@article{bb136400,
        AUTHOR = "Li, L.H. and Tang, S. and Zhang, Y.D. and Deng, L.X. and Tian, Q.",
        TITLE = "GLA: Global-Local Attention for Image Description",
        JOURNAL = MultMed,
        VOLUME = "20",
        YEAR = "2018",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "726-737",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132392"}

@article{bb136401,
        AUTHOR = "Wu, C.L. and Wei, Y.W. and Chu, X.L. and Su, F. and Wang, L.Q.",
        TITLE = "Modeling visual and word-conditional semantic attention for image
captioning",
        JOURNAL = SP:IC,
        VOLUME = "67",
        YEAR = "2018",
        PAGES = "100-107",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132393"}

@article{bb136402,
        AUTHOR = "Xu, N. and Liu, A.A. and Liu, J. and Nie, W.Z. and Su, Y.T.",
        TITLE = "Scene graph captioner:
Image captioning based on structural visual representation",
        JOURNAL = JVCIR,
        VOLUME = "58",
        YEAR = "2019",
        PAGES = "477-485",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132394"}

@article{bb136403,
        AUTHOR = "Ding, S.T. and Qu, S. and Xi, Y.L. and Sangaiah, A.K. and Wan, S.H.",
        TITLE = "Image caption generation with high-level image features",
        JOURNAL = PRL,
        VOLUME = "123",
        YEAR = "2019",
        PAGES = "89-95",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132395"}

@article{bb136404,
        AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
        TITLE = "High-Quality Image Captioning With Fine-Grained and Semantic-Guided
Visual Attention",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1681-1693",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132396"}

@inproceedings{bb136405,
        AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
        TITLE = "Fine-Grained and Semantic-Guided Visual Attention for Image
Captioning",
        BOOKTITLE = WACV18,
        YEAR = "2018",
        PAGES = "1709-1717",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132397"}

@article{bb136406,
        AUTHOR = "Tan, J.H. and Chan, C.S. and Chuah, J.H.",
        TITLE = "COMIC: Toward A Compact Image Captioning Model With Attention",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2686-2696",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132398"}

@article{bb136407,
        AUTHOR = "Yang, L. and Hu, H.F.",
        TITLE = "Visual Skeleton and Reparative Attention for Part-of-Speech image
captioning system",
        JOURNAL = CVIU,
        VOLUME = "189",
        YEAR = "2019",
        PAGES = "102819",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132399"}

@article{bb136408,
        AUTHOR = "Wang, J.B. and Wang, W. and Wang, L. and Wang, Z.Y. and Feng, D.D. and Tan, T.N.",
        TITLE = "Learning Visual Relationship and Context-Aware Attention for Image
Captioning",
        JOURNAL = PR,
        VOLUME = "98",
        YEAR = "2020",
        PAGES = "107075",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132400"}

@article{bb136409,
        AUTHOR = "Wei, H.Y. and Li, Z.X. and Zhang, C.L. and Ma, H.F.",
        TITLE = "The synergy of double attention: Combine sentence-level and
word-level attention for image captioning",
        JOURNAL = CVIU,
        VOLUME = "201",
        YEAR = "2020",
        PAGES = "103068",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132401"}

@article{bb136410,
        AUTHOR = "Ji, J.Z. and Du, Z.R. and Zhang, X.D.",
        TITLE = "Divergent-convergent attention for image captioning",
        JOURNAL = PR,
        VOLUME = "115",
        YEAR = "2021",
        PAGES = "107928",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132402"}

@article{bb136411,
        AUTHOR = "Wei, Y.W. and Wu, C.L. and Jia, Z.Y. and Hu, X.F. and Guo, S. and Shi, H.T.",
        TITLE = "Past is important: Improved image captioning by looking back in time",
        JOURNAL = SP:IC,
        VOLUME = "94",
        YEAR = "2021",
        PAGES = "116183",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132403"}

@article{bb136412,
        AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
        TITLE = "Exploring region relationships implicitly:
Image captioning with visual relationship attention",
        JOURNAL = IVC,
        VOLUME = "109",
        YEAR = "2021",
        PAGES = "104146",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132404"}

@article{bb136413,
        AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
        TITLE = "Exploring Pairwise Relationships Adaptively From Linguistic Context
in Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        PAGES = "3101-3113",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132405"}

@article{bb136414,
        AUTHOR = "Zhong, X. and Nie, G.Z. and Huang, W.X. and Liu, W.X. and Ma, B. and Lin, C.W.",
        TITLE = "Attention-guided image captioning with adaptive global and local
feature fusion",
        JOURNAL = JVCIR,
        VOLUME = "78",
        YEAR = "2021",
        PAGES = "103138",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132406"}

@article{bb136415,
        AUTHOR = "Wan, B.Y. and Jiang, W.H. and Fang, Y.M. and Zhu, M.W. and Li, Q. and Liu, Y.",
        TITLE = "Revisiting image captioning via maximum discrepancy competition",
        JOURNAL = PR,
        VOLUME = "122",
        YEAR = "2022",
        PAGES = "108358",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132407"}

@article{bb136416,
        AUTHOR = "Chen, T.Y. and Li, Z.X. and Wu, J.L. and Ma, H.F. and Su, B.P.",
        TITLE = "Improving image captioning with Pyramid Attention and SC-GAN",
        JOURNAL = IVC,
        VOLUME = "117",
        YEAR = "2022",
        PAGES = "104340",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132408"}

@article{bb136417,
        AUTHOR = "Zhou, Y.J. and Long, J.F. and Xu, S.P. and Shang, L.",
        TITLE = "Attribute-driven image captioning via soft-switch pointer",
        JOURNAL = PRL,
        VOLUME = "152",
        YEAR = "2021",
        PAGES = "34-41",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132409"}

@article{bb136418,
        AUTHOR = "Wang, Q.Z. and Wan, J. and Chan, A.B.",
        TITLE = "On Diversity in Image Captioning: Metrics and Methods",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "1035-1049",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132410"}

@article{bb136419,
        AUTHOR = "Wang, J.N. and Xu, W.J. and Wang, Q.Z. and Chan, A.B.",
        TITLE = "On Distinctive Image Captioning via Comparing and Reweighting",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "2088-2103",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132411"}

@article{bb136420,
        AUTHOR = "Wang, J.N. and Xu, W.J. and Wang, Q.Z. and Chan, A.B.",
        TITLE = "Group-Based Distinctive Image Captioning with Memory Difference
Encoding and Attention",
        JOURNAL = IJCV,
        VOLUME = "133",
        YEAR = "2025",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1435-1455",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132412"}

@inproceedings{bb136421,
        AUTHOR = "Wang, J.N. and Xu, W.J. and Wang, Q.Z. and Chan, A.B.",
        TITLE = "Compare and Reweight:
Distinctive Image Captioning Using Similar Images Sets",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "I:370-386",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132413"}

@article{bb136422,
        AUTHOR = "Liu, M.F. and Hu, H.J. and Li, L.J. and Yu, Y. and Guan, W.L.",
        TITLE = "Chinese Image Caption Generation via Visual Attention and Topic
Modeling",
        JOURNAL = Cyber,
        VOLUME = "52",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "1247-1257",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132414"}

@article{bb136423,
        AUTHOR = "Li, X. and Zhang, W.K. and Sun, X. and Gao, X.",
        TITLE = "Without detection: Two-step clustering features with local-global
attention for image captioning",
        JOURNAL = IET-CV,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "3",
        PAGES = "280-294",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132415"}

@article{bb136424,
        AUTHOR = "Yu, L.T. and Zhang, J. and Wu, Q.",
        TITLE = "Dual Attention on Pyramid Feature Maps for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        NUMBER = "2022",
        PAGES = "1775-1786",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132416"}

@article{bb136425,
        AUTHOR = "Shao, X.J. and Xiang, Z.L. and Li, Y.X. and Zhang, M.J.",
        TITLE = "Variational joint self-attention for image captioning",
        JOURNAL = IET-IPR,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "8",
        PAGES = "2075-2086",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132417"}

@article{bb136426,
        AUTHOR = "Ma, Y.W. and Ji, J.Y. and Sun, X.S. and Zhou, Y. and Ji, R.R.",
        TITLE = "Towards local visual modeling for image captioning",
        JOURNAL = PR,
        VOLUME = "138",
        YEAR = "2023",
        PAGES = "109420",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132418"}

@article{bb136427,
        AUTHOR = "Barati, A. and Farsi, H. and Mohamadzadeh, S.",
        TITLE = "Integration of the latent variable knowledge into deep image
captioning with Bayesian modeling",
        JOURNAL = IET-IPR,
        VOLUME = "17",
        YEAR = "2023",
        NUMBER = "7",
        PAGES = "2256-2271",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132419"}

@article{bb136428,
        AUTHOR = "Ji, J.Y. and Huang, X.Y. and Sun, X.S. and Zhou, Y. and Luo, G. and Cao, L.J. and Liu, J.Z. and Shao, L. and Ji, R.R.",
        TITLE = "Multi-Branch Distance-Sensitive Self-Attention Network for Image
Captioning",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "3962-3974",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132420"}

@article{bb136429,
        AUTHOR = "Cornia, M. and Baraldi, L. and Tal, A. and Cucchiara, R.",
        TITLE = "Fully-attentive iterative networks for region-based controllable
image and video captioning",
        JOURNAL = CVIU,
        VOLUME = "237",
        YEAR = "2023",
        PAGES = "103857",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132421"}

@article{bb136430,
        AUTHOR = "Song, L.F. and Li, F. and Wang, Y. and Liu, Y. and Wang, Y.H. and Xiang, S.M.",
        TITLE = "Image captioning: Semantic selection unit with stacked residual
attention",
        JOURNAL = IVC,
        VOLUME = "144",
        YEAR = "2024",
        PAGES = "104965",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132422"}

@article{bb136431,
        AUTHOR = "Du, R. and Zhang, W.K. and Li, S. and Chen, J.L. and Guo, Z.",
        TITLE = "Spatial guided image captioning: Guiding attention with object's
spatial interaction",
        JOURNAL = IET-IPR,
        VOLUME = "18",
        YEAR = "2024",
        NUMBER = "12",
        PAGES = "3368-3380",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132423"}

@article{bb136432,
        AUTHOR = "Zhang, X.D. and Jia, A. and Ji, J.Z. and Qu, L.Q. and Ye, Q.X.",
        TITLE = "Intra- and Inter-Head Orthogonal Attention for Image Captioning",
        JOURNAL = IP,
        VOLUME = "34",
        YEAR = "2025",
        PAGES = "594-607",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132424"}

@article{bb136433,
        AUTHOR = "Song, L.F. and Wang, Y. and Shi, L. and Yu, J.Z. and Li, F. and Xiang, S.M.",
        TITLE = "Transformer with token attention and attribute prediction for image
captioning",
        JOURNAL = PRL,
        VOLUME = "188",
        YEAR = "2025",
        PAGES = "74-80",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132425"}

@article{bb136434,
        AUTHOR = "Parseh, M.J. and Ghadiri, S.",
        TITLE = "Graph-based image captioning with semantic and spatial features",
        JOURNAL = SP:IC,
        VOLUME = "133",
        YEAR = "2025",
        PAGES = "117273",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132426"}

@inproceedings{bb136435,
        AUTHOR = "Sui, J.H. and Yu, H.M. and Liang, X.Y. and Ping, P.",
        TITLE = "Image Caption Method Based on Graph Attention Network with Global
Context",
        BOOKTITLE = ICIVC22,
        YEAR = "2022",
        PAGES = "480-487",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132427"}

@inproceedings{bb136436,
        AUTHOR = "Popattia, M. and Rafi, M. and Qureshi, R. and Nawaz, S.",
        TITLE = "Guiding Attention using Partial-Order Relationships for Image
Captioning",
        BOOKTITLE = MULA22,
        YEAR = "2022",
        PAGES = "4670-4679",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132428"}

@inproceedings{bb136437,
        AUTHOR = "Deb, T. and Sadmanee, A. and Bhaumik, K.K. and Ali, A.A. and Amin, M.A. and Rahman, A.K.M.M.",
        TITLE = "Variational Stacked Local Attention Networks for Diverse Video
Captioning",
        BOOKTITLE = WACV22,
        YEAR = "2022",
        PAGES = "2493-2502",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132429"}

@inproceedings{bb136438,
        AUTHOR = "Li, Z. and Tran, Q. and Mai, L. and Lin, Z. and Yuille, A.L.",
        TITLE = "Context-Aware Group Captioning via Self-Attention and Contrastive
Features",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "3437-3447",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT132430"}

@inproceedings{bb136439,
        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#TT132431"}

@inproceedings{bb136440,
        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#TT132432"}

@inproceedings{bb136441,
        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#TT132433"}

@inproceedings{bb136442,
        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#TT132434"}

@inproceedings{bb136443,
        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#TT132435"}

@inproceedings{bb136444,
        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#TT132436"}

@inproceedings{bb136445,
        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#TT132437"}

@inproceedings{bb136446,
        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#TT132438"}

@inproceedings{bb136447,
        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#TT132439"}

@inproceedings{bb136448,
        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#TT132440"}

@inproceedings{bb136449,
        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#TT132441"}

@inproceedings{bb136450,
        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#TT132442"}

@inproceedings{bb136451,
        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#TT132443"}

@inproceedings{bb136452,
        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#TT132444"}

@inproceedings{bb136453,
        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#TT132445"}

@inproceedings{bb136454,
        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#TT132446"}

@inproceedings{bb136455,
        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#TT132447"}

@inproceedings{bb136456,
        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#TT132448"}

@inproceedings{bb136457,
        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#TT132449"}

@inproceedings{bb136458,
        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#TT132450"}

@inproceedings{bb136459,
        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#TT132451"}

@inproceedings{bb136460,
        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#TT132452"}

@inproceedings{bb136461,
        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#TT132453"}

@inproceedings{bb136462,
        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#TT132454"}

@inproceedings{bb136463,
        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#TT132455"}

@inproceedings{bb136464,
        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#TT132456"}

@article{bb136465,
        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#TT132457"}

@article{bb136466,
        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#TT132458"}

@article{bb136467,
        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#TT132459"}

@article{bb136468,
        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#TT132460"}

@article{bb136469,
        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#TT132461"}

@article{bb136470,
        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#TT132462"}

@article{bb136471,
        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#TT132463"}

@article{bb136472,
        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#TT132464"}

@article{bb136473,
        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#TT132465"}

@article{bb136474,
        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#TT132466"}

@article{bb136475,
        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#TT132467"}

@article{bb136476,
        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#TT132468"}

@article{bb136477,
        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#TT132469"}

@article{bb136478,
        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#TT132470"}

@article{bb136479,
        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#TT132471"}

@article{bb136480,
        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#TT132472"}

@article{bb136481,
        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#TT132473"}

@article{bb136482,
        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#TT132474"}

@article{bb136483,
        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#TT132475"}

@article{bb136484,
        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#TT132476"}

@article{bb136485,
        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#TT132477"}

@article{bb136486,
        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#TT132478"}

@article{bb136487,
        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#TT132479"}

@article{bb136488,
        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#TT132480"}

@article{bb136489,
        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#TT132481"}

@inproceedings{bb136490,
        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#TT132482"}

@inproceedings{bb136491,
        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#TT132483"}

@article{bb136492,
        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#TT132484"}

@inproceedings{bb136493,
        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#TT132484"}

@inproceedings{bb136494,
        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#TT132485"}

@inproceedings{bb136495,
        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#TT132486"}

@inproceedings{bb136496,
        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#TT132487"}

@inproceedings{bb136497,
        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#TT132488"}

@inproceedings{bb136498,
        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#TT132489"}

@inproceedings{bb136499,
        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#TT132490"}

Last update:May 24, 2026 at 14:46:09