634_CR68","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1016\/j.ipm.2018.04.004","volume":"54","author":"SA Tabrizi","year":"2018","unstructured":"Tabrizi SA, Shakery A, Zamani H, Tavallaei MA (2018) Person: Personalized information retrieval evaluation based on citation networks. Information Processing & Management 54(4):630\u2013656","journal-title":"Information Processing & Management"},{"key":"11634_CR69","doi-asserted-by":"publisher","first-page":"84613","DOI":"10.1109\/ACCESS.2019.2923552","volume":"7","author":"I Tautkute","year":"2019","unstructured":"Tautkute I, Trzci\u0144ski T, Skorupa AP, Brocki L, Marasek K (2019) Deepstyle: Multimodal search engine for fashion and interior design. IEEE Access 7:84613\u201384628","journal-title":"IEEE Access"},{"issue":"2","key":"11634_CR70","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1049\/trit.2019.0017","volume":"4","author":"Y Tingting","year":"2019","unstructured":"Tingting Y, Junqian W, Lintai W, Yong X (2019) Three-stage network for age estimation. CAAI Transactions on Intelligence Technology 4(2):122\u2013126","journal-title":"CAAI Transactions on Intelligence Technology"},{"key":"11634_CR71","unstructured":"Vedantam R, Fischer I, Huang J, Murphy K (2017) Generative models of visually grounded imagination. arXiv:1705.10762"},{"key":"11634_CR72","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.knosys.2016.09.005","volume":"112","author":"E Vicente-L\u00f3pez","year":"2016","unstructured":"Vicente-L\u00f3pez E, de Campos LM, Fern\u00e1ndez-Luna JM, Huete JF (2016) Use of textual and conceptual profiles for personalized retrieval of political documents. Knowledge-Based Systems 112:127\u2013141","journal-title":"Knowledge-Based Systems"},{"key":"11634_CR73","doi-asserted-by":"crossref","unstructured":"Wang J, Song Y, Leung T, Rosenberg C, Wang J, Philbin J, Chen B, Wu Y (2014) Learning fine-grained image similarity with deep ranking. In: Proc. IEEE conf. computer vision and pattern recognition (CVPR), pp 1386\u20131393","DOI":"10.1109\/CVPR.2014.180"},{"key":"11634_CR74","doi-asserted-by":"crossref","unstructured":"Wang J, Zhou F, Wen S, Liu X, Lin Y (2017) Deep metric learning with angular loss. In: Proc. of the IEEE international conf. on computer vision\u00a0(ICCV), pp 2593\u20132601","DOI":"10.1109\/ICCV.2017.283"},{"key":"11634_CR75","doi-asserted-by":"crossref","unstructured":"Wang W, Yan X, Lee H, Livescu K (2016) Deep variational canonical correlation analysis. arXiv:1610.03454","DOI":"10.21437\/Interspeech.2017-1581"},{"issue":"1","key":"11634_CR76","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1504\/IJHM.2019.098949","volume":"2","author":"T Wiens","year":"2019","unstructured":"Wiens T (2019) Engine speed reduction for hydraulic machinery using predictive algorithms. International Journal of Hydromechatronics 2(1):16\u201331","journal-title":"International Journal of Hydromechatronics"},{"key":"11634_CR77","unstructured":"Wu M, Goodman N (2018) Multimodal generative models for scalable weakly-supervised learning. In: Proc. conf. neural information processing systems (NeurIPS), pp 5575\u20135585"},{"key":"11634_CR78","doi-asserted-by":"crossref","unstructured":"Wu Y, Wang S. Huang Q (2017) Online asymmetric similarity learning for cross-modal retrieval. In: Proc. IEEE conf. computer vsion and pattern recognition\u00a0(CVPR), pp 4269\u20134278","DOI":"10.1109\/CVPR.2017.424"},{"issue":"2","key":"11634_CR79","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1007\/s11280-018-0541-x","volume":"22","author":"X Xu","year":"2019","unstructured":"Xu X, He L, Lu H, Gao L, Ji Y (2019) Deep adversarial metric learning for cross-modal retrieval. World Wide Web 22(2):657\u2013672","journal-title":"World Wide Web"},{"key":"11634_CR80","doi-asserted-by":"crossref","unstructured":"Yaacob NI, Tahir NM (2012) Feature selection for gait recognition. In: 2012 IEEE symposium on humanities, science and engineering research, pp. 379\u2013383","DOI":"10.1109\/SHUSER.2012.6268871"},{"issue":"12","key":"11634_CR81","doi-asserted-by":"publisher","first-page":"4014","DOI":"10.1109\/TCYB.2016.2591583","volume":"47","author":"J Yu","year":"2016","unstructured":"Yu J, Yang X, Gao F, Tao D (2016) Deep multimodal distance metric learning using click constraints for image ranking. IEEE Trans. Cybernetics 47(12):4014\u20134024","journal-title":"IEEE Trans. Cybernetics"},{"key":"11634_CR82","doi-asserted-by":"publisher","first-page":"12","DOI":"10.4108\/eai.9-10-2017.154549","volume":"3","author":"W Zhao","year":"2017","unstructured":"Zhao W, Zhou D, Wu X, Lawless S, Liu J (2017) An augmented user model for personalized search in collaborative social tagging systems. EAI Endorsed Transactions on Collaborative Computing 3:12","journal-title":"EAI Endorsed Transactions on Collaborative Computing"},{"issue":"4","key":"11634_CR83","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1049\/trit.2019.0036","volume":"4","author":"C Zhu","year":"2019","unstructured":"Zhu C, Miao D (2019) Influence of kernel clustering on an rbfn. CAAI Transactions on Intelligence Technology 4(4):255\u2013260","journal-title":"CAAI Transactions on Intelligence Technology"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11634-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11634-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11634-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,14]],"date-time":"2023-01-14T22:26:23Z","timestamp":1673735183000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11634-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,11]]},"references-count":83,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["11634"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11634-0","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2021,11,11]]},"assertion":[{"value":"30 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}