@inproceedings{bb135700,
        AUTHOR = "Lampert, C.H.",
        TITLE = "Partitioning of image datasets using discriminative context information",
        BOOKTITLE = CVPR08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT131694"}

@inproceedings{bb135701,
        AUTHOR = "Hansen, C. and Henderson, T.C.",
        TITLE = "Towards the Automatic Generation of Recognition Strategies",
        BOOKTITLE = ICCV88,
        YEAR = "1988",
        PAGES = "275-279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT131695"}

@inproceedings{bb135702,
        AUTHOR = "Cantoni, V. and Cei, U. and Ferretti, M. and Lombardi, L.",
        TITLE = "Towards an Automatic Construction of Object Recognition Strategies",
        BOOKTITLE = ICPR88,
        YEAR = "1988",
        PAGES = "I: 371-374",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT131696"}

@inproceedings{bb135703,
        AUTHOR = "Cova, G. and Griffini, A. and Lombardi, L.",
        TITLE = "Object Recognition Strategy in a Multi-Resolution System",
        BOOKTITLE = CIAP89,
        YEAR = "1989",
        PAGES = "729-733",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT131697"}

@article{bb135704,
        AUTHOR = "Feng, Y.S. and Lapata, M.",
        TITLE = "Automatic Caption Generation for News Images",
        JOURNAL = PAMI,
        VOLUME = "35",
        YEAR = "2013",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "797-812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131698"}

@article{bb135705,
        AUTHOR = "Vinyals, O. and Toshev, A. and Bengio, S. and Erhan, D.",
        TITLE = "Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning
Challenge",
        JOURNAL = PAMI,
        VOLUME = "39",
        YEAR = "2017",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "652-663",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131699"}

@inproceedings{bb135706,
        AUTHOR = "Vinyals, O. and Toshev, A. and Bengio, S. and Erhan, D.",
        TITLE = "Show and tell: A neural image caption generator",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "3156-3164",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131700"}

@article{bb135707,
        AUTHOR = "Wang, J.Y. and Zhu, X.T. and Gong, S.G.",
        TITLE = "Discovering visual concept structure with sparse and incomplete tags",
        JOURNAL = AI,
        VOLUME = "250",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "16-36",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131701"}

@article{bb135708,
        AUTHOR = "Kilickaya, M. and Akkus, B.K. and Cakici, R. and Erdem, A. and Erdem, E. and Ikizler Cinbis, N.",
        TITLE = "Data-driven image captioning via salient region discovery",
        JOURNAL = IET-CV,
        VOLUME = "11",
        YEAR = "2017",
        NUMBER = "6",
        MONTH = "September",
        PAGES = "398-406",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131702"}

@article{bb135709,
        AUTHOR = "He, X.D. and Deng, L.",
        TITLE = "Deep Learning for Image-to-Text Generation: A Technical Overview",
        JOURNAL = SPMag,
        VOLUME = "34",
        YEAR = "2017",
        NUMBER = "6",
        MONTH = "November",
        PAGES = "109-116",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131703"}

@article{bb135710,
        AUTHOR = "Deng, L. and He, X.D.",
        TITLE = "Deep Learning for Image-to-Text Generation: A Technical Overview",
        JOURNAL = SPMag,
        VOLUME = "35",
        YEAR = "2018",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "178",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131703"}

@article{bb135711,
        AUTHOR = "Zhang, M. and Yang, Y. and Zhang, H. and Ji, Y. and Shen, H.T. and Chua, T.",
        TITLE = "More is Better: Precise and Detailed Image Captioning Using Online
Positive Recall and Missing Concepts Mining",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "32-44",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131704"}

@article{bb135712,
        AUTHOR = "Gella, S. and Keller, F. and Lapata, M.",
        TITLE = "Disambiguating Visual Verbs",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "311-322",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131705"}

@article{bb135713,
        AUTHOR = "He, X.W. and Shi, B.G. and Bai, X. and Xia, G.S. and Zhang, Z.X. and Dong, W.S.",
        TITLE = "Image Caption Generation with Part of Speech Guidance",
        JOURNAL = PRL,
        VOLUME = "119",
        YEAR = "2019",
        PAGES = "229-237",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131706"}

@article{bb135714,
        AUTHOR = "Xiao, X.Y. and Wang, L.F. and Ding, K. and Xiang, S.M. and Pan, C.H.",
        TITLE = "Dense semantic embedding network for image captioning",
        JOURNAL = PR,
        VOLUME = "90",
        YEAR = "2019",
        PAGES = "285-296",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131707"}

@article{bb135715,
        AUTHOR = "Liu, X.X. and Xu, Q.Y. and Wang, N.",
        TITLE = "A survey on deep neural network-based image captioning",
        JOURNAL = VC,
        VOLUME = "35",
        YEAR = "2019",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "445-470",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131708"}

@article{bb135716,
        AUTHOR = "Hossain, M.Z. and Sohel, F. and Shiratuddin, M.F. and Laga, H.",
        TITLE = "A Comprehensive Survey of Deep Learning for Image Captioning",
        JOURNAL = Surveys,
        VOLUME = "51",
        YEAR = "2019",
        NUMBER = "6",
        MONTH = "February",
        PAGES = "Article No 118",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131709"}

@article{bb135717,
        AUTHOR = "Li, X. and Jiang, S.",
        TITLE = "Know More Say Less: Image Captioning Based on Scene Graphs",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "2117-2130",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131710"}

@article{bb135718,
        AUTHOR = "Sharif, N. and White, L. and Bennamoun, M. and Liu, W. and Shah, S.A.A.",
        TITLE = "LCEval: Learned Composite Metric for Caption Evaluation",
        JOURNAL = IJCV,
        VOLUME = "127",
        YEAR = "2019",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "1586-1610",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131711"}

@article{bb135719,
        AUTHOR = "Zhou, L. and Zhang, Y. and Jiang, Y. and Zhang, T. and Fan, W.",
        TITLE = "Re-Caption: Saliency-Enhanced Image Captioning Through Two-Phase
Learning",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        NUMBER = "1",
        PAGES = "694-709",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131712"}

@article{bb135720,
        AUTHOR = "Xiao, X. and Wang, L. and Ding, K. and Xiang, S. and Pan, C.",
        TITLE = "Deep Hierarchical Encoder-Decoder Network for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "2942-2956",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131713"}

@article{bb135721,
        AUTHOR = "Jiang, T. and Zhang, Z. and Yang, Y.",
        TITLE = "Modeling coverage with semantic embedding for image caption generation",
        JOURNAL = VC,
        VOLUME = "35",
        YEAR = "2018",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "1655-1665",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131714"}

@article{bb135722,
        AUTHOR = "Chen, X.H. and Zhang, M.X. and Wang, Z. and Zuo, L. and Li, B. and Yang, Y.",
        TITLE = "Leveraging unpaired out-of-domain data for image captioning",
        JOURNAL = PRL,
        VOLUME = "132",
        YEAR = "2020",
        PAGES = "132-140",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131715"}

@article{bb135723,
        AUTHOR = "Xu, N. and Zhang, H. and Liu, A. and Nie, W. and Su, Y. and Nie, J. and Zhang, Y.",
        TITLE = "Multi-Level Policy and Reward-Based Deep Reinforcement Learning
Framework for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1372-1383",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131716"}

@article{bb135724,
        AUTHOR = "Guo, L. and Liu, J. and Lu, S. and Lu, H.",
        TITLE = "Show, Tell, and Polish: Ruminant Decoding for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "2149-2162",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131717"}

@article{bb135725,
        AUTHOR = "Feng, Q. and Wu, Y. and Fan, H. and Yan, C. and Xu, M. and Yang, Y.",
        TITLE = "Cascaded Revision Network for Novel Object Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "30",
        YEAR = "2020",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "3413-3421",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131718"}

@article{bb135726,
        AUTHOR = "Shilpa, M. and He, J. and Zhao, Y.J. and Sun, B. and Yu, L.J.",
        TITLE = "Feedback evaluations to promote image captioning",
        JOURNAL = IET-IPR,
        VOLUME = "14",
        YEAR = "2020",
        NUMBER = "13",
        MONTH = "November",
        PAGES = "3021-3027",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131719"}

@article{bb135727,
        AUTHOR = "Liu, H. and Zhang, S. and Lin, K. and Wen, J. and Li, J. and Hu, X.",
        TITLE = "Vocabulary-Wide Credit Assignment for Training Image Captioning
Models",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "2450-2460",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131720"}

@article{bb135728,
        AUTHOR = "Xu, N. and Tian, H.S. and Wang, Y.H. and Nie, W.Z. and Song, D. and Liu, A.A. and Liu, W.",
        TITLE = "Coupled-dynamic learning for vision and language:
Exploring Interaction between different tasks",
        JOURNAL = PR,
        VOLUME = "113",
        YEAR = "2021",
        PAGES = "107829",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131721"}

@article{bb135729,
        AUTHOR = "Yang, L. and Wang, H. and Tang, P. and Li, Q.",
        TITLE = "CaptionNet: A Tailor-made Recurrent Neural Network for Generating
Image Descriptions",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "835-845",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131722"}

@article{bb135730,
        AUTHOR = "Liu, A.A. and Wang, Y.H. and Xu, N. and Liu, S. and Li, X.Y.",
        TITLE = "Scene-Graph-Guided message passing network for dense captioning",
        JOURNAL = PRL,
        VOLUME = "145",
        YEAR = "2021",
        PAGES = "187-193",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131723"}

@article{bb135731,
        AUTHOR = "Zhang, L. and Zhang, Y.S. and Zhao, X. and Zou, Z.X.",
        TITLE = "Image captioning via proximal policy optimization",
        JOURNAL = IVC,
        VOLUME = "108",
        YEAR = "2021",
        PAGES = "104126",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131724"}

@article{bb135732,
        AUTHOR = "Wu, J. and Chen, T.S. and Wu, H.F. and Yang, Z. and Luo, G.C. and Lin, L.",
        TITLE = "Fine-Grained Image Captioning With Global-Local Discriminative
Objective",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "2413-2427",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131725"}

@article{bb135733,
        AUTHOR = "Wu, L.X. and Xu, M. and Sang, L. and Yao, T. and Mei, T.",
        TITLE = "Noise Augmented Double-Stream Graph Convolutional Networks for Image
Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "31",
        YEAR = "2021",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "3118-3127",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131726"}

@article{bb135734,
        AUTHOR = "Nivedita, M. and Chandrashekar, P. and Mahapatra, S. and Phamila, Y.A.V. and Selvaperumal, S.K.",
        TITLE = "Image Captioning for Video Surveillance System using Neural Networks",
        JOURNAL = IJIG,
        VOLUME = "21",
        YEAR = "2021",
        NUMBER = "4",
        MONTH = "October",
        PAGES = "2150044",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131727"}

@article{bb135735,
        AUTHOR = "Zha, Z.J. and Liu, D. and Zhang, H.W. and Zhang, Y.D. and Wu, F.",
        TITLE = "Context-Aware Visual Policy Network for Fine-Grained Image Captioning",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "710-722",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131728"}

@article{bb135736,
        AUTHOR = "Luo, G.F. and Cheng, L.J. and Jing, C. and Zhao, C. and Song, G.Z.",
        TITLE = "A thorough review of models, evaluation metrics, and datasets on
image captioning",
        JOURNAL = IET-IPR,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "2",
        PAGES = "311-332",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131729"}

@article{bb135737,
        AUTHOR = "Ben, H.X. and Pan, Y.W. and Li, Y. and Yao, T. and Hong, R.C. and Wang, M. and Mei, T.",
        TITLE = "Unpaired Image Captioning With semantic-Constrained Self-Learning",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        PAGES = "904-916",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131730"}

@article{bb135738,
        AUTHOR = "Song, P.P. and Guo, D. and Zhou, J.X. and Xu, M.L. and Wang, M.",
        TITLE = "Memorial GAN With Joint Semantic Optimization for Unpaired Image
Captioning",
        JOURNAL = Cyber,
        VOLUME = "53",
        YEAR = "2023",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "4388-4399",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131731"}

@inproceedings{bb135739,
        AUTHOR = "Li, Y. and Yao, T. and Pan, Y.W. and Chao, H.Y. and Mei, T.",
        TITLE = "Pointing Novel Objects in Image Captioning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "12489-12498",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131732"}

@article{bb135740,
        AUTHOR = "Yang, X. and Zhang, H.W. and Cai, J.F.",
        TITLE = "Auto-Encoding and Distilling Scene Graphs for Image Captioning",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "2313-2327",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131733"}

@article{bb135741,
        AUTHOR = "Yang, X. and Zhang, H.W. and Cai, J.F.",
        TITLE = "Deconfounded Image Captioning: A Causal Retrospect",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "12996-13010",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131734"}

@inproceedings{bb135742,
        AUTHOR = "Yang, X. and Tang, K. and Zhang, H.W. and Cai, J.F.",
        TITLE = "Auto-Encoding Scene Graphs for Image Captioning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "10677-10686",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131735"}

@article{bb135743,
        AUTHOR = "Yang, Z.P. and Wang, P.B. and Chu, T.S. and Yang, J.",
        TITLE = "Human-Centric Image Captioning",
        JOURNAL = PR,
        VOLUME = "126",
        YEAR = "2022",
        PAGES = "108545",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131736"}

@article{bb135744,
        AUTHOR = "Zhang, M. and Chen, J.X. and Li, P.F. and Jiang, M. and Zhou, Z.",
        TITLE = "Topic scene graphs for image captioning",
        JOURNAL = IET-CV,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "4",
        PAGES = "364-375",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131737"}

@article{bb135745,
        AUTHOR = "Yu, Q. and Zhang, C.X. and Weng, L. and Xiang, S.M. and Pan, C.H.",
        TITLE = "Scene captioning with deep fusion of images and point clouds",
        JOURNAL = PRL,
        VOLUME = "158",
        YEAR = "2022",
        PAGES = "9-15",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131738"}

@article{bb135746,
        AUTHOR = "Chaudhari, C.P. and Devane, S.",
        TITLE = "Improved Framework using Rider Optimization Algorithm for Precise Image
Caption Generation",
        JOURNAL = IJIG,
        VOLUME = "22",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "April",
        PAGES = "2250021",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131739"}

@article{bb135747,
        AUTHOR = "Li, Y.C. and Wu, C. and Li, L. and Liu, Y.H. and Zhu, J.",
        TITLE = "Caption Generation From Road Images for Traffic Scene Modeling",
        JOURNAL = ITS,
        VOLUME = "23",
        YEAR = "2022",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "7805-7816",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131740"}

@article{bb135748,
        AUTHOR = "Wang, Y.H. and Xu, N. and Liu, A.A. and Li, W.H. and Zhang, Y.D.",
        TITLE = "High-Order Interaction Learning for Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "4417-4430",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131741"}

@article{bb135749,
        AUTHOR = "Guo, D.D. and Lu, R.Y. and Chen, B. and Zeng, Z.Q. and Zhou, M.Y.",
        TITLE = "Matching Visual Features to Hierarchical Semantic Topics for Image
Paragraph Captioning",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1920-1937",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131742"}

@article{bb135750,
        AUTHOR = "Demirel, B. and Cinbis, R.G.",
        TITLE = "Caption generation on scenes with seen and unseen object categories",
        JOURNAL = IVC,
        VOLUME = "124",
        YEAR = "2022",
        PAGES = "104515",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131743"}

@article{bb135751,
        AUTHOR = "Wu, X.X. and Zhao, W.T. and Luo, J.B.",
        TITLE = "Learning Cooperative Neural Modules for Stylized Image Captioning",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2305-2320",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131744"}

@article{bb135752,
        AUTHOR = "Stefanini, M. and Cornia, M. and Baraldi, L. and Cascianelli, S. and Fiameni, G. and Cucchiara, R.",
        TITLE = "From Show to Tell: A Survey on Deep Learning-Based Image Captioning",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "539-559",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131745"}

@article{bb135753,
        AUTHOR = "Wu, Y. and Jiang, L. and Yang, Y.",
        TITLE = "Switchable Novel Object Captioner",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "1162-1173",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131746"}

@article{bb135754,
        AUTHOR = "Yang, X. and Zhang, H.W. and Gao, C.Y. and Cai, J.F.",
        TITLE = "Learning to Collocate Visual-Linguistic Neural Modules for Image
Captioning",
        JOURNAL = IJCV,
        VOLUME = "131",
        YEAR = "2023",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "82-100",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131747"}

@inproceedings{bb135755,
        AUTHOR = "Yang, X. and Zhang, H.W. and Cai, J.F.",
        TITLE = "Learning to Collocate Neural Modules for Image Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4249-4259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131748"}

@article{bb135756,
        AUTHOR = "Feng, J.L. and Zhao, J.P.",
        TITLE = "Effectively Utilizing the Category Labels for Image Captioning",
        JOURNAL = IEICE,
        VOLUME = "E106-D",
        YEAR = "2023",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "617-624",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131749"}

@article{bb135757,
        AUTHOR = "Wang, D.P. and Hu, Z.Z. and Zhou, Y. and Hong, R.C. and Wang, M.",
        TITLE = "A Text-Guided Generation and Refinement Model for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "2966-2977",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131750"}

@article{bb135758,
        AUTHOR = "Al Qatf, M. and Wang, X. and Hawbani, A. and Abdussalam, A. and Alsamhi, S.H.",
        TITLE = "Image Captioning With Novel Topics Guidance and Retrieval-Based
Topics Re-Weighting",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "5984-5999",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131751"}

@article{bb135759,
        AUTHOR = "Zhu, P.P. and Wang, X. and Luo, Y. and Sun, Z.L. and Zheng, W.S. and Wang, Y.W. and Chen, C.",
        TITLE = "Unpaired Image Captioning by Image-Level Weakly-Supervised Visual
Concept Recognition",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "6702-6716",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131752"}

@article{bb135760,
        AUTHOR = "Hu, N.N. and Ming, Y. and Fan, C.X. and Feng, F. and Lyu, B.Y.",
        TITLE = "TSFNet: Triple-Steam Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "6904-6916",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131753"}

@article{bb135761,
        AUTHOR = "Gonzalez Chavez, O. and Ruiz, G. and Moctezuma, D. and Ramirez delReal, T.",
        TITLE = "Are metrics measuring what they should? An evaluation of Image
Captioning task metrics",
        JOURNAL = SP:IC,
        VOLUME = "120",
        YEAR = "2024",
        PAGES = "117071",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131754"}

@article{bb135762,
        AUTHOR = "Padate, R. and Jain, A. and Kalla, M. and Sharma, A.",
        TITLE = "A Widespread Assessment and Open Issues on Image Captioning Models",
        JOURNAL = IJIG,
        VOLUME = "23",
        YEAR = "2023",
        NUMBER = "6 2023",
        PAGES = "2350057",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131755"}

@article{bb135763,
        AUTHOR = "Shao, Z. and Han, J.G. and Debattista, K. and Pang, Y.W.",
        TITLE = "Textual Context-Aware Dense Captioning With Diverse Words",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "8753-8766",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131756"}

@article{bb135764,
        AUTHOR = "Cheng, J. and Wu, F. and Liu, L. and Zhang, Q. and Rutkowski, L. and Tao, D.C.",
        TITLE = "InDecGAN: Learning to Generate Complex Images From Captions via
Independent Object-Level Decomposition and Enhancement",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "8279-8293",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131757"}

@article{bb135765,
        AUTHOR = "Ding, N. and Deng, C.R. and Tan, M.K. and Du, Q. and Ge, Z.W. and Wu, Q.",
        TITLE = "Image Captioning With Controllable and Adaptive Length Levels",
        JOURNAL = PAMI,
        VOLUME = "46",
        YEAR = "2024",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "764-779",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131758"}

@inproceedings{bb135766,
        AUTHOR = "Xu, G.H. and Niu, S.C. and Tan, M.K. and Luo, Y.C. and Du, Q. and Wu, Q.",
        TITLE = "Towards Accurate Text-based Image Captioning with Content Diversity
Exploration",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "12632-12641",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131759"}

@article{bb135767,
        AUTHOR = "Zhu, P.P. and Wang, X. and Zhu, L. and Sun, Z.L. and Zheng, W.S. and Wang, Y.W. and Chen, C.W.",
        TITLE = "Prompt-Based Learning for Unpaired Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "379-393",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131760"}

@article{bb135768,
        AUTHOR = "Liu, A.A. and Zhai, Y.C. and Xu, N. and Tian, H. and Nie, W.Z. and Zhang, Y.D.",
        TITLE = "Event-Aware Retrospective Learning for Knowledge-Based Image
Captioning",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "4898-4911",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131761"}

@article{bb135769,
        AUTHOR = "Ajankar, S. and Dutta, T.",
        TITLE = "Image-Relevant Entities Knowledge-Aware News Image Captioning",
        JOURNAL = MultMedMag,
        VOLUME = "31",
        YEAR = "2024",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "88-98",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131762"}

@article{bb135770,
        AUTHOR = "Dai, Z.Z. and Tran, V. and Markham, A. and Trigoni, N. and Rahman, M.A. and Wijayasingha, L.N.S. and Stankovic, J. and Li, C.",
        TITLE = "EgoCap and EgoFormer:
First-person image captioning with context fusion",
        JOURNAL = PRL,
        VOLUME = "181",
        YEAR = "2024",
        PAGES = "50-56",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131763"}

@article{bb135771,
        AUTHOR = "Shao, Z. and Han, J.G. and Debattista, K. and Pang, Y.W.",
        TITLE = "DCMSTRD: End-to-end Dense Captioning via Multi-Scale Transformer
Decoding",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "7581-7593",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131764"}

@article{bb135772,
        AUTHOR = "Cornia, M. and Baraldi, L. and Fiameni, G. and Cucchiara, R.",
        TITLE = "Generating More Pertinent Captions by Leveraging Semantics and Style on
Multi-Source Datasets",
        JOURNAL = IJCV,
        VOLUME = "132",
        YEAR = "2024",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1701-1720",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131765"}

@inproceedings{bb135773,
        AUTHOR = "Barraco, M. and Sarto, S. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "With a Little Help from your own Past: Prototypical Memory Networks
for Image Captioning",
        BOOKTITLE = ICCV23,
        YEAR = "2023",
        PAGES = "3009-3019",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131766"}

@inproceedings{bb135774,
        AUTHOR = "Barraco, M. and Stefanini, M. and Cornia, M. and Cascianelli, S. and Baraldi, L. and Cucchiara, R.",
        TITLE = "CaMEL: Mean Teacher Learning for Image Captioning",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "4087-4094",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131767"}

@inproceedings{bb135775,
        AUTHOR = "Cornia, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "Show, Control and Tell: A Framework for Generating Controllable and
Grounded Captions",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8299-8308",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131768"}

@article{bb135776,
        AUTHOR = "Wang, L.X. and Qiu, H.Q. and Qiu, B. and Meng, F.M. and Wu, Q.B. and Li, H.L.",
        TITLE = "TridentCap: Image-Fact-Style Trident Semantic Framework for Stylized
Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "3563-3575",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131769"}

@article{bb135777,
        AUTHOR = "Zhang, H.N. and Zeng, P.P. and Gao, L. and Lyu, X.Y. and Song, J.K. and Shen, H.T.",
        TITLE = "SPT: Spatial Pyramid Transformer for Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "4829-4842",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131770"}

@article{bb135778,
        AUTHOR = "Wang, H.Y. and Song, K. and Jiang, X. and He, Z.Q.",
        TITLE = "ragBERT: Relationship-aligned and grammar-wise BERT model for image
captioning",
        JOURNAL = IVC,
        VOLUME = "148",
        YEAR = "2024",
        PAGES = "105105",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131771"}

@article{bb135779,
        AUTHOR = "Li, J.Y. and Zhang, L. and Zhang, K. and Hu, B. and Xie, H.T. and Mao, Z.D.",
        TITLE = "Cascade Semantic Prompt Alignment Network for Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "5266-5281",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131772"}

@article{bb135780,
        AUTHOR = "Zou, Y. and Liao, S.Y. and Wang, Q.F.",
        TITLE = "Chinese image captioning with fusion encoder and visual keyword
search",
        JOURNAL = IET-IPR,
        VOLUME = "18",
        YEAR = "2024",
        NUMBER = "11",
        PAGES = "3055-3069",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131773"}

@article{bb135781,
        AUTHOR = "Chen, S.J. and Zhu, H.Y. and Li, M.S. and Chen, X. and Guo, P. and Lei, Y.J. and Yu, G. and Li, T. and Chen, T.",
        TITLE = "Vote2Cap-DETR++: Decoupling Localization and Describing for
End-to-End 3D Dense Captioning",
        JOURNAL = PAMI,
        VOLUME = "46",
        YEAR = "2024",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "7331-7347",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131774"}

@inproceedings{bb135782,
        AUTHOR = "Chen, S.J. and Zhu, H.Y. and Chen, X. and Lei, Y.J. and Yu, G. and Chen, T.",
        TITLE = "End-to-End 3D Dense Captioning with Vote2Cap-DETR",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "11124-11133",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131775"}

@article{bb135783,
        AUTHOR = "Lv, F.X. and Wang, R. and Jing, L.H. and Dai, P.W.",
        TITLE = "HIST: Hierarchical and sequential transformer for image captioning",
        JOURNAL = IET-CV,
        VOLUME = "18",
        YEAR = "2024",
        NUMBER = "7",
        PAGES = "1043-1056",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131776"}

@article{bb135784,
        AUTHOR = "Yang, X.B. and He, S. and Zhang, J. and Ma, S. and Hou, Z.Q. and Sun, W.",
        TITLE = "Memory positional encoding for image captioning",
        JOURNAL = SP:IC,
        VOLUME = "130",
        YEAR = "2025",
        PAGES = "117201",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131777"}

@article{bb135785,
        AUTHOR = "Wang, L. and Chen, H.P. and Liu, Y. and Lyu, Y.D.",
        TITLE = "Regular Constrained Multimodal Fusion for Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "11900-11913",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131778"}

@article{bb135786,
        AUTHOR = "Yang, Z. and Han, B. and Gao, X.B. and Zhan, Z.H.",
        TITLE = "Eye-movement-prompted large image captioning model",
        JOURNAL = PR,
        VOLUME = "159",
        YEAR = "2025",
        PAGES = "111097",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131779"}

@article{bb135787,
        AUTHOR = "Liang, X. and Li, C. and Tian, L.H.",
        TITLE = "Generative adversarial network for semi-supervised image captioning",
        JOURNAL = CVIU,
        VOLUME = "249",
        YEAR = "2024",
        PAGES = "104199",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131780"}

@article{bb135788,
        AUTHOR = "Zheng, Q. and Wang, C.Y. and Wang, D.D.",
        TITLE = "Bypass network for semantics driven image paragraph captioning",
        JOURNAL = CVIU,
        VOLUME = "249",
        YEAR = "2024",
        PAGES = "104154",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131781"}

@article{bb135789,
        AUTHOR = "Meena, P. and Kumar, H. and Yadav, S.K.",
        TITLE = "A Volumetric Saliency Guided Image Summarization for RGB-D Indoor
Scene Classification",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "10917-10929",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131782"}

@article{bb135790,
        AUTHOR = "Rahman, M.M. and Uzzaman, A. and Sami, S.I. and Khatun, F. and Bhuiyan, M.A.A.",
        TITLE = "A comprehensive construction of deep neural network-based
encoder-decoder framework for automatic image captioning systems",
        JOURNAL = IET-IPR,
        VOLUME = "18",
        YEAR = "2024",
        NUMBER = "14",
        PAGES = "4778-4798",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131783"}

@article{bb135791,
        AUTHOR = "Wang, Z. and Xiao, J. and Zhuang, Y.T. and Gao, F. and Shao, J. and Chen, L.",
        TITLE = "Learning Combinatorial Prompts for Universal Controllable Image
Captioning",
        JOURNAL = IJCV,
        VOLUME = "133",
        YEAR = "2025",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "129-150",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131784"}

@article{bb135792,
        AUTHOR = "Zhang, C. and Tao, L. and Yamasaki, T.",
        TITLE = "UTStyleCap4K: Generating Image Captions with Sentimental Styles",
        JOURNAL = IEICE,
        VOLUME = "E108-D",
        YEAR = "2025",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "266-276",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131785"}

@article{bb135793,
        AUTHOR = "Wei, J.H. and Li, Z.X. and Zhang, C. and Ma, H.F.",
        TITLE = "Fusing grid and adaptive region features for image captioning",
        JOURNAL = IVC,
        VOLUME = "157",
        YEAR = "2025",
        PAGES = "105513",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131786"}

@article{bb135794,
        AUTHOR = "Xu, D.S. and Huang, Q. and Zhang, X. and Cheng, H.N. and Shuang, F. and Cai, Y.",
        TITLE = "DEVICE: Depth and Visual Concepts Aware Transformer for OCR-based
image captioning",
        JOURNAL = PR,
        VOLUME = "164",
        YEAR = "2025",
        PAGES = "111522",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131787"}

@article{bb135795,
        AUTHOR = "Liu, A.A. and Wu, Q. and Xu, N. and Tian, H.S. and Wang, L.",
        TITLE = "Enriched Image Captioning Based on Knowledge Divergence and Focus",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "4937-4948",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131788"}

@article{bb135796,
        AUTHOR = "Shi, L. and Kan, S.C. and Jin, Y. and Zhang, L. and Cen, Y.G.",
        TITLE = "Multi-Modal Self-Perception Enhanced Large Language Model for 3D
Region-of-Interest Captioning With Limited Data",
        JOURNAL = MultMed,
        VOLUME = "27",
        YEAR = "2025",
        PAGES = "2935-2948",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131789"}

@article{bb135797,
        AUTHOR = "Wang, B. and Zhang, Z. and Zhao, M.B. and Jin, X.J. and Xu, M.L. and Wang, M.",
        TITLE = "SeaCap: Multi-Sight Embedding and Alignment for One-Stage Image
Captioner",
        JOURNAL = MultMed,
        VOLUME = "27",
        YEAR = "2025",
        PAGES = "3411-3425",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131790"}

@article{bb135798,
        AUTHOR = "Zhang, J. and Zhang, K.X. and Xie, Y. and Wang, Z.",
        TITLE = "Deep Reciprocal Learning for Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "6684-6697",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131791"}

@article{bb135799,
        AUTHOR = "Gao, J.C. and Zhang, L. and Li, J.Y. and Mao, Z.D.",
        TITLE = "Fully Semantic Gap Recovery for End-to-End Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "9365-9383",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131792"}

Last update:Apr 6, 2026 at 11:28:57