@article{bb139100,
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#TT135076"}
@article{bb139101,
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#TT135077"}
@article{bb139102,
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#TT135078"}
@article{bb139103,
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#TT135079"}
@article{bb139104,
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#TT135080"}
@article{bb139105,
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#TT135081"}
@article{bb139106,
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#TT135082"}
@article{bb139107,
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#TT135083"}
@article{bb139108,
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#TT135084"}
@article{bb139109,
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#TT135085"}
@article{bb139110,
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#TT135086"}
@article{bb139111,
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#TT135087"}
@article{bb139112,
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#TT135088"}
@article{bb139113,
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#TT135089"}
@article{bb139114,
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#TT135090"}
@article{bb139115,
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#TT135091"}
@article{bb139116,
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#TT135092"}
@article{bb139117,
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#TT135093"}
@article{bb139118,
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#TT135094"}
@inproceedings{bb139119,
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#TT135095"}
@article{bb139120,
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#TT135096"}
@article{bb139121,
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#TT135097"}
@inproceedings{bb139122,
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#TT135098"}
@article{bb139123,
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#TT135099"}
@article{bb139124,
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#TT135100"}
@article{bb139125,
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#TT135101"}
@article{bb139126,
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#TT135102"}
@article{bb139127,
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#TT135103"}
@article{bb139128,
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#TT135104"}
@article{bb139129,
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#TT135105"}
@article{bb139130,
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#TT135106"}
@article{bb139131,
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#TT135107"}
@article{bb139132,
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#TT135108"}
@article{bb139133,
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#TT135109"}
@article{bb139134,
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#TT135110"}
@inproceedings{bb139135,
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#TT135111"}
@article{bb139136,
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#TT135112"}
@article{bb139137,
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#TT135113"}
@article{bb139138,
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#TT135114"}
@article{bb139139,
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#TT135115"}
@article{bb139140,
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#TT135116"}
@article{bb139141,
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#TT135117"}
@article{bb139142,
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#TT135118"}
@article{bb139143,
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#TT135119"}
@article{bb139144,
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#TT135120"}
@article{bb139145,
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#TT135121"}
@inproceedings{bb139146,
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#TT135122"}
@article{bb139147,
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#TT135123"}
@article{bb139148,
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#TT135124"}
@article{bb139149,
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#TT135125"}
@article{bb139150,
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#TT135126"}
@article{bb139151,
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#TT135127"}
@article{bb139152,
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#TT135128"}
@inproceedings{bb139153,
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#TT135129"}
@inproceedings{bb139154,
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#TT135130"}
@inproceedings{bb139155,
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#TT135131"}
@article{bb139156,
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#TT135132"}
@article{bb139157,
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#TT135133"}
@article{bb139158,
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#TT135134"}
@article{bb139159,
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#TT135135"}
@article{bb139160,
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#TT135136"}
@article{bb139161,
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#TT135137"}
@inproceedings{bb139162,
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#TT135138"}
@article{bb139163,
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#TT135139"}
@article{bb139164,
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#TT135140"}
@article{bb139165,
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#TT135141"}
@article{bb139166,
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#TT135142"}
@article{bb139167,
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#TT135143"}
@article{bb139168,
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#TT135144"}
@article{bb139169,
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#TT135145"}
@article{bb139170,
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#TT135146"}
@article{bb139171,
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#TT135147"}
@article{bb139172,
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#TT135148"}
@article{bb139173,
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#TT135149"}
@article{bb139174,
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#TT135150"}
@article{bb139175,
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#TT135151"}
@article{bb139176,
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#TT135152"}
@article{bb139177,
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#TT135153"}
@article{bb139178,
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#TT135154"}
@article{bb139179,
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#TT135155"}
@article{bb139180,
AUTHOR = "Gao, Y.Q. and Suo, W. and Sun, M.Y. and Liu, L. and Wang, P.",
TITLE = "More video-relevant paragraph captioning via Perturbed Attention
Self-Distillation",
JOURNAL = PR,
VOLUME = "169",
YEAR = "2026",
PAGES = "111871",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135156"}
@article{bb139181,
AUTHOR = "Li, H. and Xiao, J. and Sun, M.J. and Lim, E.G. and Zhao, Y.",
TITLE = "Auxiliary captioning: Bridging image-text matching and image
captioning",
JOURNAL = SP:IC,
VOLUME = "138",
YEAR = "2025",
PAGES = "117337",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135157"}
@article{bb139182,
AUTHOR = "Bao, Q.Y. and Liu, F. and Jiao, L.C. and Liu, Y. and Li, S. and Li, L.L. and Liu, X. and Chen, P.",
TITLE = "Visual-Language Scene-Relation-Aware Zero-Shot Captioner",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "10",
MONTH = "October",
PAGES = "8725-8739",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135158"}
@article{bb139183,
AUTHOR = "Bui, D.C. and Nguyen, N.H. and Nguyen, K.",
TITLE = "UIT-OpenViIC: An open-domain benchmark for evaluating image
captioning in Vietnamese",
JOURNAL = SP:IC,
VOLUME = "140",
YEAR = "2026",
PAGES = "117430",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135159"}
@article{bb139184,
AUTHOR = "Zhao, S.S. and Wang, T. and Zhang, J. and Wang, X.C. and Zheng, F.",
TITLE = "MCoCa: Towards fine-grained multimodal control in image captioning",
JOURNAL = PR,
VOLUME = "172",
YEAR = "2026",
PAGES = "112381",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135160"}
@article{bb139185,
AUTHOR = "Wan, J. and Gan, M. and Zhang, L. and Zhou, J. and Liu, J. and Du, B. and Chen, C.L.P.",
TITLE = "Fine-Grained Image Captioning by Ranking Diffusion Transformer",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "8332-8344",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135161"}
@article{bb139186,
AUTHOR = "Wang, L. and Xue, R. and Yu, Z.T. and Zhang, R. and Pan, T. and Li, Y.",
TITLE = "A dynamic hybrid network with attention and mamba for image
captioning",
JOURNAL = CVIU,
VOLUME = "263",
YEAR = "2026",
PAGES = "104617",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135162"}
@article{bb139187,
AUTHOR = "Li, H.Y. and Li, L. and Wang, H. and Zhang, W.B. and Ren, P.",
TITLE = "Large Foundation Model Empowered Region-aware Underwater Image
Captioning",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "2",
MONTH = "February",
PAGES = "66",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135163"}
@article{bb139188,
AUTHOR = "Mujawar, S.R. and Iyer, S.",
TITLE = "Deep learning model with co-ordinated relationship for image
captioning enabled via attentional language encoder-decoder",
JOURNAL = SP:IC,
VOLUME = "142",
YEAR = "2026",
PAGES = "117466",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135164"}
@article{bb139189,
AUTHOR = "Zhao, Y.F. and Tao, Q.Q. and Sun, P.F. and Huang, J. and Song, W.K. and Hu, N.N.",
TITLE = "HPRNet: A holistic position-aware residual network for image
captioning",
JOURNAL = PR,
VOLUME = "177",
YEAR = "2026",
PAGES = "113249",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135165"}
@article{bb139190,
AUTHOR = "Aljunaid, R. and Umer, Q. and Mahmood, S. and Niazi, M. and Behzad, M.",
TITLE = "KRCapVLM: Beam-guided knowledge replay for knowledge-rich image
captioning using vision-language model",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113568",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135166"}
@article{bb139191,
AUTHOR = "Wang, L.X. and Qiu, H.Q. and Wen, H.T. and Meng, F.M. and Wu, Q.B. and Li, H.L.",
TITLE = "Bridging the Gap between Vision and Text for unsupervised text-only
captioning",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113937",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135167"}
@article{bb139192,
AUTHOR = "Wang, Z. and Yang, X. and Xu, H.Y. and Zhang, H.W. and Yan, M. and Huang, F. and Zhang, Y.",
TITLE = "Adaptively Clustering Neighbor Elements for Image-Text Generation",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "4475-4484",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135168"}
@article{bb139193,
AUTHOR = "Li, L. and Peng, Y.Z. and Yang, X. and Cheng, R.X. and Xu, H.Y. and Yan, M. and Huang, F.",
TITLE = "L-CLIPScore: A Lightweight Embedding-Based Captioning Metric for
Evaluating and Training",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "5487-5496",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135169"}
@article{bb139194,
AUTHOR = "Ren, Y.C. and Chen, X. and Yuan, H.R. and Li, J.Y. and Song, P.P. and Chen, L. and Ouyang, W.L. and Zhang, L. and Guo, J.Y.",
TITLE = "VMFormer: Visual Clues-Guided Multi-Stage Transformer for Image
Captioning",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "7767-7782",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135170"}
@article{bb139195,
AUTHOR = "Liu, X.L. and Fang, X.P. and Yan, J.B. and Fang, C.Y. and Fang, Y.M.",
TITLE = "IC-Bench: Benchmarking robustness of large multimodal models to
common corruptions on image captioning",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114272",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135171"}
@article{bb139196,
AUTHOR = "Liang, J. and Wu, K. and Hu, X. and Liu, T.Y.",
TITLE = "Cibic: Pixel-free foundation model for robust corrupted image
bitstream captioning",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114238",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135172"}
@article{bb139197,
AUTHOR = "Li, T.C. and Xu, C. and Song, Y.Z. and Yuan, J.Z. and Dai, S.Y. and Zhang, J.C.",
TITLE = "BPA-Net: Bidirectional Prototype Alignment for Image Captioning",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "10",
MONTH = "October",
PAGES = "14710-14725",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135173"}
@article{bb139198,
AUTHOR = "Li, L. and Wu, Y.L. and Zhu, J.Z. and Peng, J.W. and Cai, J.F. and Yang, X.",
TITLE = "Unveiling Effective In-Context Configurations for Image Captioning:
An External & Internal Analysis",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "11",
MONTH = "November",
PAGES = "14759-14776",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135174"}
@inproceedings{bb139199,
AUTHOR = "Yildiz, S. and Memis, A.",
TITLE = "Automatic Turkish Image Captioning Using Non-Native Deep Caption
Generator Models and Neural Machine Translators",
BOOKTITLE = IPTA25,
YEAR = "2025",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT135175"}
Last update: