@inproceedings{bb138000,
        AUTHOR = "Tavakoliy, H.R. and Shetty, R. and Borji, A. and Laaksonen, J.",
        TITLE = "Paying Attention to Descriptions Generated by Image Captioning Models",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2506-2515",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT133988"}

@inproceedings{bb138001,
        AUTHOR = "Lu, J. and Xiong, C. and Parikh, D. and Socher, R.",
        TITLE = "Knowing When to Look: Adaptive Attention via a Visual Sentinel for
Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3242-3250",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT133989"}

@inproceedings{bb138002,
        AUTHOR = "Chen, L. and Zhang, H. and Xiao, J. and Nie, L. and Shao, J. and Liu, W. and Chua, T.S.",
        TITLE = "SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks
for Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6298-6306",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT133990"}

@inproceedings{bb138003,
        AUTHOR = "Zanfir, M. and Marinoiu, E. and Sminchisescu, C.",
        TITLE = "Spatio-Temporal Attention Models for Grounded Video Captioning",
        BOOKTITLE = ACCV16,
        YEAR = "2016",
        PAGES = "IV: 104-119",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT133991"}

@inproceedings{bb138004,
        AUTHOR = "Chen, T.H. and Zeng, K.H. and Hsu, W.T. and Sun, M.",
        TITLE = "Video Captioning via Sentence Augmentation and Spatio-Temporal
Attention",
        BOOKTITLE = Assist16,
        YEAR = "2016",
        PAGES = "I: 269-286",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT133992"}

@inproceedings{bb138005,
        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/match607attic3.html#TT133993"}

@inproceedings{bb138006,
        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/match607attic3.html#TT133994"}

@article{bb138007,
        AUTHOR = "Lu, X. and Wang, B. and Zheng, X. and Li, X.",
        TITLE = "Exploring Models and Data for Remote Sensing Image Caption Generation",
        JOURNAL = GeoRS,
        VOLUME = "56",
        YEAR = "2018",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "2183-2195",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT133995"}

@article{bb138008,
        AUTHOR = "Zhang, X.R. and Wang, X. and Tang, X. and Zhou, H.Y. and Li, C.",
        TITLE = "Description Generation for Remote Sensing Images Using Attribute
Attention Mechanism",
        JOURNAL = RS,
        VOLUME = "11",
        YEAR = "2019",
        NUMBER = "6",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT133996"}

@article{bb138009,
        AUTHOR = "Zhang, Z.Y. and Diao, W.H. and Zhang, W.K. and Yan, M.L. and Gao, X. and Sun, X.",
        TITLE = "LAM: Remote Sensing Image Captioning with Label-Attention Mechanism",
        JOURNAL = RS,
        VOLUME = "11",
        YEAR = "2019",
        NUMBER = "20",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT133997"}

@article{bb138010,
        AUTHOR = "Fu, K. and Li, Y. and Zhang, W.K. and Yu, H.F. and Sun, X.",
        TITLE = "Boosting Memory with a Persistent Memory Mechanism for Remote Sensing
Image Captioning",
        JOURNAL = RS,
        VOLUME = "12",
        YEAR = "2020",
        NUMBER = "11",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT133998"}

@article{bb138011,
        AUTHOR = "Lu, X. and Wang, B. and Zheng, X.",
        TITLE = "Sound Active Attention Framework for Remote Sensing Image Captioning",
        JOURNAL = GeoRS,
        VOLUME = "58",
        YEAR = "2020",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "1985-2000",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT133999"}

@article{bb138012,
        AUTHOR = "Li, Y.Y. and Fang, S.K. and Jiao, L.C. and Liu, R.J. and Shang, R.H.",
        TITLE = "A Multi-Level Attention Model for Remote Sensing Image Captions",
        JOURNAL = RS,
        VOLUME = "12",
        YEAR = "2020",
        NUMBER = "6",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134000"}

@article{bb138013,
        AUTHOR = "Li, X.L. and Zhang, X.T. and Huang, W. and Wang, Q.",
        TITLE = "Truncation Cross Entropy Loss for Remote Sensing Image Captioning",
        JOURNAL = GeoRS,
        VOLUME = "59",
        YEAR = "2021",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "5246-5257",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134001"}

@article{bb138014,
        AUTHOR = "Sumbul, G. and Nayak, S. and Demir, B.",
        TITLE = "SD-RSIC: Summarization-Driven Deep Remote Sensing Image Captioning",
        JOURNAL = GeoRS,
        VOLUME = "59",
        YEAR = "2021",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "6922-6934",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134002"}

@article{bb138015,
        AUTHOR = "Wang, Q. and Huang, W. and Zhang, X.T. and Li, X.L.",
        TITLE = "Word-Sentence Framework for Remote Sensing Image Captioning",
        JOURNAL = GeoRS,
        VOLUME = "59",
        YEAR = "2021",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "10532-10543",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134003"}

@article{bb138016,
        AUTHOR = "Yang, Q.Q. and Ni, Z.H. and Ren, P.",
        TITLE = "Meta captioning:
A meta learning based remote sensing image captioning framework",
        JOURNAL = PandRS,
        VOLUME = "186",
        YEAR = "2022",
        PAGES = "190-200",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134004"}

@article{bb138017,
        AUTHOR = "Liu, Z.Y. and Dong, A.M. and Yu, J.G. and Han, Y.B. and Zhou, Y. and Zhao, K.",
        TITLE = "Scene classification for remote sensing images with self-attention
augmented CNN",
        JOURNAL = IET-IPR,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "11",
        PAGES = "3085-3096",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134005"}

@article{bb138018,
        AUTHOR = "Zhou, H.N. and Du, X.P. and Xia, L. and Li, S.",
        TITLE = "Self-Learning for Few-Shot Remote Sensing Image Captioning",
        JOURNAL = RS,
        VOLUME = "14",
        YEAR = "2022",
        NUMBER = "18",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134006"}

@article{bb138019,
        AUTHOR = "Wang, Q. and Huang, W. and Zhang, X.T. and Li, X.L.",
        TITLE = "GLCM: Global-Local Captioning Model for Remote Sensing Image
Captioning",
        JOURNAL = Cyber,
        VOLUME = "53",
        YEAR = "2023",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "6910-6922",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134007"}

@article{bb138020,
        AUTHOR = "Wang, Q. and Zhou, Q. and Yang, T. and Gao, J.Y. and Ni, W.P. and Wu, J.Z.",
        TITLE = "A benchmark For multi-lingual vision-language learning in remote
sensing image captioning",
        JOURNAL = PR,
        VOLUME = "178",
        YEAR = "2026",
        PAGES = "113399",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134008"}

@article{bb138021,
        AUTHOR = "Yang, T. and Zhou, Q. and Wang, Q.",
        TITLE = "DIA: Deriving linguistic information from auxiliary languages for
remote sensing image captioning",
        JOURNAL = PR,
        VOLUME = "171",
        YEAR = "2026",
        PAGES = "112209",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134009"}

@article{bb138022,
        AUTHOR = "Cheng, Q. and Xu, Y.Q. and Huang, Z.Y.",
        TITLE = "VCC-DiffNet: Visual Conditional Control Diffusion Network for Remote
Sensing Image Captioning",
        JOURNAL = RS,
        VOLUME = "16",
        YEAR = "2024",
        NUMBER = "16",
        PAGES = "2961",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134010"}

@article{bb138023,
        AUTHOR = "Li, Y.P. and Zhang, X.R. and Zhang, T.Y. and Wang, G.C. and Wang, X.L. and Li, S.",
        TITLE = "A Patch-Level Region-Aware Module with a Multi-Label Framework for
Remote Sensing Image Captioning",
        JOURNAL = RS,
        VOLUME = "16",
        YEAR = "2024",
        NUMBER = "21",
        PAGES = "3987",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134011"}

@article{bb138024,
        AUTHOR = "Zhang, K. and Li, P. and Wang, J.Q.",
        TITLE = "A Review of Deep Learning-Based Remote Sensing Image Caption:
Methods, Models, Comparisons and Future Directions",
        JOURNAL = RS,
        VOLUME = "16",
        YEAR = "2024",
        NUMBER = "21",
        PAGES = "4113",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134012"}

@article{bb138025,
        AUTHOR = "Leng, G. and Xiong, Y.J. and Qiu, C.P. and Guo, C.Z.",
        TITLE = "Discrete diffusion models with Refined Language-Image Pre-trained
representations for remote sensing image captioning",
        JOURNAL = PRL,
        VOLUME = "186",
        YEAR = "2024",
        PAGES = "164-169",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134013"}

@article{bb138026,
        AUTHOR = "Li, Y.P. and Zhang, X.R. and Wang, G.C. and Zhang, T.Y.",
        TITLE = "Exploring Difference Semantic Prior Guidance for Remote Sensing Image
Change Captioning",
        JOURNAL = RS,
        VOLUME = "18",
        YEAR = "2026",
        NUMBER = "2",
        PAGES = "232",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134014"}

@article{bb138027,
        AUTHOR = "Wang, S.A. and Ye, X.T. and Gu, Y. and Wang, J.H. and Meng, Y. and Tian, J.X. and Hou, B. and Jiao, L.C.",
        TITLE = "Multi-Label Semantic Feature Fusion for Remote Sensing Image
Captioning",
        JOURNAL = PandRS,
        VOLUME = "184",
        YEAR = "2022",
        PAGES = "1-18",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134015"}

@article{bb138028,
        AUTHOR = "Han, X. and Wu, Z.J. and Li, Y.P. and Zhang, X.R. and Wang, G.C. and Hou, B.",
        TITLE = "CSSA: A Cross-Modal Spatial-Semantic Alignment Framework for Remote
Sensing Image Captioning",
        JOURNAL = RS,
        VOLUME = "18",
        YEAR = "2026",
        NUMBER = "3",
        PAGES = "522",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134016"}

@article{bb138029,
        AUTHOR = "Zhang, X.R. and Li, Y.P. and Wang, X. and Liu, F.X. and Wu, Z.J. and Cheng, X. and Jiao, L.C.",
        TITLE = "Multi-Source Interactive Stair Attention for Remote Sensing Image
Captioning",
        JOURNAL = RS,
        VOLUME = "15",
        YEAR = "2023",
        NUMBER = "3",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134017"}

@article{bb138030,
        AUTHOR = "Li, Y.P. and Zhang, X.R. and Cheng, X. and Tang, X. and Jiao, L.C.",
        TITLE = "Learning Consensus-Aware Semantic Knowledge for Remote Sensing Image
Captioning",
        JOURNAL = PR,
        VOLUME = "145",
        YEAR = "2024",
        PAGES = "109893",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134018"}

@article{bb138031,
        AUTHOR = "Guo, Z. and Liu, H.M. and Ren, Z. and Jiao, L.C. and Gou, S.P. and Li, R.M.",
        TITLE = "Attribute-Based Learning for Remote Sensing Image Captioning in
Unseen Scenes",
        JOURNAL = RS,
        VOLUME = "17",
        YEAR = "2025",
        NUMBER = "7",
        PAGES = "1237",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134019"}

@article{bb138032,
        AUTHOR = "Mehmood, M. and Shahzad, A. and Hussain, F. and Caceres Najarro, L.A. and Usman, M.",
        TITLE = "Remote Sensing Image Captioning via Self-Supervised DINOv3 and
Transformer Fusion",
        JOURNAL = RS,
        VOLUME = "18",
        YEAR = "2026",
        NUMBER = "6",
        PAGES = "846",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134020"}

@article{bb138033,
        AUTHOR = "Zhang, C. and Ren, Z. and Hou, B. and Ning, J.W. and Wang, K. and Li, W.B. and Jiao, L.C.",
        TITLE = "Scale-Aware Prompting With Optimal Transport for Remote Sensing Image
Captioning",
        JOURNAL = IP,
        VOLUME = "35",
        YEAR = "2026",
        PAGES = "4816-4831",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134021"}

@inproceedings{bb138034,
        AUTHOR = "Wei, Y.C. and Li, L. and Geng, S.L.",
        TITLE = "Remote Sensing Image Captioning Using Hire-MLP",
        BOOKTITLE = CVIDL23,
        YEAR = "2023",
        PAGES = "109-112",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134022"}

@inproceedings{bb138035,
        AUTHOR = "Chavhan, R. and Banerjee, B. and Zhu, X.X. and Chaudhuri, S.",
        TITLE = "A Novel Actor Dual-Critic Model for Remote Sensing Image Captioning",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "4918-4925",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607rsic2.html#TT134023"}

@article{bb138036,
        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#TT134024"}

@inproceedings{bb138037,
        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#TT134024"}

@inproceedings{bb138038,
        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#TT134025"}

@inproceedings{bb138039,
        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#TT134026"}

@inproceedings{bb138040,
        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#TT134027"}

@inproceedings{bb138041,
        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#TT134028"}

@inproceedings{bb138042,
        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#TT134029"}

@inproceedings{bb138043,
        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#TT134030"}

@article{bb138044,
        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#TT134031"}

@article{bb138045,
        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#TT134032"}

@article{bb138046,
        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#TT134033"}

@article{bb138047,
        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#TT134034"}

@article{bb138048,
        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#TT134035"}

@article{bb138049,
        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#TT134036"}

@article{bb138050,
        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#TT134037"}

@article{bb138051,
        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#TT134038"}

@article{bb138052,
        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#TT134039"}

@article{bb138053,
        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#TT134040"}

@article{bb138054,
        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#TT134041"}

@article{bb138055,
        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#TT134042"}

@article{bb138056,
        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#TT134043"}

@article{bb138057,
        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#TT134044"}

@article{bb138058,
        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#TT134045"}

@article{bb138059,
        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#TT134046"}

@article{bb138060,
        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#TT134047"}

@article{bb138061,
        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#TT134048"}

@article{bb138062,
        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#TT134049"}

@article{bb138063,
        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#TT134050"}

@article{bb138064,
        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#TT134051"}

@article{bb138065,
        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#TT134052"}

@inproceedings{bb138066,
        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#TT134053"}

@inproceedings{bb138067,
        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#TT134054"}

@inproceedings{bb138068,
        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#TT134055"}

@inproceedings{bb138069,
        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#TT134056"}

@inproceedings{bb138070,
        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#TT134057"}

@inproceedings{bb138071,
        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#TT134058"}

@inproceedings{bb138072,
        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#TT134059"}

@inproceedings{bb138073,
        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#TT134060"}

@inproceedings{bb138074,
        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#TT134061"}

@inproceedings{bb138075,
        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#TT134062"}

@inproceedings{bb138076,
        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#TT134063"}

@inproceedings{bb138077,
        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#TT134064"}

@inproceedings{bb138078,
        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#TT134065"}

@inproceedings{bb138079,
        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#TT134066"}

@inproceedings{bb138080,
        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#TT134067"}

@article{bb138081,
        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#TT134068"}

@article{bb138082,
        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#TT134069"}

@article{bb138083,
        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#TT134070"}

@article{bb138084,
        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#TT134071"}

@article{bb138085,
        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#TT134072"}

@article{bb138086,
        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#TT134073"}

@article{bb138087,
        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#TT134074"}

@article{bb138088,
        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#TT134075"}

@article{bb138089,
        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#TT134076"}

@article{bb138090,
        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#TT134077"}

@article{bb138091,
        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#TT134078"}

@article{bb138092,
        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#TT134079"}

@article{bb138093,
        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#TT134080"}

@article{bb138094,
        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#TT134081"}

@article{bb138095,
        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#TT134082"}

@inproceedings{bb138096,
        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#TT134083"}

@article{bb138097,
        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#TT134084"}

@inproceedings{bb138098,
        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#TT134085"}

@inproceedings{bb138099,
        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#TT134086"}

Last update:Aug 19, 2026 at 13:26:35