@article{bb136800,
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#TT132790"}
@article{bb136801,
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#TT132791"}
@article{bb136802,
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#TT132792"}
@article{bb136803,
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#TT132793"}
@article{bb136804,
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#TT132794"}
@article{bb136805,
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#TT132795"}
@article{bb136806,
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#TT132796"}
@article{bb136807,
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#TT132797"}
@article{bb136808,
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#TT132798"}
@article{bb136809,
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#TT132799"}
@article{bb136810,
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#TT132800"}
@article{bb136811,
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#TT132801"}
@article{bb136812,
AUTHOR = "Tang, C. and Liu, X.W. and Wang, P.C. and Zhang, C.Q. and Li, M.M. and Wang, L.Z.",
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#TT132802"}
@article{bb136813,
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#TT132803"}
@article{bb136814,
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#TT132804"}
@article{bb136815,
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#TT132805"}
@article{bb136816,
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#TT132806"}
@article{bb136817,
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#TT132807"}
@article{bb136818,
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#TT132808"}
@inproceedings{bb136819,
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#TT132809"}
@inproceedings{bb136820,
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#TT132810"}
@inproceedings{bb136821,
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#TT132811"}
@inproceedings{bb136822,
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#TT132812"}
@inproceedings{bb136823,
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#TT132813"}
@inproceedings{bb136824,
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#TT132814"}
@inproceedings{bb136825,
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#TT132815"}
@inproceedings{bb136826,
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#TT132816"}
@inproceedings{bb136827,
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#TT132817"}
@inproceedings{bb136828,
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#TT132818"}
@inproceedings{bb136829,
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#TT132819"}
@inproceedings{bb136830,
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#TT132820"}
@inproceedings{bb136831,
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#TT132821"}
@inproceedings{bb136832,
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#TT132822"}
@inproceedings{bb136833,
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#TT132823"}
@article{bb136834,
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#TT132824"}
@article{bb136835,
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#TT132825"}
@article{bb136836,
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#TT132826"}
@article{bb136837,
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#TT132827"}
@article{bb136838,
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#TT132828"}
@article{bb136839,
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#TT132829"}
@article{bb136840,
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#TT132830"}
@article{bb136841,
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#TT132831"}
@article{bb136842,
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#TT132832"}
@article{bb136843,
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#TT132833"}
@article{bb136844,
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#TT132834"}
@article{bb136845,
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#TT132835"}
@article{bb136846,
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#TT132836"}
@article{bb136847,
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#TT132837"}
@article{bb136848,
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#TT132838"}
@inproceedings{bb136849,
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#TT132839"}
@article{bb136850,
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#TT132840"}
@inproceedings{bb136851,
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#TT132841"}
@inproceedings{bb136852,
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#TT132842"}
@inproceedings{bb136853,
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#TT132843"}
@article{bb136854,
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#TT132844"}
@inproceedings{bb136855,
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#TT132845"}
@article{bb136856,
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#TT132846"}
@article{bb136857,
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#TT132847"}
@article{bb136858,
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#TT132848"}
@article{bb136859,
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#TT132849"}
@article{bb136860,
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#TT132850"}
@article{bb136861,
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#TT132851"}
@article{bb136862,
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#TT132852"}
@inproceedings{bb136863,
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#TT132853"}
@article{bb136864,
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#TT132854"}
@article{bb136865,
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#TT132855"}
@article{bb136866,
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#TT132856"}
@article{bb136867,
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#TT132857"}
@article{bb136868,
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#TT132858"}
@article{bb136869,
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#TT132859"}
@article{bb136870,
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#TT132860"}
@article{bb136871,
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#TT132861"}
@article{bb136872,
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#TT132862"}
@article{bb136873,
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#TT132863"}
@inproceedings{bb136874,
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#TT132864"}
@article{bb136875,
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#TT132865"}
@article{bb136876,
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#TT132866"}
@article{bb136877,
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#TT132867"}
@article{bb136878,
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#TT132868"}
@article{bb136879,
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#TT132869"}
@article{bb136880,
AUTHOR = "Cao, S. and An, G. and Cen, Y.G. and Yang, Z.Q. and Lin, W.S.",
TITLE = "CAST: Cross-Modal Retrieval and Visual Conditioning for image
captioning",
JOURNAL = PR,
VOLUME = "153",
YEAR = "2024",
PAGES = "110555",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132870"}
@article{bb136881,
AUTHOR = "Song, Z.J. and Hu, Z.Z. and Zhou, Y. and Zhao, Y. and Hong, R.C. and Wang, M.",
TITLE = "Embedded Heterogeneous Attention Transformer for Cross-Lingual Image
Captioning",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "9008-9020",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132871"}
@article{bb136882,
AUTHOR = "Li, Y. and Ji, J.Y. and Sun, X.S. and Zhou, Y. and Luo, Y.P. and Ji, R.R.",
TITLE = "M3ixup: A multi-modal data augmentation approach for image captioning",
JOURNAL = PR,
VOLUME = "158",
YEAR = "2025",
PAGES = "110941",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132872"}
@article{bb136883,
AUTHOR = "Deng, H.Y. and Xie, Y.S. and Wang, Q. and Wang, J.J. and Ruan, W.J. and Liu, W. and Liu, Y.J.",
TITLE = "CDKM: Common and Distinct Knowledge Mining Network With Content
Interaction for Dense Captioning",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "10462-10473",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132873"}
@article{bb136884,
AUTHOR = "Zhang, G.Q. and Kan, S.C. and Shi, L. and Xu, W. and An, G. and Cen, Y.G.",
TITLE = "Cross-scene visual context parsing with large vision-language model",
JOURNAL = PR,
VOLUME = "166",
YEAR = "2025",
PAGES = "111641",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132874"}
@inproceedings{bb136885,
AUTHOR = "Chen, L. and Li, J.S. and Dong, X.Y. and Zhang, P. and He, C.H. and Wang, J.Q. and Zhao, F. and Lin, D.",
TITLE = "ShareGPT4V: Improving Large Multi-modal Models with Better Captions",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVII: 370-387",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132875"}
@inproceedings{bb136886,
AUTHOR = "Jin, B. and Zheng, Y.P. and Li, P.F. and Li, W. and Zheng, Y.H. and Hu, S. and Liu, X.Y. and Zhu, J. and Yan, Z.J. and Sun, H.Y. and Zhan, K. and Jia, P. and Long, X.X. and Chen, Y.L. and Zhao, H.",
TITLE = "Tod3cap: Towards 3d Dense Captioning in Outdoor Scenes",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVIII: 367-384",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132876"}
@inproceedings{bb136887,
AUTHOR = "Kim, M.J. and Lim, H.S. and Lee, S. and Kim, B. and Kim, G.",
TITLE = "Bi-directional Contextual Attention for 3d Dense Captioning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVIII: 385-401",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132877"}
@inproceedings{bb136888,
AUTHOR = "Zhao, Y.Z. and Liu, Y. and Guo, Z.H. and Wu, W.J. and Gong, C. and Ye, Q.X. and Wan, F.",
TITLE = "Controlcap: Controllable Region-level Captioning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXVIII: 21-38",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132878"}
@inproceedings{bb136889,
AUTHOR = "Wang, Z. and Jiang, X.Y. and Xiao, J. and Chen, T. and Chen, L.",
TITLE = "Decap: Towards Generalized Explicit Caption Editing via Diffusion
Mechanism",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIII: 365-381",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132879"}
@inproceedings{bb136890,
AUTHOR = "Mao, S.Q. and Zhang, C.Y. and Su, H. and Song, H. and Shalyminov, I. and Cai, W.D.",
TITLE = "Controllable Contextualized Image Captioning: Directing the Visual
Narrative Through User-defined Highlights",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "L: 464-481",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132880"}
@inproceedings{bb136891,
AUTHOR = "Sarto, S. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
TITLE = "Bridge: Bridging Gaps in Image Captioning Evaluation with Stronger
Visual Cues",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXVIII: 70-87",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132881"}
@inproceedings{bb136892,
AUTHOR = "Matsuda, K. and Wada, Y. and Sugiura, K.",
TITLE = "DENEB: A Hallucination-robust Automatic Evaluation Metric for Image
Captioning",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 166-182",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132882"}
@inproceedings{bb136893,
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#TT132883"}
@inproceedings{bb136894,
AUTHOR = "Hu, W.Z. and Wang, L.X. and Xu, L.F.",
TITLE = "Spatial-Semantic Attention for Grounded Image Captioning",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "61-65",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT132884"}
@inproceedings{bb136895,
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#TT132885"}
@inproceedings{bb136896,
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#TT132886"}
@inproceedings{bb136897,
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#TT132887"}
@inproceedings{bb136898,
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#TT132888"}
@inproceedings{bb136899,
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#TT132889"}
Last update:Jun 4, 2026 at 16:38:45