@inproceedings{bb135600,
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#TT131593"}
@inproceedings{bb135601,
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#TT131594"}
@inproceedings{bb135602,
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#TT131595"}
@inproceedings{bb135603,
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#TT131596"}
@inproceedings{bb135604,
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#TT131597"}
@inproceedings{bb135605,
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#TT131598"}
@inproceedings{bb135606,
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#TT131599"}
@inproceedings{bb135607,
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#TT131600"}
@inproceedings{bb135608,
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#TT131601"}
@inproceedings{bb135609,
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#TT131602"}
@inproceedings{bb135610,
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#TT131603"}
@inproceedings{bb135611,
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#TT131604"}
@inproceedings{bb135612,
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#TT131605"}
@inproceedings{bb135613,
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#TT131606"}
@inproceedings{bb135614,
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#TT131607"}
@inproceedings{bb135615,
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#TT131608"}
@inproceedings{bb135616,
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#TT131609"}
@inproceedings{bb135617,
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#TT131610"}
@inproceedings{bb135618,
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#TT131611"}
@inproceedings{bb135619,
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#TT131612"}
@inproceedings{bb135620,
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#TT131613"}
@inproceedings{bb135621,
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#TT131614"}
@inproceedings{bb135622,
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#TT131615"}
@inproceedings{bb135623,
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#TT131616"}
@article{bb135624,
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#TT131617"}
@article{bb135625,
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#TT131618"}
@article{bb135626,
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#TT131619"}
@article{bb135627,
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#TT131620"}
@article{bb135628,
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#TT131621"}
@article{bb135629,
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#TT131622"}
@article{bb135630,
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#TT131623"}
@article{bb135631,
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#TT131624"}
@article{bb135632,
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#TT131625"}
@article{bb135633,
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#TT131626"}
@article{bb135634,
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#TT131627"}
@article{bb135635,
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#TT131628"}
@article{bb135636,
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#TT131629"}
@article{bb135637,
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#TT131630"}
@article{bb135638,
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#TT131631"}
@article{bb135639,
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#TT131632"}
@article{bb135640,
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#TT131633"}
@article{bb135641,
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#TT131634"}
@article{bb135642,
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#TT131635"}
@article{bb135643,
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#TT131636"}
@article{bb135644,
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#TT131637"}
@article{bb135645,
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#TT131638"}
@article{bb135646,
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#TT131639"}
@article{bb135647,
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#TT131640"}
@inproceedings{bb135648,
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#TT131641"}
@inproceedings{bb135649,
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#TT131642"}
@article{bb135650,
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#TT131643"}
@inproceedings{bb135651,
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#TT131643"}
@inproceedings{bb135652,
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#TT131644"}
@inproceedings{bb135653,
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#TT131645"}
@inproceedings{bb135654,
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#TT131646"}
@inproceedings{bb135655,
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#TT131647"}
@inproceedings{bb135656,
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#TT131648"}
@inproceedings{bb135657,
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#TT131649"}
@article{bb135658,
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#TT131650"}
@article{bb135659,
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#TT131651"}
@article{bb135660,
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#TT131652"}
@article{bb135661,
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#TT131653"}
@article{bb135662,
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#TT131654"}
@article{bb135663,
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#TT131655"}
@article{bb135664,
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#TT131656"}
@article{bb135665,
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#TT131657"}
@article{bb135666,
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#TT131658"}
@article{bb135667,
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#TT131659"}
@article{bb135668,
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#TT131660"}
@article{bb135669,
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#TT131661"}
@article{bb135670,
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#TT131662"}
@article{bb135671,
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#TT131663"}
@article{bb135672,
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#TT131664"}
@article{bb135673,
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#TT131665"}
@article{bb135674,
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#TT131666"}
@article{bb135675,
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#TT131667"}
@article{bb135676,
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#TT131668"}
@article{bb135677,
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#TT131669"}
@article{bb135678,
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#TT131670"}
@article{bb135679,
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#TT131671"}
@inproceedings{bb135680,
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#TT131672"}
@inproceedings{bb135681,
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#TT131673"}
@inproceedings{bb135682,
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#TT131674"}
@inproceedings{bb135683,
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#TT131675"}
@inproceedings{bb135684,
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#TT131676"}
@inproceedings{bb135685,
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#TT131677"}
@inproceedings{bb135686,
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#TT131678"}
@inproceedings{bb135687,
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#TT131679"}
@inproceedings{bb135688,
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#TT131680"}
@inproceedings{bb135689,
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#TT131681"}
@inproceedings{bb135690,
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#TT131682"}
@inproceedings{bb135691,
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#TT131683"}
@inproceedings{bb135692,
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#TT131684"}
@inproceedings{bb135693,
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#TT131685"}
@inproceedings{bb135694,
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#TT131686"}
@article{bb135695,
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#TT131687"}
@article{bb135696,
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#TT131688"}
@article{bb135697,
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#TT131689"}
@article{bb135698,
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#TT131690"}
@article{bb135699,
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#TT131691"}
Last update:Feb 26, 2026 at 10:58:24