@inproceedings{bb122700,
        AUTHOR = "Liu, Y. and Guo, Y.M. and Lew, M.S.",
        TITLE = "What Convnets Make for Image Captioning?",
        BOOKTITLE = MMMod17,
        YEAR = "2017",
        PAGES = "I: 416-428",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118806"}

@inproceedings{bb122701,
        AUTHOR = "Tran, K. and He, X. and Zhang, L. and Sun, J.",
        TITLE = "Rich Image Captioning in the Wild",
        BOOKTITLE = DeepLearn-C16,
        YEAR = "2016",
        PAGES = "434-441",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118807"}

@inproceedings{bb122702,
        AUTHOR = "Wang, Y.L. and Wang, S.H. and Tang, J.L. and Liu, H. and Li, B.X.",
        TITLE = "PPP: Joint Pointwise and Pairwise Image Label Prediction",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "6005-6013",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118808"}

@inproceedings{bb122703,
        AUTHOR = "Yatskar, M. and Ordonez, V. and Zettlemoyer, L. and Farhadi, A.",
        TITLE = "Commonly Uncommon: Semantic Sparsity in Situation Recognition",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6335-6344",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118809"}

@inproceedings{bb122704,
        AUTHOR = "Yatskar, M. and Zettlemoyer, L. and Farhadi, A.",
        TITLE = "Situation Recognition: Visual Semantic Role Labeling for Image
Understanding",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "5534-5542",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118810"}

@inproceedings{bb122705,
        AUTHOR = "Sadhu, A. and Gupta, T. and Yatskar, M. and Nevatia, R. and Kembhavi, A.",
        TITLE = "Visual Semantic Role Labeling for Video Understanding",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "5585-5596",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118811"}

@inproceedings{bb122706,
        AUTHOR = "Kottur, S. and Vedantam, R. and Moura, J.M.F. and Parikh, D.",
        TITLE = "VisualWord2Vec (Vis-W2V):
Learning Visually Grounded Word Embeddings Using Abstract Scenes",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4985-4994",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118812"}

@inproceedings{bb122707,
        AUTHOR = "Zhu, Y. and Groth, O. and Bernstein, M. and Fei Fei, L.",
        TITLE = "Visual7W: Grounded Question Answering in Images",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4995-5004",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118813"}

@inproceedings{bb122708,
        AUTHOR = "Zhang, P. and Goyal, Y. and Summers Stay, D. and Batra, D. and Parikh, D.",
        TITLE = "Yin and Yang: Balancing and Answering Binary Visual Questions",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "5014-5022",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118814"}

@inproceedings{bb122709,
        AUTHOR = "Park, D.H. and Darrell, T.J. and Rohrbach, A.",
        TITLE = "Robust Change Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4623-4632",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118815"}

@inproceedings{bb122710,
        AUTHOR = "Venugopalan, S. and Hendricks, L.A. and Rohrbach, M. and Mooney, R. and Darrell, T.J. and Saenko, K.",
        TITLE = "Captioning Images with Diverse Objects",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1170-1178",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118816"}

@inproceedings{bb122711,
        AUTHOR = "Hendricks, L.A. and Venugopalan, S. and Rohrbach, M. and Mooney, R. and Saenko, K. and Darrell, T.J.",
        TITLE = "Deep Compositional Captioning: Describing Novel Object Categories
without Paired Training Data",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "1-10",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118817"}

@inproceedings{bb122712,
        AUTHOR = "Johnson, J. and Karpathy, A. and Fei Fei, L.",
        TITLE = "DenseCap:
Fully Convolutional Localization Networks for Dense Captioning",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4565-4574",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118818"}

@inproceedings{bb122713,
        AUTHOR = "Lin, X. and Parikh, D.",
        TITLE = "Leveraging Visual Question Answering for Image-Caption Ranking",
        BOOKTITLE = ECCV16,
        YEAR = "2016",
        PAGES = "II: 261-277",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118819"}

@inproceedings{bb122714,
        AUTHOR = "Lin, X. and Parikh, D.",
        TITLE = "Don't just listen, use your imagination:
Leveraging visual common sense for non-visual tasks",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2984-2993",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118820"}

@inproceedings{bb122715,
        AUTHOR = "Chen, T.L. and Zhang, Z.P. and You, Q.Z. and Fang, C. and Wang, Z.W. and Jin, H.L. and Luo, J.B.",
        TITLE = "'Factual' or 'Emotional':
Stylized Image Captioning with Adaptive Learning and Attention",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "X: 527-543",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118821"}

@inproceedings{bb122716,
        AUTHOR = "You, Q.Z. and Jin, H.L. and Wang, Z.W. and Fang, C. and Luo, J.B.",
        TITLE = "Image Captioning with Semantic Attention",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4651-4659",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118822"}

@inproceedings{bb122717,
        AUTHOR = "Jia, X. and Gavves, E. and Fernando, B. and Tuytelaars, T.",
        TITLE = "Guiding the Long-Short Term Memory Model for Image Caption Generation",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "2407-2415",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118823"}

@inproceedings{bb122718,
        AUTHOR = "Chen, X.L. and Zitnick, C.L.",
        TITLE = "Mind's eye:
A recurrent visual representation for image caption generation",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2422-2431",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118824"}

@inproceedings{bb122719,
        AUTHOR = "Vedantam, R. and Zitnick, C.L. and Parikh, D.",
        TITLE = "CIDEr: Consensus-based image description evaluation",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "4566-4575",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118825"}

@inproceedings{bb122720,
        AUTHOR = "Fang, H. and Gupta, S. and Iandola, F. and Srivastava, R.K. and Deng, L. and Dollar, P. and Gao, J.F. and He, X.D. and Mitchell, M. and Platt, J.C. and Zitnick, C.L. and Zweig, G.",
        TITLE = "From captions to visual concepts and back",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "1473-1482",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118826"}

@inproceedings{bb122721,
        AUTHOR = "Ramnath, K. and Baker, S. and Vanderwende, L. and El Saban, M. and Sinha, S.N. and Kannan, A. and Hassan, N. and Galley, M. and Yang, Y. and Ramanan, D. and Bergamo, A. and Torresani, L.",
        TITLE = "AutoCaption: Automatic caption generation for personal photos",
        BOOKTITLE = WACV14,
        YEAR = "2014",
        PAGES = "1050-1057",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118827"}

@article{bb122722,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "Dense Sampling Low-Level Statistics of Local Features",
        JOURNAL = IEICE,
        VOLUME = "E93-D",
        YEAR = "2010",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1727-1736",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118828"}

@inproceedings{bb122723,
        AUTHOR = "Kuniyoshi, Y. and Harada, T. and Nakayama, H.",
        TITLE = "Dense Sampling Low-Level Statistics of Local Features",
        BOOKTITLE = CIVR09,
        YEAR = "2009",
        PAGES = "Article No 17",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118828"}

@inproceedings{bb122724,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "Global Gaussian approach for scene categorization using information
geometry",
        BOOKTITLE = CVPR10,
        YEAR = "2010",
        PAGES = "2336-2343",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118829"}

@inproceedings{bb122725,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "AI Goggles: Real-time Description and Retrieval in the Real World with
Online Learning",
        BOOKTITLE = CRV09,
        YEAR = "2009",
        PAGES = "184-191",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118830"}

@inproceedings{bb122726,
        AUTHOR = "Ushiku, Y. and Yamaguchi, M. and Mukuta, Y. and Harada, T.",
        TITLE = "Common Subspace for Model and Similarity:
Phrase Learning for Caption Generation from Images",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "2668-2676",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118831"}

@inproceedings{bb122727,
        AUTHOR = "Harada, T. and Nakayama, H. and Kuniyoshi, Y.",
        TITLE = "Improving Local Descriptors by Embedding Global and Local Spatial
Information",
        BOOKTITLE = ECCV10,
        YEAR = "2010",
        PAGES = "IV: 736-749",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118832"}

@inproceedings{bb122728,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "Evaluation of dimensionality reduction methods for image
auto-annotation",
        BOOKTITLE = BMVC10,
        YEAR = "2010",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118833"}

@inproceedings{bb122729,
        AUTHOR = "Jin, J. and Nakayama, H.",
        TITLE = "Annotation order matters:
Recurrent Image Annotator for arbitrary length image tagging",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "2452-2457",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118834"}

@article{bb122730,
        AUTHOR = "Tariq, A. and Foroosh, H.",
        TITLE = "A Context-Driven Extractive Framework for Generating Realistic Image
Descriptions",
        JOURNAL = IP,
        VOLUME = "26",
        YEAR = "2017",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "619-632",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118835"}

@article{bb122731,
        AUTHOR = "Cheng, Q. and Zhang, Q. and Fu, P. and Tu, C.H. and Li, S.",
        TITLE = "A survey and analysis on automatic image annotation",
        JOURNAL = PR,
        VOLUME = "79",
        YEAR = "2018",
        PAGES = "242-259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118836"}

@article{bb122732,
        AUTHOR = "Ben Rejeb, I. and Ouni, S. and Barhoumi, W. and Zagrouba, E.",
        TITLE = "Fuzzy VA-Files for multi-label image annotation based on visual content
of regions",
        JOURNAL = SIViP,
        VOLUME = "12",
        YEAR = "2018",
        NUMBER = "5",
        MONTH = "July",
        PAGES = "877-884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT118837"}

@article{bb122733,
        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#TT118838"}

@article{bb122734,
        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#TT118839"}

@article{bb122735,
        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#TT118840"}

@article{bb122736,
        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#TT118841"}

@article{bb122737,
        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#TT118842"}

@article{bb122738,
        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#TT118843"}

@article{bb122739,
        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#TT118844"}

@article{bb122740,
        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#TT118845"}

@article{bb122741,
        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#TT118846"}

@article{bb122742,
        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#TT118847"}

@article{bb122743,
        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#TT118848"}

@article{bb122744,
        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#TT118849"}

@article{bb122745,
        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#TT118850"}

@article{bb122746,
        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#TT118851"}

@article{bb122747,
        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#TT118852"}

@article{bb122748,
        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#TT118853"}

@article{bb122749,
        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#TT118854"}

@article{bb122750,
        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#TT118855"}

@article{bb122751,
        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#TT118856"}

@article{bb122752,
        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#TT118857"}

@inproceedings{bb122753,
        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#TT118858"}

@inproceedings{bb122754,
        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#TT118859"}

@inproceedings{bb122755,
        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#TT118860"}

@inproceedings{bb122756,
        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#TT118861"}

@inproceedings{bb122757,
        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#TT118862"}

@inproceedings{bb122758,
        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#TT118863"}

@inproceedings{bb122759,
        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#TT118864"}

@inproceedings{bb122760,
        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#TT118865"}

@inproceedings{bb122761,
        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#TT118866"}

@inproceedings{bb122762,
        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#TT118867"}

@inproceedings{bb122763,
        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#TT118868"}

@inproceedings{bb122764,
        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#TT118869"}

@inproceedings{bb122765,
        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#TT118870"}

@inproceedings{bb122766,
        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#TT118871"}

@inproceedings{bb122767,
        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#TT118872"}

@inproceedings{bb122768,
        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#TT118873"}

@article{bb122769,
        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#TT118874"}

@article{bb122770,
        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#TT118875"}

@article{bb122771,
        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#TT118876"}

@article{bb122772,
        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#TT118877"}

@article{bb122773,
        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#TT118878"}

@article{bb122774,
        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#TT118879"}

@article{bb122775,
        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#TT118880"}

@article{bb122776,
        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#TT118881"}

@article{bb122777,
        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#TT118882"}

@article{bb122778,
        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#TT118883"}

@article{bb122779,
        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#TT118884"}

@article{bb122780,
        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#TT118885"}

@article{bb122781,
        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#TT118886"}

@article{bb122782,
        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#TT118887"}

@article{bb122783,
        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#TT118888"}

@inproceedings{bb122784,
        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#TT118889"}

@article{bb122785,
        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#TT118890"}

@inproceedings{bb122786,
        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#TT118891"}

@inproceedings{bb122787,
        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#TT118892"}

@inproceedings{bb122788,
        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#TT118893"}

@article{bb122789,
        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#TT118894"}

@inproceedings{bb122790,
        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#TT118895"}

@article{bb122791,
        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#TT118896"}

@article{bb122792,
        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#TT118897"}

@article{bb122793,
        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#TT118898"}

@article{bb122794,
        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#TT118899"}

@article{bb122795,
        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#TT118900"}

@article{bb122796,
        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#TT118901"}

@article{bb122797,
        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#TT118902"}

@inproceedings{bb122798,
        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#TT118903"}

@article{bb122799,
        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#TT118904"}

Last update:Jun 17, 2024 at 21:38:11