@book{bb137600,
AUTHOR = "McKevitt, P.",
TITLE = "Integration of Natural-Language and Vision Processing: Theory",
PUBLISHER = "Springer",
YEAR = "1995",
BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133590"}
@article{bb137601,
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#TT133591"}
@article{bb137602,
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#TT133592"}
@article{bb137603,
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#TT133593"}
@book{bb137604,
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#TT133593"}
@article{bb137605,
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#TT133594"}
@book{bb137606,
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#TT133595"}
@article{bb137607,
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#TT133596"}
@article{bb137608,
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#TT133597"}
@article{bb137609,
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#TT133598"}
@article{bb137610,
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#TT133599"}
@article{bb137611,
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#TT133600"}
@inproceedings{bb137612,
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#TT133601"}
@inproceedings{bb137613,
AUTHOR = "Srihari, R.K.",
TITLE = "Linguistic Context In Vision",
BOOKTITLE = Context95,
YEAR = "1995",
PAGES = "xx",
BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133602"}
@inproceedings{bb137614,
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#TT133603"}
@inproceedings{bb137615,
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#TT133604"}
@inproceedings{bb137616,
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#TT133605"}
@inproceedings{bb137617,
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#TT133606"}
@inproceedings{bb137618,
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#TT133607"}
@article{bb137619,
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#TT133608"}
@article{bb137620,
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#TT133609"}
@article{bb137621,
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#TT133610"}
@article{bb137622,
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#TT133611"}
@article{bb137623,
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#TT133612"}
@article{bb137624,
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#TT133613"}
@article{bb137625,
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#TT133614"}
@article{bb137626,
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#TT133615"}
@article{bb137627,
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#TT133616"}
@article{bb137628,
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#TT133617"}
@inproceedings{bb137629,
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#TT133618"}
@article{bb137630,
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#TT133619"}
@inproceedings{bb137631,
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#TT133620"}
@inproceedings{bb137632,
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#TT133621"}
@article{bb137633,
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#TT133622"}
@inproceedings{bb137634,
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#TT133623"}
@inproceedings{bb137635,
AUTHOR = "Perona, P.",
TITLE = "A taxonomy of visual recognition",
BOOKTITLE = VMV04,
YEAR = "2004",
PAGES = "187",
BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT133624"}
@inproceedings{bb137636,
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#TT133625"}
@inproceedings{bb137637,
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#TT133626"}
@inproceedings{bb137638,
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#TT133627"}
@inproceedings{bb137639,
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#TT133628"}
@article{bb137640,
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#TT133629"}
@inproceedings{bb137641,
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#TT133630"}
@article{bb137642,
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#TT133631"}
@inproceedings{bb137643,
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#TT133632"}
@inproceedings{bb137644,
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#TT133633"}
@article{bb137645,
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#TT133634"}
@inproceedings{bb137646,
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#TT133635"}
@inproceedings{bb137647,
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#TT133636"}
@inproceedings{bb137648,
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#TT133637"}
@inproceedings{bb137649,
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#TT133638"}
@inproceedings{bb137650,
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#TT133639"}
@inproceedings{bb137651,
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#TT133640"}
@article{bb137652,
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#TT133641"}
@article{bb137653,
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#TT133642"}
@inproceedings{bb137654,
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#TT133643"}
@article{bb137655,
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#TT133644"}
@article{bb137656,
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#TT133645"}
@article{bb137657,
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#TT133646"}
@article{bb137658,
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#TT133646"}
@article{bb137659,
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#TT133647"}
@article{bb137660,
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#TT133648"}
@article{bb137661,
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#TT133649"}
@article{bb137662,
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#TT133650"}
@article{bb137663,
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#TT133651"}
@article{bb137664,
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#TT133652"}
@article{bb137665,
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#TT133653"}
@article{bb137666,
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#TT133654"}
@article{bb137667,
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#TT133655"}
@article{bb137668,
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#TT133656"}
@article{bb137669,
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#TT133657"}
@article{bb137670,
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#TT133658"}
@article{bb137671,
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#TT133659"}
@article{bb137672,
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#TT133660"}
@article{bb137673,
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#TT133661"}
@article{bb137674,
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#TT133662"}
@article{bb137675,
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#TT133663"}
@article{bb137676,
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#TT133664"}
@article{bb137677,
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#TT133665"}
@article{bb137678,
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#TT133666"}
@article{bb137679,
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#TT133667"}
@article{bb137680,
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#TT133668"}
@article{bb137681,
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#TT133669"}
@article{bb137682,
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#TT133670"}
@article{bb137683,
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#TT133671"}
@article{bb137684,
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#TT133672"}
@article{bb137685,
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#TT133673"}
@article{bb137686,
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#TT133674"}
@inproceedings{bb137687,
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#TT133675"}
@article{bb137688,
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#TT133676"}
@article{bb137689,
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#TT133677"}
@inproceedings{bb137690,
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#TT133678"}
@article{bb137691,
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#TT133679"}
@article{bb137692,
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#TT133680"}
@article{bb137693,
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#TT133681"}
@article{bb137694,
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#TT133682"}
@article{bb137695,
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#TT133683"}
@article{bb137696,
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#TT133684"}
@article{bb137697,
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#TT133685"}
@article{bb137698,
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#TT133686"}
@article{bb137699,
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#TT133687"}
Last update:Aug 19, 2026 at 13:26:35