@article{bb137300,
        AUTHOR = "McKevitt, P. and Guo, C.M.",
        TITLE = "From Chinese Rooms to Irish Rooms: New Words on Visions for Language",
        JOURNAL = AIR,
        VOLUME = "10",
        YEAR = "1996",
        NUMBER = "1-2",
        MONTH = "April",
        PAGES = "49-63",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133290"}

@article{bb137301,
        AUTHOR = "Grumbach, A.",
        TITLE = "Grounding Symbols into Perceptions",
        JOURNAL = AIR,
        VOLUME = "10",
        YEAR = "1996",
        NUMBER = "1-2",
        MONTH = "April",
        PAGES = "131-146",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133291"}

@article{bb137302,
        AUTHOR = "Socher, G. and Sagerer, G.F. and Perona, P.",
        TITLE = "Bayesian reasoning on qualitative descriptions from images and speech",
        JOURNAL = IVC,
        VOLUME = "18",
        YEAR = "2000",
        NUMBER = "2",
        MONTH = "January",
        PAGES = "155-172",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133292"}

@article{bb137303,
        AUTHOR = "Mukerjee, A. and Gupta, K. and Nautiyal, S. and Singh, M.P. and Mishra, N.",
        TITLE = "Conceptual description of visual scenes from linguistic models",
        JOURNAL = IVC,
        VOLUME = "18",
        YEAR = "2000",
        NUMBER = "2",
        MONTH = "January",
        PAGES = "173-187",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133293"}

@article{bb137304,
        AUTHOR = "Arens, M. and Gerber, R. and Nagel, H.H.",
        TITLE = "Conceptual representations between video signals and natural language
descriptions",
        JOURNAL = IVC,
        VOLUME = "26",
        YEAR = "2008",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "53-66",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133294"}

@inproceedings{bb137305,
        AUTHOR = "Gerber, R. and Nagel, H.H.",
        TITLE = "(Mis?-) Using DRT for Generation of Natural Language Text
from Image Sequences",
        BOOKTITLE = ECCV98,
        YEAR = "1998",
        PAGES = "II: 255",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133295"}

@article{bb137306,
        AUTHOR = "Lee, Y.J. and Grauman, K.",
        TITLE = "Object-Graphs for Context-Aware Visual Category Discovery",
        JOURNAL = PAMI,
        VOLUME = "34",
        YEAR = "2012",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "346-358",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133296"}

@inproceedings{bb137307,
        AUTHOR = "Lee, Y.J. and Grauman, K.",
        TITLE = "Object-graphs for context-aware category discovery",
        BOOKTITLE = CVPR10,
        YEAR = "2010",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133297"}

@inproceedings{bb137308,
        AUTHOR = "Lee, Y.J. and Grauman, K.",
        TITLE = "Learning the easy things first: Self-paced visual category discovery",
        BOOKTITLE = CVPR11,
        YEAR = "2011",
        PAGES = "1721-1728",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133298"}

@article{bb137309,
        AUTHOR = "Yu, A. and Grauman, K.",
        TITLE = "Densifying Supervision for Fine-Grained Visual Comparisons",
        JOURNAL = IJCV,
        VOLUME = "128",
        YEAR = "2020",
        NUMBER = "10-11",
        MONTH = "November",
        PAGES = "2704-2730",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133299"}

@inproceedings{bb137310,
        AUTHOR = "Hessel, J. and Hwang, J.D. and Park, J.S. and Zellers, R. and Bhagavatula, C. and Rohrbach, A. and Saenko, K. and Choi, Y.",
        TITLE = "The Abduction of Sherlock Holmes:
A Dataset for Visual Abductive Reasoning",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXVI:558-575",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133300"}

@inproceedings{bb137311,
        AUTHOR = "Perona, P.",
        TITLE = "A taxonomy of visual recognition",
        BOOKTITLE = VMV04,
        YEAR = "2004",
        PAGES = "187",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133301"}

@inproceedings{bb137312,
        AUTHOR = "Takahashi, T. and Nakanishi, S. and Kuno, Y. and Shirai, Y.",
        TITLE = "Helping Computer Vision by Verbal and Nonverbal Communication",
        BOOKTITLE = ICPR98,
        YEAR = "1998",
        PAGES = "Vol II: 1216-1218",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133302"}

@inproceedings{bb137313,
        AUTHOR = "Satoh, S. and Nakamura, Y. and Kanade, T.",
        TITLE = "Name-It: Naming and Detecting Faces in Video by the Integration 
of Image and Natural Language Processing",
        BOOKTITLE = IJCAI97,
        YEAR = "1997",
        PAGES = "1488-1495",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133303"}

@inproceedings{bb137314,
        AUTHOR = "Satoh, S. and Kanade, T.",
        TITLE = "Name-It: Association Of Face And Name In Video",
        BOOKTITLE = CVPR97,
        YEAR = "1997",
        PAGES = "368-373",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133304"}

@inproceedings{bb137315,
        AUTHOR = "Socher, G. and Sagerer, G.F. and Kummert, F. and Fuhr, T.",
        TITLE = "Talking About 3D Scenes: Integration of Image and Speech Understanding
in a Hybrid Distributed System",
        BOOKTITLE = ICIP96,
        YEAR = "1996",
        PAGES = "II: 809-812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133305"}

@article{bb137316,
        AUTHOR = "Kuniyoshi, Y. and Inaba, M. and Inoue, H.",
        TITLE = "Learning by Watching: Extracting Reusable Task Knowledge from
Visual Observation of Human Performance",
        JOURNAL = RA,
        VOLUME = "10",
        YEAR = "1994",
        PAGES = "799-822",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT133306"}

@inproceedings{bb137317,
        AUTHOR = "Kuniyoshi, Y. and Inoue, H.",
        TITLE = "Indexicality and dynamic attention control in qualitative recognition
of assembly actions",
        BOOKTITLE = ECCV92,
        YEAR = "1992",
        PAGES = "874-878",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT133307"}

@article{bb137318,
        AUTHOR = "Porway, J. and Wang, Q.C. and Zhu, S.C.",
        TITLE = "A Hierarchical and Contextual Model for Aerial Image Parsing",
        JOURNAL = IJCV,
        VOLUME = "88",
        YEAR = "2010",
        NUMBER = "2",
        MONTH = "June",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT133308"}

@inproceedings{bb137319,
        AUTHOR = "Porway, J. and Wang, K. and Yao, B. and Zhu, S.C.",
        TITLE = "A hierarchical and contextual model for aerial image understanding",
        BOOKTITLE = CVPR08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT133309"}

@inproceedings{bb137320,
        AUTHOR = "Si, Z.Z. and Gong, H.F. and Wu, Y.N. and Zhu, S.C.",
        TITLE = "Learning mixed templates for object recognition",
        BOOKTITLE = CVPR09,
        YEAR = "2009",
        PAGES = "272-279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT133310"}

@article{bb137321,
        AUTHOR = "Tu, Z.W. and Bai, X.",
        TITLE = "Auto-Context and Its Application to High-Level Vision Tasks and 3D
Brain Image Segmentation",
        JOURNAL = PAMI,
        VOLUME = "32",
        YEAR = "2010",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "1744-1757",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT133311"}

@inproceedings{bb137322,
        AUTHOR = "Tu, Z.W.",
        TITLE = "Auto-context and its application to high-level vision tasks",
        BOOKTITLE = CVPR08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT133312"}

@inproceedings{bb137323,
        AUTHOR = "Jones, J. and Hager, G.D. and Khudanpur, S.",
        TITLE = "Toward Computer Vision Systems That Understand Real-World Assembly
Processes",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "426-434",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT133313"}

@inproceedings{bb137324,
        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#TT133314"}

@inproceedings{bb137325,
        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#TT133315"}

@inproceedings{bb137326,
        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#TT133316"}

@inproceedings{bb137327,
        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#TT133317"}

@article{bb137328,
        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#TT133318"}

@article{bb137329,
        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#TT133319"}

@inproceedings{bb137330,
        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#TT133320"}

@article{bb137331,
        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#TT133321"}

@article{bb137332,
        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#TT133322"}

@article{bb137333,
        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#TT133323"}

@article{bb137334,
        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#TT133323"}

@article{bb137335,
        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#TT133324"}

@article{bb137336,
        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#TT133325"}

@article{bb137337,
        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#TT133326"}

@article{bb137338,
        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#TT133327"}

@article{bb137339,
        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#TT133328"}

@article{bb137340,
        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#TT133329"}

@article{bb137341,
        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#TT133330"}

@article{bb137342,
        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#TT133331"}

@article{bb137343,
        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#TT133332"}

@article{bb137344,
        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#TT133333"}

@article{bb137345,
        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#TT133334"}

@article{bb137346,
        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#TT133335"}

@article{bb137347,
        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#TT133336"}

@article{bb137348,
        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#TT133337"}

@article{bb137349,
        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#TT133338"}

@article{bb137350,
        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#TT133339"}

@article{bb137351,
        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#TT133340"}

@article{bb137352,
        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#TT133341"}

@article{bb137353,
        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#TT133342"}

@article{bb137354,
        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#TT133343"}

@article{bb137355,
        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#TT133344"}

@article{bb137356,
        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#TT133345"}

@article{bb137357,
        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#TT133346"}

@article{bb137358,
        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#TT133347"}

@article{bb137359,
        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#TT133348"}

@article{bb137360,
        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#TT133349"}

@article{bb137361,
        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#TT133350"}

@article{bb137362,
        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#TT133351"}

@inproceedings{bb137363,
        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#TT133352"}

@article{bb137364,
        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#TT133353"}

@article{bb137365,
        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#TT133354"}

@inproceedings{bb137366,
        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#TT133355"}

@article{bb137367,
        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#TT133356"}

@article{bb137368,
        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#TT133357"}

@article{bb137369,
        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#TT133358"}

@article{bb137370,
        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#TT133359"}

@article{bb137371,
        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#TT133360"}

@article{bb137372,
        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#TT133361"}

@article{bb137373,
        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#TT133362"}

@article{bb137374,
        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#TT133363"}

@article{bb137375,
        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#TT133364"}

@article{bb137376,
        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#TT133365"}

@article{bb137377,
        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#TT133366"}

@article{bb137378,
        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#TT133367"}

@inproceedings{bb137379,
        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#TT133368"}

@article{bb137380,
        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#TT133369"}

@article{bb137381,
        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#TT133370"}

@article{bb137382,
        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#TT133371"}

@article{bb137383,
        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#TT133372"}

@article{bb137384,
        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#TT133373"}

@article{bb137385,
        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#TT133374"}

@article{bb137386,
        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#TT133375"}

@article{bb137387,
        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#TT133376"}

@article{bb137388,
        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#TT133377"}

@article{bb137389,
        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#TT133378"}

@inproceedings{bb137390,
        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#TT133379"}

@article{bb137391,
        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#TT133380"}

@article{bb137392,
        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#TT133381"}

@article{bb137393,
        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#TT133382"}

@article{bb137394,
        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#TT133383"}

@article{bb137395,
        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#TT133384"}

@article{bb137396,
        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#TT133385"}

@inproceedings{bb137397,
        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#TT133386"}

@inproceedings{bb137398,
        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#TT133387"}

@inproceedings{bb137399,
        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#TT133388"}

Last update:Jul 24, 2026 at 15:25:55