@article{bb121300,
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/match607ic1.html#TT117415"}
@article{bb121301,
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#TT117416"}
@article{bb121302,
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#TT117417"}
@article{bb121303,
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/match607ic1.html#TT117418"}
@article{bb121304,
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/match607ic1.html#TT117419"}
@article{bb121305,
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#TT117420"}
@article{bb121306,
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#TT117421"}
@article{bb121307,
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#TT117422"}
@article{bb121308,
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#TT117423"}
@article{bb121309,
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/match607ic1.html#TT117424"}
@article{bb121310,
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#TT117425"}
@article{bb121311,
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#TT117426"}
@article{bb121312,
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#TT117427"}
@article{bb121313,
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#TT117428"}
@article{bb121314,
AUTHOR = "Liu, A.A. and Wang, Y.H. and Xu, N. and Liu, S. and Li, X.",
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#TT117429"}
@article{bb121315,
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#TT117430"}
@article{bb121316,
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/match607ic1.html#TT117431"}
@article{bb121317,
AUTHOR = "Wei, Y.W. and Wu, C.L. and Jia, Z.Y. and Hu, X. 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/match607ic1.html#TT117432"}
@article{bb121318,
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/match607ic1.html#TT117433"}
@article{bb121319,
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/match607ic1.html#TT117434"}
@article{bb121320,
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/match607ic1.html#TT117435"}
@article{bb121321,
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/match607ic1.html#TT117436"}
@article{bb121322,
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/match607ic1.html#TT117437"}
@article{bb121323,
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#TT117438"}
@article{bb121324,
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#TT117439"}
@article{bb121325,
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#TT117440"}
@article{bb121326,
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/match607ic1.html#TT117441"}
@article{bb121327,
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/match607ic1.html#TT117442"}
@article{bb121328,
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/match607ic1.html#TT117443"}
@article{bb121329,
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/match607ic1.html#TT117444"}
@article{bb121330,
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#TT117445"}
@article{bb121331,
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/match607ic1.html#TT117446"}
@inproceedings{bb121332,
AUTHOR = "Wang, J. 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/match607ic1.html#TT117447"}
@article{bb121333,
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#TT117448"}
@article{bb121334,
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#TT117449"}
@article{bb121335,
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#TT117450"}
@inproceedings{bb121336,
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#TT117451"}
@article{bb121337,
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/match607ic1.html#TT117452"}
@article{bb121338,
AUTHOR = "Yang, Q.Q. and Ni, Z. 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/match607ic1.html#TT117453"}
@article{bb121339,
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#TT117454"}
@article{bb121340,
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#TT117455"}
@inproceedings{bb121341,
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#TT117456"}
@article{bb121342,
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#TT117457"}
@article{bb121343,
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/match607ic1.html#TT117458"}
@article{bb121344,
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/match607ic1.html#TT117459"}
@article{bb121345,
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#TT117460"}
@article{bb121346,
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#TT117461"}
@article{bb121347,
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#TT117462"}
@article{bb121348,
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/match607ic1.html#TT117463"}
@article{bb121349,
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#TT117464"}
@article{bb121350,
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#TT117465"}
@article{bb121351,
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#TT117466"}
@article{bb121352,
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#TT117467"}
@article{bb121353,
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/match607ic1.html#TT117468"}
@article{bb121354,
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#TT117469"}
@article{bb121355,
AUTHOR = "Zhou, H. and Du, X.P. and Xia, L. and Li, S.",
TITLE = "Self-Learning for Few-Shot Remote Sensing Image Captioning",
JOURNAL = RS,
VOLUME = "14",
YEAR = "2022",
NUMBER = "18",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117470"}
@article{bb121356,
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#TT117471"}
@article{bb121357,
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#TT117472"}
@article{bb121358,
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#TT117473"}
@inproceedings{bb121359,
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#TT117474"}
@article{bb121360,
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/match607ic1.html#TT117475"}
@article{bb121361,
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/match607ic1.html#TT117476"}
@article{bb121362,
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#TT117477"}
@article{bb121363,
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#TT117478"}
@article{bb121364,
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/match607ic1.html#TT117479"}
@article{bb121365,
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/match607ic1.html#TT117480"}
@article{bb121366,
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/match607ic1.html#TT117481"}
@article{bb121367,
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/match607ic1.html#TT117482"}
@article{bb121368,
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#TT117483"}
@article{bb121369,
AUTHOR = "Zhu, P.P. and Wang, X. and Luo, Y. and Sun, Z.L. and Zheng, W.S. and Wang, Y. 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#TT117484"}
@article{bb121370,
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#TT117485"}
@article{bb121371,
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#TT117486"}
@article{bb121372,
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#TT117487"}
@article{bb121373,
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#TT117488"}
@article{bb121374,
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#TT117489"}
@article{bb121375,
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#TT117490"}
@inproceedings{bb121376,
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#TT117491"}
@article{bb121377,
AUTHOR = "Zhu, P.P. and Wang, X. and Zhu, L. and Sun, Z.L. and Zheng, W.S. and Wang, Y. 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#TT117492"}
@article{bb121378,
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#TT117493"}
@article{bb121379,
AUTHOR = "Song, L.F. and Li, F. and Wang, Y. and Liu, Y. and Wang, Y. 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/match607ic1.html#TT117494"}
@inproceedings{bb121380,
AUTHOR = "Sabir, A.",
TITLE = "Word to Sentence Visual Semantic Similarity for Caption Generation:
Lessons Learned",
BOOKTITLE = MVA23,
YEAR = "2023",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117495"}
@inproceedings{bb121381,
AUTHOR = "Verma, A. and Agarwal, S. and Arya, K.V. and Petrlik, I. and Esparza, R. and Rodriguez, C.",
TITLE = "Image Captioning with Reinforcement Learning",
BOOKTITLE = ICCVMI23,
YEAR = "2023",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117496"}
@inproceedings{bb121382,
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/match607ic1.html#TT117497"}
@inproceedings{bb121383,
AUTHOR = "Fan, J. and Liang, Y. and Liu, L. and Huang, S. and Zhang, L.",
TITLE = "RCA-NOC: Relative Contrastive Alignment for Novel Object Captioning",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15464-15474",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117498"}
@inproceedings{bb121384,
AUTHOR = "Li, R. and Sun, S.Y. and Elhoseiny, M. and Torr, P.",
TITLE = "OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20236-20246",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117499"}
@inproceedings{bb121385,
AUTHOR = "Hu, A. and Chen, S.Z. and Zhang, L. and Jin, Q.",
TITLE = "Explore and Tell: Embodied Visual Captioning in 3D Environments",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2482-2491",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117500"}
@inproceedings{bb121386,
AUTHOR = "Kang, W. and Mun, J. and Lee, S.J. and Roh, B.",
TITLE = "Noise-aware Learning from Web-crawled Image-Text Data for Image
Captioning",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2930-2940",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117501"}
@inproceedings{bb121387,
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#TT117502"}
@inproceedings{bb121388,
AUTHOR = "Fei, J.J. and Wang, T. and Zhang, J. and He, Z.Y. and Wang, C.J. and Zheng, F.",
TITLE = "Transferable Decoding with Visual Entities for Zero-Shot Image
Captioning",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "3113-3123",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117503"}
@inproceedings{bb121389,
AUTHOR = "Kornblith, S. and Li, L. and Wang, Z. and Nguyen, T.",
TITLE = "Guiding image captioning models toward more specific captions",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15213-15223",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117504"}
@inproceedings{bb121390,
AUTHOR = "Kim, Y. and Kim, J. and Lee, B.K. and Shin, S. and Ro, Y.M.",
TITLE = "Mitigating Dataset Bias in Image Captioning Through Clip
Confounder-Free Captioning Network",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1720-1724",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117505"}
@inproceedings{bb121391,
AUTHOR = "Dessi, R. and Bevilacqua, M. and Gualdoni, E. and Rakotonirina, N.C. and Franzon, F. and Baroni, M.",
TITLE = "Cross-Domain Image Captioning with Discriminative Finetuning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6935-6944",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117506"}
@inproceedings{bb121392,
AUTHOR = "Vo, D.M. and Luong, Q.A. and Sugimoto, A. and Nakayama, H.",
TITLE = "A-CAP: Anticipation Captioning with Commonsense Knowledge",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10824-10833",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117507"}
@inproceedings{bb121393,
AUTHOR = "Kuo, C.W. and Kira, Z.",
TITLE = "HAAV: Hierarchical Aggregation of Augmented Views for Image
Captioning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11039-11049",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117508"}
@inproceedings{bb121394,
AUTHOR = "Ramos, R. and Martins, B. and Elliott, D. and Kementchedjhieva, Y.",
TITLE = "Smallcap: Lightweight Image Captioning Prompted with Retrieval
Augmentation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2840-2849",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117509"}
@inproceedings{bb121395,
AUTHOR = "Hirota, Y. and Nakashima, Y. and Garcia, N.",
TITLE = "Model-Agnostic Gender Debiased Image Captioning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "15191-15200",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117510"}
@inproceedings{bb121396,
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#TT117511"}
@inproceedings{bb121397,
AUTHOR = "Tran, H.T.T. and Okatani, T.",
TITLE = "Bright as the Sun: In-depth Analysis of Imagination-driven Image
Captioning",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "IV:675-691",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117512"}
@inproceedings{bb121398,
AUTHOR = "Phueaksri, I. and Kastner, M.A. and Kawanishi, Y. and Komamizu, T. and Ide, I.",
TITLE = "Towards Captioning an Image Collection from a Combined Scene Graph
Representation Approach",
BOOKTITLE = MMMod23,
YEAR = "2023",
PAGES = "I: 178-190",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117513"}
@inproceedings{bb121399,
AUTHOR = "Zhang, Y. and Wang, J. and Wu, H. and Xu, W.J.",
TITLE = "Distinctive Image Captioning via Clip Guided Group Optimization",
BOOKTITLE = CMHRI22,
YEAR = "2022",
PAGES = "223-238",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117514"}
Last update:Apr 10, 2024 at 09:54:40