@inproceedings{bb134900,
        AUTHOR = "Guo, L. and Liu, J. and Zhu, X. and Yao, P. and Lu, S. and Lu, H.",
        TITLE = "Normalized and Geometry-Aware Self-Attention Network for Image
Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10324-10333",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130895"}

@inproceedings{bb134901,
        AUTHOR = "Pan, Y. and Yao, T. and Li, Y. and Mei, T.",
        TITLE = "X-Linear Attention Networks for Image Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10968-10977",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130896"}

@inproceedings{bb134902,
        AUTHOR = "Park, G. and Han, C. and Kim, D. and Yoon, W.J.",
        TITLE = "MHSAN: Multi-Head Self-Attention Network for Visual Semantic
Embedding",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1507-1515",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130897"}

@inproceedings{bb134903,
        AUTHOR = "He, S. and Tavakoli, H.R. and Borji, A. and Pugeault, N.",
        TITLE = "Human Attention in Image Captioning: Dataset and Analysis",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "8528-8537",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130898"}

@inproceedings{bb134904,
        AUTHOR = "Huang, L. and Wang, W. and Chen, J. and Wei, X.",
        TITLE = "Attention on Attention for Image Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4633-4642",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130899"}

@inproceedings{bb134905,
        AUTHOR = "Wei, H.Y. and Li, Z.X. and Zhang, C.L.",
        TITLE = "Image Captioning Based on Visual and Semantic Attention",
        BOOKTITLE = MMMod20,
        YEAR = "2020",
        PAGES = "I:151-162",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130900"}

@inproceedings{bb134906,
        AUTHOR = "Fukui, H. and Hirakawa, T. and Yamashita, T. and Fujiyoshi, H.",
        TITLE = "Attention Branch Network: Learning of Attention Mechanism for Visual
Explanation",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "10697-10706",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130901"}

@inproceedings{bb134907,
        AUTHOR = "Huang, Y. and Li, C. and Li, T. and Wan, W. and Chen, J.",
        TITLE = "Image Captioning with Attribute Refinement",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "1820-1824",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130902"}

@inproceedings{bb134908,
        AUTHOR = "Shi, J. and Li, Y. and Wang, S.",
        TITLE = "Cascade Attention: Multiple Feature Based Learning for Image
Captioning",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "1970-1974",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130903"}

@inproceedings{bb134909,
        AUTHOR = "Xiao, H. and Shi, J.",
        TITLE = "A Novel Attribute Selection Mechanism for Video Captioning",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "619-623",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130904"}

@inproceedings{bb134910,
        AUTHOR = "Wang, Q.Z. and Chan, A.B.",
        TITLE = "Gated Hierarchical Attention for Image Captioning",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "IV:21-37",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130905"}

@inproceedings{bb134911,
        AUTHOR = "Wang, W.X. and Chen, Z.H. and Hu, H.F.",
        TITLE = "Multivariate Attention Network for Image Captioning",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "VI:587-602",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130906"}

@inproceedings{bb134912,
        AUTHOR = "Ghanimifard, M. and Dobnik, S.",
        TITLE = "Knowing When to Look for What and Where: Evaluating Generation of
Spatial Descriptions with Adaptive Attention",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:153-161",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130907"}

@inproceedings{bb134913,
        AUTHOR = "Khademi, M. and Schulte, O.",
        TITLE = "Image Caption Generation with Hierarchical Contextual Visual Spatial
Attention",
        BOOKTITLE = Cognitive18,
        YEAR = "2018",
        PAGES = "2024-20248",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130908"}

@inproceedings{bb134914,
        AUTHOR = "Wang, F. and Gong, X. and Huang, L.",
        TITLE = "Time-Dependent Pre-attention Model for Image Captioning",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3297-3302",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130909"}

@inproceedings{bb134915,
        AUTHOR = "Chen, S. and Zhao, Q.",
        TITLE = "Boosted Attention: Leveraging Human Attention for Image Captioning",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XI: 72-88",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130910"}

@inproceedings{bb134916,
        AUTHOR = "Fang, F. and Wang, H. and Tang, P.",
        TITLE = "Image Captioning with Word Level Attention",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "1278-1282",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130911"}

@inproceedings{bb134917,
        AUTHOR = "Zhu, Z. and Xue, Z. and Yuan, Z.",
        TITLE = "Topic-Guided Attention for Image Captioning",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "2615-2619",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130912"}

@inproceedings{bb134918,
        AUTHOR = "Pedersoli, M. and Lucas, T. and Schmid, C. and Verbeek, J.",
        TITLE = "Areas of Attention for Image Captioning",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1251-1259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT130913"}

@inproceedings{bb134919,
        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#TT130914"}

@inproceedings{bb134920,
        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#TT130915"}

@inproceedings{bb134921,
        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#TT130916"}

@inproceedings{bb134922,
        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#TT130917"}

@inproceedings{bb134923,
        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#TT130918"}

@inproceedings{bb134924,
        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#TT130919"}

@inproceedings{bb134925,
        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#TT130920"}

@article{bb134926,
        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#TT130921"}

@article{bb134927,
        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#TT130922"}

@article{bb134928,
        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#TT130923"}

@article{bb134929,
        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#TT130924"}

@article{bb134930,
        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#TT130925"}

@article{bb134931,
        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#TT130926"}

@article{bb134932,
        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#TT130927"}

@article{bb134933,
        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#TT130928"}

@article{bb134934,
        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#TT130929"}

@article{bb134935,
        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#TT130930"}

@article{bb134936,
        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#TT130931"}

@article{bb134937,
        AUTHOR = "Zhou, H. 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#TT130932"}

@article{bb134938,
        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#TT130933"}

@article{bb134939,
        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#TT130934"}

@article{bb134940,
        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#TT130935"}

@article{bb134941,
        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#TT130936"}

@article{bb134942,
        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#TT130937"}

@article{bb134943,
        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#TT130938"}

@article{bb134944,
        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#TT130939"}

@inproceedings{bb134945,
        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#TT130940"}

@inproceedings{bb134946,
        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#TT130941"}

@article{bb134947,
        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#TT130942"}

@inproceedings{bb134948,
        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#TT130942"}

@inproceedings{bb134949,
        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#TT130943"}

@inproceedings{bb134950,
        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#TT130944"}

@inproceedings{bb134951,
        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#TT130945"}

@inproceedings{bb134952,
        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#TT130946"}

@inproceedings{bb134953,
        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#TT130947"}

@inproceedings{bb134954,
        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#TT130948"}

@article{bb134955,
        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#TT130949"}

@article{bb134956,
        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#TT130950"}

@article{bb134957,
        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#TT130951"}

@article{bb134958,
        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#TT130952"}

@article{bb134959,
        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#TT130953"}

@article{bb134960,
        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#TT130954"}

@article{bb134961,
        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#TT130955"}

@article{bb134962,
        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#TT130956"}

@article{bb134963,
        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#TT130957"}

@article{bb134964,
        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#TT130958"}

@article{bb134965,
        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#TT130959"}

@article{bb134966,
        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#TT130960"}

@article{bb134967,
        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#TT130961"}

@article{bb134968,
        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#TT130962"}

@article{bb134969,
        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#TT130963"}

@article{bb134970,
        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#TT130964"}

@article{bb134971,
        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#TT130965"}

@article{bb134972,
        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#TT130966"}

@article{bb134973,
        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#TT130967"}

@article{bb134974,
        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#TT130968"}

@article{bb134975,
        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#TT130969"}

@article{bb134976,
        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#TT130970"}

@inproceedings{bb134977,
        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#TT130971"}

@inproceedings{bb134978,
        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#TT130972"}

@inproceedings{bb134979,
        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#TT130973"}

@inproceedings{bb134980,
        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#TT130974"}

@inproceedings{bb134981,
        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#TT130975"}

@inproceedings{bb134982,
        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#TT130976"}

@inproceedings{bb134983,
        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#TT130977"}

@inproceedings{bb134984,
        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#TT130978"}

@inproceedings{bb134985,
        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#TT130979"}

@inproceedings{bb134986,
        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#TT130980"}

@inproceedings{bb134987,
        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#TT130981"}

@inproceedings{bb134988,
        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#TT130982"}

@inproceedings{bb134989,
        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#TT130983"}

@inproceedings{bb134990,
        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#TT130984"}

@inproceedings{bb134991,
        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#TT130985"}

@article{bb134992,
        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#TT130986"}

@article{bb134993,
        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#TT130987"}

@article{bb134994,
        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#TT130988"}

@article{bb134995,
        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#TT130989"}

@article{bb134996,
        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#TT130990"}

@article{bb134997,
        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#TT130991"}

@article{bb134998,
        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#TT130992"}

@article{bb134999,
        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#TT130993"}

Last update:Jan 8, 2026 at 12:52:16