@inproceedings{bb121400,
        AUTHOR = "Liu, D.C. and Wang, Y. and Mase, K.J. and Kato, J.",
        TITLE = "Attention-Based Multi-Task Learning for Fine-Grained Image
Classification",
        BOOKTITLE = ICIP21,
        YEAR = "2021",
        PAGES = "1499-1503",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117517"}

@article{bb121401,
        AUTHOR = "Deng, W.J. and Marsh, J. and Gould, S. and Zheng, L.",
        TITLE = "Fine-Grained Classification via Categorical Memory Networks",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "4186-4196",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117518"}

@article{bb121402,
        AUTHOR = "Zhu, J.W. and Li, Z.X. and Wei, J. and Zeng, Y.F. and Ma, H.F.",
        TITLE = "Fine-grained bidirectional attentional generation and
knowledge-assisted networks for cross-modal retrieval",
        JOURNAL = IVC,
        VOLUME = "124",
        YEAR = "2022",
        PAGES = "104507",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117519"}

@article{bb121403,
        AUTHOR = "Lang, W.X. and Sun, H. and Xu, C. and Liu, N.Z. and Zhou, H.Y.",
        TITLE = "Discriminative feature mining hashing for fine-grained image
retrieval",
        JOURNAL = JVCIR,
        VOLUME = "87",
        YEAR = "2022",
        PAGES = "103592",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117520"}

@article{bb121404,
        AUTHOR = "Sun, H. and Lang, W.X. and Xu, C. and Liu, N.Z. and Zhou, H.Y.",
        TITLE = "Graph-based discriminative features learning for fine-grained image
retrieval",
        JOURNAL = SP:IC,
        VOLUME = "110",
        YEAR = "2023",
        PAGES = "116885",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117521"}

@article{bb121405,
        AUTHOR = "Liu, K.J. and Chen, K. and Jia, K.",
        TITLE = "Convolutional Fine-Grained Classification With Self-Supervised Target
Relation Regularization",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "5570-5584",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117522"}

@inproceedings{bb121406,
        AUTHOR = "Yang, X. and Wang, Y. and Chen, K. and Xu, Y. and Tian, Y.H.",
        TITLE = "Fine-Grained Object Classification via Self-Supervised Pose Alignment",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "7389-7398",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117523"}

@article{bb121407,
        AUTHOR = "Han, J.W. and Yao, X. and Cheng, G. and Feng, X.X. and Xu, D.",
        TITLE = "P-CNN: Part-Based Convolutional Neural Networks for Fine-Grained
Visual Categorization",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "579-590",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117524"}

@article{bb121408,
        AUTHOR = "Koniusz, P. and Zhang, H.G.",
        TITLE = "Power Normalizations in Fine-Grained Image, Few-Shot Image and Graph
Classification",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "591-609",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117525"}

@article{bb121409,
        AUTHOR = "Sun, X. and Wang, P.J. and Yan, Z.Y. and Xu, F. and Wang, R.P. and Diao, W.H. and Chen, J. and Li, J. and Feng, Y.C. and Xu, T. and Weinmann, M. and Hinz, S. and Wang, C. and Fu, K.",
        TITLE = "FAIR1M: A benchmark dataset for fine-grained object recognition in
high-resolution remote sensing imagery",
        JOURNAL = PandRS,
        VOLUME = "184",
        YEAR = "2022",
        PAGES = "116-130",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117526"}

@article{bb121410,
        AUTHOR = "Xu, Q. and Zhang, M.Q. and Li, Y. and Tao, Z.",
        TITLE = "Learning more discriminative clues with gradual attention for
fine-grained visual categorization",
        JOURNAL = IVC,
        VOLUME = "136",
        YEAR = "2023",
        PAGES = "104753",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117527"}

@article{bb121411,
        AUTHOR = "Yu, H. and Lu, H. and Zhao, M. and Li, Z.Y. and Gu, G.H.",
        TITLE = "Gradient aggregation based fine-grained image retrieval:
A unified viewpoint for CNN and Transformer",
        JOURNAL = PR,
        VOLUME = "149",
        YEAR = "2024",
        PAGES = "110248",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117528"}

@inproceedings{bb121412,
        AUTHOR = "Xu, Z.R. and Yu, F.X. and Liu, C.X. and Wu, Z. and Wang, H.C. and Chen, X.",
        TITLE = "FalCon: Fine-grained Feature Map Sparsity Computing with Decomposed
Convolutions for Inference Optimization",
        BOOKTITLE = WACV22,
        YEAR = "2022",
        PAGES = "3634-3644",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117529"}

@inproceedings{bb121413,
        AUTHOR = "Mahmoudi, M.A. and Chetouani, A. and Boufera, F. and Tabia, H.",
        TITLE = "Taylor Series Kernelized Layer for Fine-Grained Recognition",
        BOOKTITLE = ICIP21,
        YEAR = "2021",
        PAGES = "1914-1918",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117530"}

@inproceedings{bb121414,
        AUTHOR = "Cheng, J.C. and Vasconcelos, N.M.",
        TITLE = "Learning Deep Classifiers Consistent with Fine-Grained Novelty
Detection",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "1664-1673",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117531"}

@inproceedings{bb121415,
        AUTHOR = "Ji, R. and Wen, L. and Zhang, L. and Du, D. and Wu, Y. and Zhao, C. and Liu, X. and Huang, F.",
        TITLE = "Attention Convolutional Binary Neural Tree for Fine-Grained Visual
Categorization",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10465-10474",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117532"}

@inproceedings{bb121416,
        AUTHOR = "Taherkhani, F. and Kazemi, H. and Dabouei, A. and Dawson, J. and Nasrabadi, N.",
        TITLE = "A Weakly Supervised Fine Label Classifier Enhanced by Coarse
Supervision",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "6458-6467",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117533"}

@inproceedings{bb121417,
        AUTHOR = "Yang, H. and Wu, H. and Chen, H.",
        TITLE = "Detecting 11K Classes: Large Scale Object Detection Without
Fine-Grained Bounding Boxes",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "9804-9812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117534"}

@inproceedings{bb121418,
        AUTHOR = "Wagner, J. and Kohler, J.M. and Gindele, T. and Hetzel, L. and Wiedemer, J.T. and Behnke, S.",
        TITLE = "Interpretable and Fine-Grained Visual Explanations for Convolutional
Neural Networks",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "9089-9099",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117535"}

@inproceedings{bb121419,
        AUTHOR = "Feng, Z. and Fu, K. and Zhao, Q.",
        TITLE = "Learning to Focus and Discriminate for Fine-Grained Classification",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "415-419",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117536"}

@inproceedings{bb121420,
        AUTHOR = "Xin, Q. and Lv, T. and Gao, H.",
        TITLE = "Random Part Localization Model for Fine Grained Image Classification",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "420-424",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117537"}

@inproceedings{bb121421,
        AUTHOR = "Zhong, W. and Jiang, L. and Zhang, T. and Ji, J. and Xiong, H.",
        TITLE = "A Multi-part Convolutional Attention Network for Fine-Grained Image
Recognition",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "1857-1862",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117538"}

@inproceedings{bb121422,
        AUTHOR = "Simonelli, A. and de Natale, F.G.B. and Messelodi, S. and Bulo, S.R.",
        TITLE = "Increasingly Specialized Ensemble of Convolutional Neural Networks
for Fine-Grained Recognition",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "594-598",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117539"}

@inproceedings{bb121423,
        AUTHOR = "Wang, Y. and Morariu, V.I. and Davis, L.S.",
        TITLE = "Learning a Discriminative Filter Bank Within a CNN for Fine-Grained
Recognition",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "4148-4157",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117540"}

@inproceedings{bb121424,
        AUTHOR = "Cai, S.J. and Zuo, W.M. and Zhang, L.",
        TITLE = "Higher-Order Integration of Hierarchical Convolutional Activations
for Fine-Grained Visual Categorization",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "511-520",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117541"}

@inproceedings{bb121425,
        AUTHOR = "Kong, S. and Fowlkes, C.C.",
        TITLE = "Pixel-Wise Attentional Gating for Scene Parsing",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "1024-1033",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117542"}

@inproceedings{bb121426,
        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#TT117543"}

@inproceedings{bb121427,
        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#TT117544"}

@inproceedings{bb121428,
        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#TT117545"}

@inproceedings{bb121429,
        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#TT117546"}

@inproceedings{bb121430,
        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#TT117547"}

@inproceedings{bb121431,
        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#TT117548"}

@inproceedings{bb121432,
        AUTHOR = "Zhang, H. and Xu, T. and Elhoseiny, M. and Huang, X.L. and Zhang, S.T. and Elgammal, A.E. and Metaxas, D.N.",
        TITLE = "SPDA-CNN: Unifying Semantic Part Detection and Abstraction for
Fine-Grained Recognition",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "1143-1152",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117549"}

@inproceedings{bb121433,
        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#TT117550"}

@inproceedings{bb121434,
        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#TT117551"}

@inproceedings{bb121435,
        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#TT117552"}

@inproceedings{bb121436,
        AUTHOR = "Zhang, N. and Donahue, J. and Girshick, R. and Darrell, T.J.",
        TITLE = "Part-Based R-CNNs for Fine-Grained Category Detection",
        BOOKTITLE = ECCV14,
        YEAR = "2014",
        PAGES = "I: 834-849",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605cnnfg2.html#TT117553"}

@article{bb121437,
        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#TT117554"}

@article{bb121438,
        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#TT117555"}

@book{bb121439,
        AUTHOR = "McKevitt, P.",
        TITLE = "Integration of Natural-Language and Vision Processing: Theory",
        PUBLISHER = "Springer",
        YEAR = "1995",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT117555"}

@article{bb121440,
        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#TT117556"}

@article{bb121441,
        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#TT117557"}

@article{bb121442,
        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#TT117558"}

@book{bb121443,
        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#TT117558"}

@article{bb121444,
        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#TT117559"}

@book{bb121445,
        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#TT117560"}

@article{bb121446,
        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#TT117561"}

@article{bb121447,
        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#TT117562"}

@article{bb121448,
        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#TT117563"}

@article{bb121449,
        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#TT117564"}

@article{bb121450,
        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#TT117565"}

@inproceedings{bb121451,
        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#TT117566"}

@inproceedings{bb121452,
        AUTHOR = "Srihari, R.K.",
        TITLE = "Linguistic Context In Vision",
        BOOKTITLE = Context95,
        YEAR = "1995",
        PAGES = "xx",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT117567"}

@inproceedings{bb121453,
        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#TT117568"}

@inproceedings{bb121454,
        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#TT117569"}

@inproceedings{bb121455,
        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#TT117570"}

@inproceedings{bb121456,
        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#TT117571"}

@inproceedings{bb121457,
        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#TT117572"}

@article{bb121458,
        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#TT117573"}

@article{bb121459,
        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#TT117574"}

@article{bb121460,
        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#TT117575"}

@article{bb121461,
        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#TT117576"}

@article{bb121462,
        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#TT117577"}

@article{bb121463,
        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#TT117578"}

@article{bb121464,
        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#TT117579"}

@article{bb121465,
        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#TT117580"}

@article{bb121466,
        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#TT117581"}

@article{bb121467,
        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#TT117582"}

@inproceedings{bb121468,
        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#TT117583"}

@article{bb121469,
        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#TT117584"}

@inproceedings{bb121470,
        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#TT117585"}

@inproceedings{bb121471,
        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#TT117586"}

@article{bb121472,
        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#TT117587"}

@inproceedings{bb121473,
        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#TT117588"}

@inproceedings{bb121474,
        AUTHOR = "Perona, P.",
        TITLE = "A taxonomy of visual recognition",
        BOOKTITLE = VMV04,
        YEAR = "2004",
        PAGES = "187",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT117589"}

@inproceedings{bb121475,
        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#TT117590"}

@inproceedings{bb121476,
        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#TT117591"}

@inproceedings{bb121477,
        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#TT117592"}

@inproceedings{bb121478,
        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#TT117593"}

@article{bb121479,
        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#TT117594"}

@inproceedings{bb121480,
        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#TT117595"}

@article{bb121481,
        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#TT117596"}

@inproceedings{bb121482,
        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#TT117597"}

@inproceedings{bb121483,
        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#TT117598"}

@article{bb121484,
        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#TT117599"}

@inproceedings{bb121485,
        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#TT117600"}

@inproceedings{bb121486,
        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#TT117601"}

@inproceedings{bb121487,
        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#TT117602"}

@inproceedings{bb121488,
        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#TT117603"}

@inproceedings{bb121489,
        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#TT117604"}

@inproceedings{bb121490,
        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#TT117605"}

@article{bb121491,
        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#TT117606"}

@article{bb121492,
        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#TT117607"}

@inproceedings{bb121493,
        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#TT117608"}

@article{bb121494,
        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#TT117609"}

@article{bb121495,
        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#TT117610"}

@article{bb121496,
        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#TT117611"}

@article{bb121497,
        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#TT117611"}

@article{bb121498,
        AUTHOR = "Li, L.H. and Tang, S. and Zhang, Y.D. and Deng, L.X. and Tian, Q.",
        TITLE = "GLA: Global-Local Attention for Image Description",
        JOURNAL = MultMed,
        VOLUME = "20",
        YEAR = "2018",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "726-737",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117612"}

@article{bb121499,
        AUTHOR = "Lu, X. and Wang, B. and Zheng, X. and Li, X.",
        TITLE = "Exploring Models and Data for Remote Sensing Image Caption Generation",
        JOURNAL = GeoRS,
        VOLUME = "56",
        YEAR = "2018",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "2183-2195",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117613"}