@article{bb121800, AUTHOR = "Helmy, T.", TITLE = "A Generic Framework for Semantic Annotation of Images", JOURNAL = IJIG, VOLUME = "18", YEAR = "2018", NUMBER = "3", MONTH = "July", PAGES = "Article 1850013", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117913"} @article{bb121801, AUTHOR = "Hu, J. and Lam, K.M. and Lou, P. and Liu, Q. and Deng, W.P.", TITLE = "Can a machine have two systems for recognition, like human beings?", JOURNAL = JVCIR, VOLUME = "56", YEAR = "2018", PAGES = "275-286", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117914"} @article{bb121802, AUTHOR = "Bhagat, P.K. and Choudhary, P.", TITLE = "Image annotation: Then and now", JOURNAL = IVC, VOLUME = "80", YEAR = "2018", PAGES = "1-23", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117915"} @article{bb121803, AUTHOR = "Bazrafkan, S. and Javidnia, H. and Corcoran, P.", TITLE = "Latent space mapping for generation of object elements with corresponding data annotation", JOURNAL = PRL, VOLUME = "116", YEAR = "2018", PAGES = "179-186", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117916"} @article{bb121804, AUTHOR = "Jiu, M.Y. and Sahbi, H.", TITLE = "Deep representation design from deep kernel networks", JOURNAL = PR, VOLUME = "88", YEAR = "2019", PAGES = "447-457", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117917"} @article{bb121805, AUTHOR = "Foumani, S.N.M. and Nickabadi, A.", TITLE = "A probabilistic topic model using deep visual word representation for simultaneous image classification and annotation", JOURNAL = JVCIR, VOLUME = "59", YEAR = "2019", PAGES = "195-203", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117918"} @article{bb121806, AUTHOR = "Zhang, J.J. and Wu, Q. and Zhang, J. and Shen, C.H. and Lu, J.F. and Wu, Q.A.", TITLE = "Heritage image annotation via collective knowledge", JOURNAL = PR, VOLUME = "93", YEAR = "2019", PAGES = "204-214", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117919"} @article{bb121807, AUTHOR = "Verma, Y.", TITLE = "Diverse image annotation with missing labels", JOURNAL = PR, VOLUME = "93", YEAR = "2019", PAGES = "470-484", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117920"} @article{bb121808, AUTHOR = "Markatopoulou, F. and Mezaris, V. and Patras, I.", TITLE = "Implicit and Explicit Concept Relations in Deep Neural Networks for Multi-Label Video/Image Annotation", JOURNAL = CirSysVideo, VOLUME = "29", YEAR = "2019", NUMBER = "6", MONTH = "June", PAGES = "1631-1644", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117921"} @article{bb121809, AUTHOR = "Laib, L. and Allili, M.S. and Ait Aoudia, S.", TITLE = "A probabilistic topic model for event-based image classification and multi-label annotation", JOURNAL = SP:IC, VOLUME = "76", YEAR = "2019", PAGES = "283-294", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117922"} @article{bb121810, AUTHOR = "Olaode, A. and Naghdy, G.", TITLE = "Review of the application of machine learning to the automatic semantic annotation of images", JOURNAL = IET-IPR, VOLUME = "13", YEAR = "2019", NUMBER = "8", MONTH = "June", PAGES = "1232-1245", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117923"} @article{bb121811, AUTHOR = "Zhang, C.J. and Cheng, J. and Tian, Q.", TITLE = "Multiview, Few-Labeled Object Categorization by Predicting Labels With View Consistency", JOURNAL = Cyber, VOLUME = "49", YEAR = "2019", NUMBER = "11", MONTH = "November", PAGES = "3834-3843", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117924"} @article{bb121812, AUTHOR = "Tang, C. and Liu, X. and Wang, P. and Zhang, C. and Li, M. and Wang, L.", TITLE = "Adaptive Hypergraph Embedded Semi-Supervised Multi-Label Image Annotation", JOURNAL = MultMed, VOLUME = "21", YEAR = "2019", NUMBER = "11", MONTH = "November", PAGES = "2837-2849", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117925"} @article{bb121813, AUTHOR = "Mundnich, K. and Booth, B.M. and Girault, B. and Narayanan, S.", TITLE = "Generating labels for regression of subjective constructs using triplet embeddings", JOURNAL = PRL, VOLUME = "128", YEAR = "2019", PAGES = "385-392", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117926"} @article{bb121814, AUTHOR = "Chaudhary, C. and Goyal, P. and Prasad, D.N. and Chen, Y.P.", TITLE = "Enhancing the Quality of Image Tagging Using a Visio-Textual Knowledge Base", JOURNAL = MultMed, VOLUME = "22", YEAR = "2020", NUMBER = "4", MONTH = "April", PAGES = "897-911", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117927"} @article{bb121815, AUTHOR = "Khatchatoorian, A.G. and Jamzad, M.", TITLE = "Architecture to improve the accuracy of automatic image annotation systems", JOURNAL = IET-CV, VOLUME = "14", YEAR = "2020", NUMBER = "5", MONTH = "August", PAGES = "214-223", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117928"} @article{bb121816, AUTHOR = "Theodosiou, Z. and Tsapatsoulis, N.", TITLE = "Image annotation: the effects of content, lexicon and annotation method", JOURNAL = MultInfoRetr, VOLUME = "9", YEAR = "2020", NUMBER = "3", MONTH = "September", PAGES = "191-203", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117929"} @article{bb121817, AUTHOR = "Haghighi, F. and Taher, M.R.H. and Zhou, Z.W. and Gotway, M.B. and Liang, J.M.", TITLE = "Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-Supervised Learning", JOURNAL = MedImg, VOLUME = "40", YEAR = "2021", NUMBER = "10", MONTH = "October", PAGES = "2857-2868", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117930"} @article{bb121818, AUTHOR = "Hochberg, D.C. and Greenspan, H. and Giryes, R.", TITLE = "A Self Supervised StyleGAN for Image Annotation and Classification With Extremely Limited Labels", JOURNAL = MedImg, VOLUME = "41", YEAR = "2022", NUMBER = "12", MONTH = "December", PAGES = "3509-3519", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117931"} @article{bb121819, AUTHOR = "Wang, J. and Xu, W.J. and Wang, Q.Z. and Chan, A.B.", TITLE = "On Distinctive Image Captioning via Comparing and Reweighting", JOURNAL = PAMI, VOLUME = "45", YEAR = "2023", NUMBER = "2", MONTH = "February", PAGES = "2088-2103", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117932"} @inproceedings{bb121820, AUTHOR = "Lahtinen, T. and Turtiainen, H. and Costin, A.", TITLE = "Brima: Low-Overhead Browser-Only Image Annotation Tool (Preprint)", BOOKTITLE = ICIP21, YEAR = "2021", PAGES = "2633-2637", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117933"} @inproceedings{bb121821, AUTHOR = "Lotfi, F. and Jamzad, M. and Beigy, H.", TITLE = "Automatic Image Annotation using Tag Relations and Graph Convolutional Networks", BOOKTITLE = IPRIA21, YEAR = "2021", PAGES = "1-6", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117934"} @inproceedings{bb121822, AUTHOR = "Chen, X.Y. and Jiang, M. and Zhao, Q.", TITLE = "Self-Distillation for Few-Shot Image Captioning", BOOKTITLE = WACV21, YEAR = "2021", PAGES = "545-555", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117935"} @inproceedings{bb121823, AUTHOR = "Jiu, M. and Sahbi, H.", TITLE = "End-to-End Deep Kernel Map Design for Image Annotation", BOOKTITLE = ICIP20, YEAR = "2020", PAGES = "1546-1550", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117936"} @inproceedings{bb121824, AUTHOR = "Hu, H. and Misra, I. and van der Maaten, L.", TITLE = "Evaluating Text-to-Image Matching using Binary Image Selection (BISON)", BOOKTITLE = CLVL19, YEAR = "2019", PAGES = "1887-1890", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117937"} @inproceedings{bb121825, AUTHOR = "Tanaka, M. and Itamochi, T. and Narioka, K. and Sato, I. and Ushiku, Y. and Harada, T.", TITLE = "Generating Easy-to-Understand Referring Expressions for Target Identifications", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "5793-5802", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117938"} @inproceedings{bb121826, AUTHOR = "Gupta, T. and Schwing, A.G. and Hoiem, D.", TITLE = "ViCo: Word Embeddings From Visual Co-Occurrences", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "7424-7433", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117939"} @inproceedings{bb121827, AUTHOR = "Bracha, L. and Chechik, G.", TITLE = "Informative Object Annotations: Tell Me Something I Don't Know", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "12499-12507", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117940"} @inproceedings{bb121828, AUTHOR = "Rapson, C.J. and Seet, B. and Naeem, M.A. and Lee, J.E. and Al Sarayreh, M. and Klette, R.", TITLE = "Reducing the Pain: A Novel Tool for Efficient Ground-Truth Labelling in Images", BOOKTITLE = IVCNZ18, YEAR = "2018", PAGES = "1-9", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117941"} @inproceedings{bb121829, AUTHOR = "Wu, B.Y. and Chen, W.D. and Sun, P. and Liu, W. and Ghanem, B. and Lyu, S.W.", TITLE = "Tagging Like Humans: Diverse and Distinct Image Annotation", BOOKTITLE = CVPR18, YEAR = "2018", PAGES = "7967-7975", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117942"} @inproceedings{bb121830, AUTHOR = "Wu, X.J. and Zhang, L. and Li, F.Z. and Wang, B.J.", TITLE = "A Novel Model for Multi-label Image Annotation", BOOKTITLE = ICPR18, YEAR = "2018", PAGES = "1953-1958", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117943"} @inproceedings{bb121831, AUTHOR = "Jiu, M. and Sahbi, H. and Qi, L.", TITLE = "Deep Context Networks for Image Annotation", BOOKTITLE = ICPR18, YEAR = "2018", PAGES = "2422-2427", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117944"} @inproceedings{bb121832, AUTHOR = "Khatchatoorian, A.G. and Jamzad, M.", TITLE = "Post Rectifying Methods to Improve the Accuracy of Image Annotation", BOOKTITLE = DICTA17, YEAR = "2017", PAGES = "1-7", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117945"} @inproceedings{bb121833, AUTHOR = "Pellegrin, L. and Escalante, H.J. and Montes y Gomez, M. and Villegas, M. and Gonzalez, F.A.", TITLE = "A Flexible Framework for the Evaluation of Unsupervised Image Annotation", BOOKTITLE = CIARP17, YEAR = "2017", PAGES = "508-516", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117946"} @inproceedings{bb121834, AUTHOR = "Tripathi, A. and Gupta, A. and Chaudhary, S. and Lall, B.", TITLE = "Image Annotation Using Latent Components and Transmedia Association", BOOKTITLE = PReMI17, YEAR = "2017", PAGES = "493-500", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117947"} @inproceedings{bb121835, AUTHOR = "Wu, B.Y. and Jia, F. and Liu, W. and Ghanem, B.", TITLE = "Diverse Image Annotation", BOOKTITLE = CVPR17, YEAR = "2017", PAGES = "6194-6202", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117948"} @article{bb121836, AUTHOR = "Gao, L.L. and Guo, Z. and Zhang, H.W. and Xu, X. and Shen, H.T.", TITLE = "Video Captioning With Attention-Based LSTM and Semantic Consistency", JOURNAL = MultMed, VOLUME = "19", YEAR = "2017", NUMBER = "9", MONTH = "September", PAGES = "2045-2055", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117949"} @article{bb121837, AUTHOR = "Bin, Y. and Yang, Y. and Shen, F. and Xie, N. and Shen, H.T. and Li, X.", TITLE = "Describing Video With Attention-Based Bidirectional LSTM", JOURNAL = Cyber, VOLUME = "49", YEAR = "2019", NUMBER = "7", MONTH = "July", PAGES = "2631-2641", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117950"} @article{bb121838, AUTHOR = "Fu, K. and Jin, J.Q. and Cui, R.P. and Sha, F. and Zhang, C.S.", TITLE = "Aligning Where to See and What to Tell: Image Captioning with Region-Based Attention and Scene-Specific Contexts", JOURNAL = PAMI, VOLUME = "39", YEAR = "2017", NUMBER = "12", MONTH = "December", PAGES = "2321-2334", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117951"} @article{bb121839, AUTHOR = "Xiao, C.M. and Yang, Q. and Xu, X.Q. and Zhang, J.W. and Zhou, F. and Zhang, C.S.", TITLE = "Where you edit is what you get: Text-guided image editing with region-based attention", JOURNAL = PR, VOLUME = "139", YEAR = "2023", PAGES = "109458", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117952"} @article{bb121840, AUTHOR = "Nian, F.D. and Li, T. and Wang, Y. and Wu, X.Y. and Ni, B.B. and Xu, C.S.", TITLE = "Learning explicit video attributes from mid-level representation for video captioning", JOURNAL = CVIU, VOLUME = "163", YEAR = "2017", NUMBER = "1", PAGES = "126-138", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117953"} @article{bb121841, AUTHOR = "Ye, S. and Han, J. and Liu, N.", TITLE = "Attentive Linear Transformation for Image Captioning", JOURNAL = IP, VOLUME = "27", YEAR = "2018", NUMBER = "11", MONTH = "November", PAGES = "5514-5524", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117954"} @article{bb121842, AUTHOR = "Xian, Y. and Tian, Y.", TITLE = "Self-Guiding Multimodal LSTM: When We Do Not Have a Perfect Training Dataset for Image Captioning", JOURNAL = IP, VOLUME = "28", YEAR = "2019", NUMBER = "11", MONTH = "November", PAGES = "5241-5252", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117955"} @article{bb121843, AUTHOR = "Peng, Y.Q. and Liu, X. and Wang, W.H. and Zhao, X.S. and Wei, M.", TITLE = "Image caption model of double LSTM with scene factors", JOURNAL = IVC, VOLUME = "86", YEAR = "2019", PAGES = "38-44", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117956"} @article{bb121844, AUTHOR = "Wu, L. and Xu, M. and Wang, J. and Perry, S.", TITLE = "Recall What You See Continually Using GridLSTM in Image Captioning", JOURNAL = MultMed, VOLUME = "22", YEAR = "2020", NUMBER = "3", MONTH = "March", PAGES = "808-818", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117957"} @article{bb121845, AUTHOR = "Deng, Z.R. and Jiang, Z.Q. and Lan, R. and Huang, W.M. and Luo, X.N.", TITLE = "Image captioning using DenseNet network and adaptive attention", JOURNAL = SP:IC, VOLUME = "85", YEAR = "2020", PAGES = "115836", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117958"} @article{bb121846, AUTHOR = "Ji, J. and Xu, C. and Zhang, X. and Wang, B. and Song, X.", TITLE = "Spatio-Temporal Memory Attention for Image Captioning", JOURNAL = IP, VOLUME = "29", YEAR = "2020", PAGES = "7615-7628", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117959"} @article{bb121847, AUTHOR = "Che, W.B. and Fan, X.P. and Xiong, R.Q. and Zhao, D.B.", TITLE = "Visual Relationship Embedding Network for Image Paragraph Generation", JOURNAL = MultMed, VOLUME = "22", YEAR = "2020", NUMBER = "9", MONTH = "September", PAGES = "2307-2320", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117960"} @article{bb121848, AUTHOR = "Zhang, J. and Li, K.K. and Wang, Z.", TITLE = "Parallel-fusion LSTM with synchronous semantic and visual information for image captioning", JOURNAL = JVCIR, VOLUME = "75", YEAR = "2021", PAGES = "103044", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117961"} @article{bb121849, AUTHOR = "He, S. and Lu, Y.Y. and Chen, S.N.", TITLE = "Image Captioning Algorithm Based on Multi-Branch CNN and Bi-LSTM", JOURNAL = IEICE, VOLUME = "E104-D", YEAR = "2021", NUMBER = "7", MONTH = "July", PAGES = "941-947", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117962"} @article{bb121850, AUTHOR = "Yuan, J. and Zhu, S. and Huang, S.Y. and Zhang, H.W. and Xiao, Y.Q. and Li, Z.Y. and Wang, M.", TITLE = "Discriminative Style Learning for Cross-Domain Image Captioning", JOURNAL = IP, VOLUME = "31", YEAR = "2022", PAGES = "1723-1736", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117963"} @inproceedings{bb121851, AUTHOR = "Zhou, Y. and Zhang, Y. and Hu, Z.Z. and Wang, M.", TITLE = "Semi-Autoregressive Transformer for Image Captioning", BOOKTITLE = CLVL21, YEAR = "2021", PAGES = "3132-3136", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117964"} @article{bb121852, AUTHOR = "Lv, G. and Sun, Y.N. and Nian, F. and Zhu, M.F. and Tang, W.L. and Hu, Z.Z.", TITLE = "COME: Clip-OCR and Master ObjEct for text image captioning", JOURNAL = IVC, VOLUME = "136", YEAR = "2023", PAGES = "104751", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117965"} @inproceedings{bb121853, AUTHOR = "Niu, Z.X. and Zhou, M. and Wang, L. and Gao, X.B. and Hua, G.", TITLE = "Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding", BOOKTITLE = ICCV17, YEAR = "2017", PAGES = "1899-1907", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117966"} @inproceedings{bb121854, AUTHOR = "Tan, Y.H. and Chan, C.S.", TITLE = "phi-LSTM: A Phrase-Based Hierarchical LSTM Model for Image Captioning", BOOKTITLE = ACCV16, YEAR = "2016", PAGES = "V: 101-117", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117967"} @inproceedings{bb121855, AUTHOR = "Wang, M. and Song, L. and Yang, X.K. and Luo, C.F.", TITLE = "A parallel-fusion RNN-LSTM architecture for image caption generation", BOOKTITLE = ICIP16, YEAR = "2016", PAGES = "4448-4452", BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117968"} @article{bb121856, AUTHOR = "Verma, Y. and Jawahar, C.V.", TITLE = "A support vector approach for cross-modal search of images and texts", JOURNAL = CVIU, VOLUME = "154", YEAR = "2017", NUMBER = "1", PAGES = "48-63", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117969"} @inproceedings{bb121857, AUTHOR = "Dutta, A. and Verma, Y. and Jawahar, C.V.", TITLE = "Recurrent Image Annotation with Explicit Inter-Label Dependencies", BOOKTITLE = ECCV20, YEAR = "2020", PAGES = "XXIX: 191-207", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117970"} @article{bb121858, AUTHOR = "Xue, J.F. and Eguchi, K.", TITLE = "Video Data Modeling Using Sequential Correspondence Hierarchical Dirichlet Processes", JOURNAL = IEICE, VOLUME = "E100-D", YEAR = "2017", NUMBER = "1", MONTH = "January", PAGES = "33-41", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117971"} @article{bb121859, AUTHOR = "Liu, A.A. and Xu, N. and Wong, Y.K. and Li, J. and Su, Y.T. and Kankanhalli, M.", TITLE = "Hierarchical & multimodal video captioning: Discovering and transferring multimodal knowledge for vision to language", JOURNAL = CVIU, VOLUME = "163", YEAR = "2017", NUMBER = "1", PAGES = "113-125", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117972"} @article{bb121860, AUTHOR = "Guan, J.N. and Wang, E.", TITLE = "Repeated review based image captioning for image evidence review", JOURNAL = SP:IC, VOLUME = "63", YEAR = "2018", PAGES = "141-148", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117973"} @article{bb121861, AUTHOR = "Hu, M. and Yang, Y. and Shen, F. and Zhang, L. and Shen, H.T. and Li, X.", TITLE = "Robust Web Image Annotation via Exploring Multi-Facet and Structural Knowledge", JOURNAL = IP, VOLUME = "26", YEAR = "2017", NUMBER = "10", MONTH = "October", PAGES = "4871-4884", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117974"} @article{bb121862, AUTHOR = "Gil Gonzalez, J. and Alvarez Meza, A. and Orozco Gutierrez, A.", TITLE = "Learning from multiple annotators using kernel alignment", JOURNAL = PRL, VOLUME = "116", YEAR = "2018", PAGES = "150-156", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117975"} @article{bb121863, AUTHOR = "Zheng, H. and Wu, J.H. and Liang, R. and Li, Y. and Li, X.Z.", TITLE = "Multi-task learning for captioning images with novel words", JOURNAL = IET-CV, VOLUME = "13", YEAR = "2019", NUMBER = "3", MONTH = "April", PAGES = "294-301", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117976"} @article{bb121864, AUTHOR = "Park, C.C. and Kim, B. and Kim, G.", TITLE = "Towards Personalized Image Captioning via Multimodal Memory Networks", JOURNAL = PAMI, VOLUME = "41", YEAR = "2019", NUMBER = "4", MONTH = "April", PAGES = "999-1012", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117977"} @inproceedings{bb121865, AUTHOR = "Park, C.C. and Kim, B. and Kim, G.", TITLE = "Attend to You: Personalized Image Captioning with Context Sequence Memory Networks", BOOKTITLE = CVPR17, YEAR = "2017", PAGES = "6432-6440", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117978"} @article{bb121866, AUTHOR = "Yang, M. and Zhao, W. and Xu, W. and Feng, Y. and Zhao, Z. and Chen, X. and Lei, K.", TITLE = "Multitask Learning for Cross-Domain Image Captioning", JOURNAL = MultMed, VOLUME = "21", YEAR = "2019", NUMBER = "4", MONTH = "April", PAGES = "1047-1061", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117979"} @article{bb121867, AUTHOR = "Yu, N. and Hu, X. and Song, B. and Yang, J. and Zhang, J.", TITLE = "Topic-Oriented Image Captioning Based on Order-Embedding", JOURNAL = IP, VOLUME = "28", YEAR = "2019", NUMBER = "6", MONTH = "June", PAGES = "2743-2754", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117980"} @article{bb121868, AUTHOR = "Li, X. and Xu, C. and Wang, X. and Lan, W. and Jia, Z. and Yang, G. and Xu, J.", TITLE = "COCO-CN for Cross-Lingual Image Tagging, Captioning, and Retrieval", JOURNAL = MultMed, VOLUME = "21", YEAR = "2019", NUMBER = "9", MONTH = "September", PAGES = "2347-2360", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117981"} @article{bb121869, AUTHOR = "Tian, C. and Tian, M. and Jiang, M.M. and Liu, H. and Deng, D.H.", TITLE = "How much do cross-modal related semantics benefit image captioning by weighting attributes and re-ranking sentences?", JOURNAL = PRL, VOLUME = "125", YEAR = "2019", PAGES = "639-645", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117982"} @article{bb121870, AUTHOR = "Niu, Y. and Lu, Z. and Wen, J. and Xiang, T. and Chang, S.", TITLE = "Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation", JOURNAL = IP, VOLUME = "28", YEAR = "2019", NUMBER = "4", MONTH = "April", PAGES = "1720-1731", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117983"} @article{bb121871, AUTHOR = "Huang, Y. and Chen, J. and Ouyang, W. and Wan, W. and Xue, Y.", TITLE = "Image Captioning With End-to-End Attribute Detection and Subsequent Attributes Prediction", JOURNAL = IP, VOLUME = "29", YEAR = "2020", PAGES = "4013-4026", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117984"} @article{bb121872, AUTHOR = "Zhao, W. and Wu, X. and Luo, J.", TITLE = "Cross-Domain Image Captioning via Cross-Modal Retrieval and Model Adaptation", JOURNAL = IP, VOLUME = "30", YEAR = "2021", PAGES = "1180-1192", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117985"} @article{bb121873, AUTHOR = "Wang, H. and Du, Y.T. and Zhang, G.X. and Cai, Z.M. and Su, C.", TITLE = "Learning Fundamental Visual Concepts Based on Evolved Multi-Edge Concept Graph", JOURNAL = MultMed, VOLUME = "23", YEAR = "2021", PAGES = "4400-4413", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117986"} @article{bb121874, AUTHOR = "Zhang, J. and Mei, K. and Zheng, Y. and Fan, J.", TITLE = "Integrating Part of Speech Guidance for Image Captioning", JOURNAL = MultMed, VOLUME = "23", YEAR = "2021", PAGES = "92-104", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117987"} @article{bb121875, AUTHOR = "Kim, D.J. and Oh, T.H. and Choi, J. and Kweon, I.S.", TITLE = "Dense Relational Image Captioning via Multi-Task Triple-Stream Networks", JOURNAL = PAMI, VOLUME = "44", YEAR = "2022", NUMBER = "11", MONTH = "November", PAGES = "7348-7362", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117988"} @inproceedings{bb121876, AUTHOR = "Kim, D.J. and Choi, J. and Oh, T.H. and Kweon, I.S.", TITLE = "Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "6264-6273", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117989"} @article{bb121877, AUTHOR = "Nguyen, T.S. and Fernando, B.", TITLE = "Effective Multimodal Encoding for Image Paragraph Captioning", JOURNAL = IP, VOLUME = "31", YEAR = "2022", PAGES = "6381-6395", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117990"} @article{bb121878, AUTHOR = "Duan, Y.Q. and Wang, Z. and Li, Y. and Wang, J.Y.", TITLE = "Cross-domain multi-style merge for image captioning", JOURNAL = CVIU, VOLUME = "228", YEAR = "2023", PAGES = "103617", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117991"} @article{bb121879, AUTHOR = "Wu, X.X. and Li, T.", TITLE = "Sentimental Visual Captioning using Multimodal Transformer", JOURNAL = IJCV, VOLUME = "131", YEAR = "2023", NUMBER = "1", MONTH = "January", PAGES = "1073-1090", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117992"} @article{bb121880, AUTHOR = "Ding, Z.W. and Lan, G.L. and Song, Y.Z. and Yang, Z.W.", TITLE = "SGIR: Star Graph-Based Interaction for Efficient and Robust Multimodal Representation", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "4217-4229", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117993"} @article{bb121881, AUTHOR = "Zhao, W.T. and Wu, X.X.", TITLE = "Boosting Entity-Aware Image Captioning With Multi-Modal Knowledge Graph", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "2659-2670", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117994"} @article{bb121882, AUTHOR = "Gao, J.L. and Li, J. and Jia, C.M. and Wang, S.S. and Ma, S.W. and Gao, W.", TITLE = "Cross Modal Compression With Variable Rate Prompt", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "3444-3456", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117995"} @inproceedings{bb121883, AUTHOR = "Hu, J.C. and Cavicchioli, R. and Capotondi, A.", TITLE = "A Request for Clarity over the End of Sequence Token in the Self-critical Sequence Training", BOOKTITLE = CIAP23, YEAR = "2023", PAGES = "I:39-50", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117996"} @inproceedings{bb121884, AUTHOR = "Hu, W.Z. and Wang, L. and Xu, L.", TITLE = "Spatial-Semantic Attention for Grounded Image Captioning", BOOKTITLE = ICIP22, YEAR = "2022", PAGES = "61-65", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117997"} @inproceedings{bb121885, AUTHOR = "Sharif, N. and Jalwana, M.A.A.K. and Bennamoun, M. and Liu, W. and Shah, S.A.A.", TITLE = "Leveraging Linguistically-aware Object Relations and NASNet for Image Captioning", BOOKTITLE = IVCNZ20, YEAR = "2020", PAGES = "1-6", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117998"} @inproceedings{bb121886, AUTHOR = "Kuo, C.W. and Kira, Z.", TITLE = "Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "17948-17958", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117999"} @inproceedings{bb121887, AUTHOR = "Zhou, M.Y. and Zhou, L.W. and Wang, S.H. and Cheng, Y. and Li, L.J. and Yu, Z. and Liu, J.J.", TITLE = "UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training", BOOKTITLE = CVPR21, YEAR = "2021", PAGES = "4153-4163", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT118000"} @inproceedings{bb121888, AUTHOR = "Laina, I. and Rupprecht, C. and Navab, N.", TITLE = "Towards Unsupervised Image Captioning With Shared Multimodal Embeddings", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "7413-7423", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT118001"} @inproceedings{bb121889, AUTHOR = "Akbari, H. and Karaman, S. and Bhargava, S. and Chen, B. and Vondrick, C. and Chang, S.F.", TITLE = "Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "12468-12478", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT118002"} @inproceedings{bb121890, AUTHOR = "Chen, T.H. and Liao, Y.H. and Chuang, C.Y. and Hsu, W.T. and Fu, J. and Sun, M.", TITLE = "Show, Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner", BOOKTITLE = ICCV17, YEAR = "2017", PAGES = "521-530", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT118003"} @inproceedings{bb121891, AUTHOR = "Pini, S. and Cornia, M. and Baraldi, L. and Cucchiara, R.", TITLE = "Towards Video Captioning with Naming: A Novel Dataset and a Multi-modal Approach", BOOKTITLE = CIAP17, YEAR = "2017", PAGES = "II:384-395", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT118004"} @inproceedings{bb121892, AUTHOR = "Pan, J.Y. and Yang, H.J. and Faloutsos, C.", TITLE = "MMSS: Graph-based Multi-modal Story-oriented Video Summarization and Retrieval", BOOKTITLE = CMU-CS-TR, YEAR = "2004", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT118005"} @inproceedings{bb121893, AUTHOR = "Pan, J.Y. and Yang, H.J. and Faloutsos, C. and Duygulu, P.", TITLE = "GCap: Graph-based Automatic Image Captioning", BOOKTITLE = MMDE04, YEAR = "2004", PAGES = "146", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT118006"} @inproceedings{bb121894, AUTHOR = "Pan, J.Y.", TITLE = "Advanced Tools for Video and Multimedia Mining", BOOKTITLE = CMU-CS, YEAR = "2006", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT118007"} @inproceedings{bb121895, AUTHOR = "Pan, J.Y.", TITLE = "Advanced Tools for Video and Multimedia Mining", BOOKTITLE = Ph.D., YEAR = "2006", BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT118007"} @article{bb121896, AUTHOR = "Yu, J. and Li, J. and Yu, Z. and Huang, Q.", TITLE = "Multimodal Transformer With Multi-View Visual Representation for Image Captioning", JOURNAL = CirSysVideo, VOLUME = "30", YEAR = "2020", NUMBER = "12", MONTH = "December", PAGES = "4467-4480", BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT118008"} @article{bb121897, AUTHOR = "Zhang, Y. and Shi, X.Y. and Mi, S. and Yang, X.", TITLE = "Image captioning with transformer and knowledge graph", JOURNAL = PRL, VOLUME = "143", YEAR = "2021", PAGES = "43-49", BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT118009"} @article{bb121898, AUTHOR = "Yan, C.G. and Hao, Y.M. and Li, L. and Yin, J. and Liu, A. and Mao, Z. and Chen, Z.Y. and Gao, X.Y.", TITLE = "Task-Adaptive Attention for Image Captioning", JOURNAL = CirSysVideo, VOLUME = "32", YEAR = "2022", NUMBER = "1", MONTH = "January", PAGES = "43-51", BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT118010"} @article{bb121899, AUTHOR = "Ren, Z.H. and Gou, S.P. and Guo, Z. and Mao, S.S. and Li, R.M.", TITLE = "A Mask-Guided Transformer Network with Topic Token for Remote Sensing Image Captioning", JOURNAL = RS, VOLUME = "14", YEAR = "2022", NUMBER = "12", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT118011"}