@inproceedings{bb137000,
        AUTHOR = "Kong, S. and Fowlkes, C.C.",
        TITLE = "Recurrent Scene Parsing with Perspective Understanding in the Loop",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "956-965",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT132992"}

@inproceedings{bb137001,
        AUTHOR = "Zheng, H. and Fu, J. and Mei, T. and Luo, J.",
        TITLE = "Learning Multi-attention Convolutional Neural Network for
Fine-Grained Image Recognition",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "5219-5227",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT132993"}

@inproceedings{bb137002,
        AUTHOR = "Fu, J. and Zheng, H. and Mei, T.",
        TITLE = "Look Closer to See Better: Recurrent Attention Convolutional Neural
Network for Fine-Grained Image Recognition",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "4476-4484",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT132994"}

@inproceedings{bb137003,
        AUTHOR = "Ge, Z.Y. and McCool, C. and Sanderson, C. and Wang, P. and Liu, L.Q. and Reid, I.D. and Corke, P.",
        TITLE = "Exploiting Temporal Information for DCNN-Based Fine-Grained Object
Classification",
        BOOKTITLE = DICTA16,
        YEAR = "2016",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT132995"}

@inproceedings{bb137004,
        AUTHOR = "Ai, S.S. and Jia, C.Y. and Chen, Z.N.",
        TITLE = "Large-Scale Product Classification via Spatial Attention Based CNN
Learning and Multi-class Regression",
        BOOKTITLE = MMMod17,
        YEAR = "2017",
        PAGES = "I: 176-188",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT132996"}

@inproceedings{bb137005,
        AUTHOR = "Diba, A. and Pazandeh, A.M. and Pirsiavash, H. and Van Gool, L.J.",
        TITLE = "DeepCAMP: Deep Convolutional Action Attribute Mid-Level Patterns",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "3557-3565",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT132997"}

@inproceedings{bb137006,
        AUTHOR = "Chevalier, M. and Thome, N. and Cord, M. and Fournier, J. and Henaff, G. and Dusch, E.",
        TITLE = "LR-CNN for fine-grained classification with varying resolution",
        BOOKTITLE = ICIP15,
        YEAR = "2015",
        PAGES = "3101-3105",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT132998"}

@inproceedings{bb137007,
        AUTHOR = "Ge, Z. and Bewley, A. and McCool, C. and Corke, P. and Upcroft, B. and Sanderson, C.",
        TITLE = "Fine-grained classification via mixture of deep convolutional neural
networks",
        BOOKTITLE = WACV16,
        YEAR = "2016",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT132999"}

@inproceedings{bb137008,
        AUTHOR = "Ge, Z. and McCool, C. and Sanderson, C. and Corke, P.",
        TITLE = "Modelling local deep convolutional neural network features to improve
fine-grained image classification",
        BOOKTITLE = ICIP15,
        YEAR = "2015",
        PAGES = "4112-4116",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT133000"}

@article{bb137009,
        AUTHOR = "Taylor, S.L. and Dahl, D.A. and Lipshutz, M. and Weir, C. and Norton, L.M. and Nilson, R.W. and Linebarger, M.C.",
        TITLE = "Integrating Natural-Language Understanding with
Document Structure-Analysis",
        JOURNAL = AIR,
        VOLUME = "8",
        YEAR = "1994",
        NUMBER = "2-3",
        PAGES = "255-276",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133001"}

@article{bb137010,
        AUTHOR = "McKevitt, P.",
        TITLE = "Integration of Natural-Language and Vision Processing: Theory",
        JOURNAL = AIR,
        VOLUME = "9",
        YEAR = "1995",
        NUMBER = "4-5",
        MONTH = "October",
        PAGES = "247-250",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133002"}

@book{bb137011,
        AUTHOR = "McKevitt, P.",
        TITLE = "Integration of Natural-Language and Vision Processing: Theory",
        PUBLISHER = "Springer",
        YEAR = "1995",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133002"}

@article{bb137012,
        AUTHOR = "McKevitt, P.",
        TITLE = "Integration of Natural-Language and Vision Processing:
Intelligent Multimedia",
        JOURNAL = AIR,
        VOLUME = "9",
        YEAR = "1995",
        NUMBER = "2-3",
        MONTH = "June",
        PAGES = "77-80",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133003"}

@article{bb137013,
        AUTHOR = "McKevitt, P.",
        TITLE = "Integration of Natural-Language and Vision Processing:
More Computational Models and Systems",
        JOURNAL = AIR,
        VOLUME = "8",
        YEAR = "1995",
        NUMBER = "5-6",
        PAGES = "345-348",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133004"}

@article{bb137014,
        AUTHOR = "McKevitt, P.",
        TITLE = "Integration of Natural-Language and Vision Processing:
Computational Models and Systems",
        JOURNAL = AIR,
        VOLUME = "8",
        YEAR = "1994",
        NUMBER = "2-3",
        PAGES = "99-104",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133005"}

@book{bb137015,
        AUTHOR = "McKevitt, P.",
        TITLE = "Integration of Natural-Language and Vision Processing:
Computational Models and Systems",
        PUBLISHER = "Kluwer",
        YEAR = "1995",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133005"}

@article{bb137016,
        AUTHOR = "McKevitt, P.",
        TITLE = "Integration of Natural-Language and Vision Processing:
Grounding Representations",
        JOURNAL = AIR,
        VOLUME = "10",
        YEAR = "1996",
        NUMBER = "1-2",
        MONTH = "April",
        PAGES = "7-13",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133006"}

@book{bb137017,
        AUTHOR = "McKevitt, P.",
        TITLE = "Integration of Natural Language and Vision Processing",
        PUBLISHER = "Kluwer",
        YEAR = "1996",
        MONTH = "September",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133007"}

@article{bb137018,
        AUTHOR = "Siskind, J.M.",
        TITLE = "Grounding Language in Perception",
        JOURNAL = AIR,
        VOLUME = "8",
        YEAR = "1995",
        NUMBER = "5-6",
        PAGES = "371-391",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133008"}

@article{bb137019,
        AUTHOR = "Srihari, R.K.",
        TITLE = "Automatic-Indexing and Content-Based Retrieval of Captioned Images",
        JOURNAL = Computer,
        VOLUME = "28",
        YEAR = "1995",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "49-56",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133009"}

@article{bb137020,
        AUTHOR = "Srihari, R.K.",
        TITLE = "Use of Captions and Other Collateral Text in Understanding Photographs",
        JOURNAL = AIR,
        VOLUME = "8",
        YEAR = "1995",
        NUMBER = "5-6",
        PAGES = "409-430",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133010"}

@article{bb137021,
        AUTHOR = "Srihari, R.K.",
        TITLE = "Use of Collateral Text in Understanding Photos in Documents",
        JOURNAL = SPIE,
        VOLUME = "2368",
        YEAR = "1994",
        PAGES = "186-199",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133011"}

@article{bb137022,
        AUTHOR = "Srihari, R.K.",
        TITLE = "Computational Models for Integrating Linguistic and Visual Information:
A Survey",
        JOURNAL = AIR,
        VOLUME = "8",
        YEAR = "1995",
        NUMBER = "5-6",
        PAGES = "349-369",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133012"}

@inproceedings{bb137023,
        AUTHOR = "Srihari, R.K.",
        TITLE = "Using Linguistic Context for Image Interpretation and Annotation",
        BOOKTITLE = "Radius97",
        YEAR = "1997",
        PAGES = "419-427",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133013"}

@inproceedings{bb137024,
        AUTHOR = "Srihari, R.K.",
        TITLE = "Linguistic Context In Vision",
        BOOKTITLE = Context95,
        YEAR = "1995",
        PAGES = "xx",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133014"}

@inproceedings{bb137025,
        AUTHOR = "Srihari, R.K. and Zhang, Z. and Venkatraman, M. and Chopra, R.",
        TITLE = "Using Speech Input for Image Interpretation and Annotation",
        BOOKTITLE = ARPA96,
        YEAR = "1996",
        PAGES = "501-510",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133015"}

@inproceedings{bb137026,
        AUTHOR = "Burhans, D.T. and Chopra, R. and Srihari, R.K. and Govindaraju, V. and Venkataraman, M.",
        TITLE = "Use of Collateral Text in Image Interpretation",
        BOOKTITLE = ARPA94,
        YEAR = "1994",
        PAGES = "II:897-907",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133016"}

@inproceedings{bb137027,
        AUTHOR = "Srihari, R.K. and Burhans, D.T.",
        TITLE = "Visual Semantics: Extracting Visual Information from
Text Accompanying Pictures",
        BOOKTITLE = AAAI-94,
        YEAR = "1994",
        PAGES = "793-798",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133017"}

@inproceedings{bb137028,
        AUTHOR = "Govindaraju, V. and Srihari, S.N. and Sher, D.B.",
        TITLE = "Caption-Aided Face Location In Newspaper Photographs",
        BOOKTITLE = ICPR92,
        YEAR = "1992",
        PAGES = "I:474-477",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133018"}

@inproceedings{bb137029,
        AUTHOR = "Govindaraju, V. and Srihari, S.N. and Sher, D.B.",
        TITLE = "A Computational Model for Face Location Based on Cognitive Principles",
        BOOKTITLE = AAAI-92,
        YEAR = "1992",
        PAGES = "350-355",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133019"}

@article{bb137030,
        AUTHOR = "Schank, R.C. and Fano, A.",
        TITLE = "Memory and Expectations in Learning, Language, and Visual Understanding",
        JOURNAL = AIR,
        VOLUME = "9",
        YEAR = "1995",
        NUMBER = "4-5",
        MONTH = "October",
        PAGES = "261-271",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133020"}

@article{bb137031,
        AUTHOR = "Wilks, Y.",
        TITLE = "Language, Vision and Metaphor",
        JOURNAL = AIR,
        VOLUME = "9",
        YEAR = "1995",
        NUMBER = "4-5",
        MONTH = "October",
        PAGES = "273-289",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133021"}

@article{bb137032,
        AUTHOR = "Partridge, D.",
        TITLE = "Language and Vision: A Single Perceptual Mechanism",
        JOURNAL = AIR,
        VOLUME = "9",
        YEAR = "1995",
        NUMBER = "4-5",
        MONTH = "October",
        PAGES = "291-303",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133022"}

@article{bb137033,
        AUTHOR = "Marconi, D.",
        TITLE = "Work on the Integration of Language and Vision at the
University of Torino",
        JOURNAL = AIR,
        VOLUME = "10",
        YEAR = "1996",
        NUMBER = "1-2",
        MONTH = "April",
        PAGES = "15-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133023"}

@article{bb137034,
        AUTHOR = "Meini, C. and Paternoster, A.",
        TITLE = "Understanding Language Through Vision",
        JOURNAL = AIR,
        VOLUME = "10",
        YEAR = "1996",
        NUMBER = "1-2",
        MONTH = "April",
        PAGES = "37-48",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133024"}

@article{bb137035,
        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#TT133025"}

@article{bb137036,
        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#TT133026"}

@article{bb137037,
        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#TT133027"}

@article{bb137038,
        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#TT133028"}

@article{bb137039,
        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#TT133029"}

@inproceedings{bb137040,
        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#TT133030"}

@article{bb137041,
        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#TT133031"}

@inproceedings{bb137042,
        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#TT133032"}

@inproceedings{bb137043,
        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#TT133033"}

@article{bb137044,
        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#TT133034"}

@inproceedings{bb137045,
        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#TT133035"}

@inproceedings{bb137046,
        AUTHOR = "Perona, P.",
        TITLE = "A taxonomy of visual recognition",
        BOOKTITLE = VMV04,
        YEAR = "2004",
        PAGES = "187",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133036"}

@inproceedings{bb137047,
        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#TT133037"}

@inproceedings{bb137048,
        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#TT133038"}

@inproceedings{bb137049,
        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#TT133039"}

@inproceedings{bb137050,
        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#TT133040"}

@article{bb137051,
        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#TT133041"}

@inproceedings{bb137052,
        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#TT133042"}

@article{bb137053,
        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#TT133043"}

@inproceedings{bb137054,
        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#TT133044"}

@inproceedings{bb137055,
        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#TT133045"}

@article{bb137056,
        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#TT133046"}

@inproceedings{bb137057,
        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#TT133047"}

@inproceedings{bb137058,
        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#TT133048"}

@inproceedings{bb137059,
        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#TT133049"}

@inproceedings{bb137060,
        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#TT133050"}

@inproceedings{bb137061,
        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#TT133051"}

@inproceedings{bb137062,
        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#TT133052"}

@article{bb137063,
        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#TT133053"}

@article{bb137064,
        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#TT133054"}

@inproceedings{bb137065,
        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#TT133055"}

@article{bb137066,
        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#TT133056"}

@article{bb137067,
        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#TT133057"}

@article{bb137068,
        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#TT133058"}

@article{bb137069,
        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#TT133058"}

@article{bb137070,
        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#TT133059"}

@article{bb137071,
        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#TT133060"}

@article{bb137072,
        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#TT133061"}

@article{bb137073,
        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#TT133062"}

@article{bb137074,
        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#TT133063"}

@article{bb137075,
        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#TT133064"}

@article{bb137076,
        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#TT133065"}

@article{bb137077,
        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#TT133066"}

@article{bb137078,
        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#TT133067"}

@article{bb137079,
        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#TT133068"}

@article{bb137080,
        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#TT133069"}

@article{bb137081,
        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#TT133070"}

@article{bb137082,
        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#TT133071"}

@article{bb137083,
        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#TT133072"}

@article{bb137084,
        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#TT133073"}

@article{bb137085,
        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#TT133074"}

@article{bb137086,
        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#TT133075"}

@article{bb137087,
        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#TT133076"}

@article{bb137088,
        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#TT133077"}

@article{bb137089,
        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#TT133078"}

@article{bb137090,
        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#TT133079"}

@article{bb137091,
        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#TT133080"}

@article{bb137092,
        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#TT133081"}

@article{bb137093,
        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#TT133082"}

@article{bb137094,
        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#TT133083"}

@article{bb137095,
        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#TT133084"}

@article{bb137096,
        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#TT133085"}

@article{bb137097,
        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#TT133086"}

@inproceedings{bb137098,
        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#TT133087"}

@article{bb137099,
        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#TT133088"}