@inproceedings{bb114200,
        AUTHOR = "Hendricks, L.A. and Venugopalan, S. and Rohrbach, M. and Mooney, R. and Saenko, K. and Darrell, T.J.",
        TITLE = "Deep Compositional Captioning: Describing Novel Object Categories
without Paired Training Data",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "1-10",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110440"}

@inproceedings{bb114201,
        AUTHOR = "Johnson, J. and Karpathy, A. and Fei Fei, L.",
        TITLE = "DenseCap:
Fully Convolutional Localization Networks for Dense Captioning",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4565-4574",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110441"}

@inproceedings{bb114202,
        AUTHOR = "Wang, M. and Song, L. and Yang, X.K. and Luo, C.F.",
        TITLE = "A parallel-fusion RNN-LSTM architecture for image caption generation",
        BOOKTITLE = ICIP16,
        YEAR = "2016",
        PAGES = "4448-4452",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110442"}

@inproceedings{bb114203,
        AUTHOR = "Lin, X. and Parikh, D.",
        TITLE = "Leveraging Visual Question Answering for Image-Caption Ranking",
        BOOKTITLE = ECCV16,
        YEAR = "2016",
        PAGES = "II: 261-277",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110443"}

@inproceedings{bb114204,
        AUTHOR = "Lin, X. and Parikh, D.",
        TITLE = "Don't just listen, use your imagination:
Leveraging visual common sense for non-visual tasks",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2984-2993",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110444"}

@inproceedings{bb114205,
        AUTHOR = "Chen, T.L. and Zhang, Z.P. and You, Q.Z. and Fang, C. and Wang, Z.W. and Jin, H.L. and Luo, J.B.",
        TITLE = "'Factual' or 'Emotional':
Stylized Image Captioning with Adaptive Learning and Attention",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "X: 527-543",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110445"}

@inproceedings{bb114206,
        AUTHOR = "You, Q.Z. and Jin, H.L. and Wang, Z.W. and Fang, C. and Luo, J.B.",
        TITLE = "Image Captioning with Semantic Attention",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4651-4659",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110446"}

@inproceedings{bb114207,
        AUTHOR = "Jia, X. and Gavves, E. and Fernando, B. and Tuytelaars, T.",
        TITLE = "Guiding the Long-Short Term Memory Model for Image Caption Generation",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "2407-2415",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110447"}

@inproceedings{bb114208,
        AUTHOR = "Chen, X.L. and Zitnick, C.L.",
        TITLE = "Mind's eye:
A recurrent visual representation for image caption generation",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2422-2431",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110448"}

@inproceedings{bb114209,
        AUTHOR = "Vedantam, R. and Zitnick, C.L. and Parikh, D.",
        TITLE = "CIDEr: Consensus-based image description evaluation",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "4566-4575",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110449"}

@inproceedings{bb114210,
        AUTHOR = "Fang, H. and Gupta, S. and Iandola, F. and Srivastava, R.K. and Deng, L. and Dollar, P. and Gao, J.F. and He, X.D. and Mitchell, M. and Platt, J.C. and Zitnick, C.L. and Zweig, G.",
        TITLE = "From captions to visual concepts and back",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "1473-1482",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110450"}

@inproceedings{bb114211,
        AUTHOR = "Ramnath, K. and Baker, S. and Vanderwende, L. and El Saban, M. and Sinha, S.N. and Kannan, A. and Hassan, N. and Galley, M. and Yang, Y. and Ramanan, D. and Bergamo, A. and Torresani, L.",
        TITLE = "AutoCaption: Automatic caption generation for personal photos",
        BOOKTITLE = WACV14,
        YEAR = "2014",
        PAGES = "1050-1057",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110451"}

@article{bb114212,
        AUTHOR = "Verma, Y. and Jawahar, C.V.",
        TITLE = "A support vector approach for cross-modal search of images and texts",
        JOURNAL = CVIU,
        VOLUME = "154",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "48-63",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110452"}

@inproceedings{bb114213,
        AUTHOR = "Dutta, A. and Verma, Y. and Jawahar, C.V.",
        TITLE = "Recurrent Image Annotation with Explicit Inter-Label Dependencies",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXIX: 191-207",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110453"}

@article{bb114214,
        AUTHOR = "Xue, J.F. and Eguchi, K.",
        TITLE = "Video Data Modeling Using Sequential Correspondence Hierarchical
Dirichlet Processes",
        JOURNAL = IEICE,
        VOLUME = "E100-D",
        YEAR = "2017",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "33-41",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110454"}

@article{bb114215,
        AUTHOR = "Liu, A.A. and Xu, N. and Wong, Y.K. and Li, J. and Su, Y.T. and Kankanhalli, M.",
        TITLE = "Hierarchical & multimodal video captioning: Discovering and
transferring multimodal knowledge for vision to language",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "113-125",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110455"}

@article{bb114216,
        AUTHOR = "Guan, J.N. and Wang, E.",
        TITLE = "Repeated review based image captioning for image evidence review",
        JOURNAL = SP:IC,
        VOLUME = "63",
        YEAR = "2018",
        PAGES = "141-148",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110456"}

@article{bb114217,
        AUTHOR = "Park, C.C. and Kim, B. and Kim, G.",
        TITLE = "Towards Personalized Image Captioning via Multimodal Memory Networks",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "999-1012",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110457"}

@inproceedings{bb114218,
        AUTHOR = "Park, C.C. and Kim, B. and Kim, G.",
        TITLE = "Attend to You: Personalized Image Captioning with Context Sequence
Memory Networks",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6432-6440",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110458"}

@article{bb114219,
        AUTHOR = "Xian, Y. and Tian, Y.",
        TITLE = "Self-Guiding Multimodal LSTM: When We Do Not Have a Perfect Training
Dataset for Image Captioning",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "5241-5252",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110459"}

@article{bb114220,
        AUTHOR = "Yang, M. and Zhao, W. and Xu, W. and Feng, Y. and Zhao, Z. and Chen, X. and Lei, K.",
        TITLE = "Multitask Learning for Cross-Domain Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1047-1061",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110460"}

@article{bb114221,
        AUTHOR = "Yu, N. and Hu, X. and Song, B. and Yang, J. and Zhang, J.",
        TITLE = "Topic-Oriented Image Captioning Based on Order-Embedding",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "2743-2754",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110461"}

@article{bb114222,
        AUTHOR = "Li, X. and Xu, C. and Wang, X. and Lan, W. and Jia, Z. and Yang, G. and Xu, J.",
        TITLE = "COCO-CN for Cross-Lingual Image Tagging, Captioning, and Retrieval",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2347-2360",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110462"}

@article{bb114223,
        AUTHOR = "Tian, C. and Tian, M. and Jiang, M.M. and Liu, H. and Deng, D.H.",
        TITLE = "How much do cross-modal related semantics benefit image captioning by
weighting attributes and re-ranking sentences?",
        JOURNAL = PRL,
        VOLUME = "125",
        YEAR = "2019",
        PAGES = "639-645",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110463"}

@article{bb114224,
        AUTHOR = "Niu, Y. and Lu, Z. and Wen, J. and Xiang, T. and Chang, S.",
        TITLE = "Multi-Modal Multi-Scale Deep Learning for Large-Scale Image
Annotation",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1720-1731",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110464"}

@article{bb114225,
        AUTHOR = "Huang, Y. and Chen, J. and Ouyang, W. and Wan, W. and Xue, Y.",
        TITLE = "Image Captioning With End-to-End Attribute Detection and Subsequent
Attributes Prediction",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        PAGES = "4013-4026",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110465"}

@article{bb114226,
        AUTHOR = "Zhao, W. and Wu, X. and Luo, J.",
        TITLE = "Cross-Domain Image Captioning via Cross-Modal Retrieval and Model
Adaptation",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "1180-1192",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110466"}

@article{bb114227,
        AUTHOR = "Wang, H. and Du, Y.T. and Zhang, G.X. and Cai, Z.M. and Su, C.",
        TITLE = "Learning Fundamental Visual Concepts Based on Evolved Multi-Edge
Concept Graph",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "4400-4413",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110467"}

@inproceedings{bb114228,
        AUTHOR = "Kuo, C.W. and Kira, Z.",
        TITLE = "Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual
Context for Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17948-17958",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110468"}

@inproceedings{bb114229,
        AUTHOR = "Zhou, M.Y. and Zhou, L.W. and Wang, S.H. and Cheng, Y. and Li, L.J. and Yu, Z. and Liu, J.J.",
        TITLE = "UC2: Universal Cross-lingual Cross-modal Vision-and-Language
Pre-training",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "4153-4163",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110469"}

@inproceedings{bb114230,
        AUTHOR = "Laina, I. and Rupprecht, C. and Navab, N.",
        TITLE = "Towards Unsupervised Image Captioning With Shared Multimodal
Embeddings",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "7413-7423",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110470"}

@inproceedings{bb114231,
        AUTHOR = "Akbari, H. and Karaman, S. and Bhargava, S. and Chen, B. and Vondrick, C. and Chang, S.F.",
        TITLE = "Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "12468-12478",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110471"}

@inproceedings{bb114232,
        AUTHOR = "Chen, T.H. and Liao, Y.H. and Chuang, C.Y. and Hsu, W.T. and Fu, J. and Sun, M.",
        TITLE = "Show, Adapt and Tell:
Adversarial Training of Cross-Domain Image Captioner",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "521-530",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110472"}

@inproceedings{bb114233,
        AUTHOR = "Niu, Z.X. and Zhou, M. and Wang, L. and Gao, X.B. and Hua, G.",
        TITLE = "Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1899-1907",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110473"}

@inproceedings{bb114234,
        AUTHOR = "Pini, S. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "Towards Video Captioning with Naming:
A Novel Dataset and a Multi-modal Approach",
        BOOKTITLE = CIAP17,
        YEAR = "2017",
        PAGES = "II:384-395",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110474"}

@inproceedings{bb114235,
        AUTHOR = "Pan, J.Y. and Yang, H.J. and Faloutsos, C.",
        TITLE = "MMSS: Graph-based Multi-modal Story-oriented Video Summarization and
Retrieval",
        BOOKTITLE = CMU-CS-TR,
        YEAR = "2004",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110475"}

@inproceedings{bb114236,
        AUTHOR = "Pan, J.Y. and Yang, H.J. and Faloutsos, C. and Duygulu, P.",
        TITLE = "GCap: Graph-based Automatic Image Captioning",
        BOOKTITLE = MMDE04,
        YEAR = "2004",
        PAGES = "146",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110476"}

@inproceedings{bb114237,
        AUTHOR = "Pan, J.Y.",
        TITLE = "Advanced Tools for Video and Multimedia Mining",
        BOOKTITLE = CMU-CS,
        YEAR = "2006",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110477"}

@inproceedings{bb114238,
        AUTHOR = "Pan, J.Y.",
        TITLE = "Advanced Tools for Video and Multimedia Mining",
        BOOKTITLE = Ph.D.,
        YEAR = "2006",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT110477"}

@article{bb114239,
        AUTHOR = "Yu, J. and Li, J. and Yu, Z. and Huang, Q.",
        TITLE = "Multimodal Transformer With Multi-View Visual Representation for
Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "30",
        YEAR = "2020",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "4467-4480",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110478"}

@article{bb114240,
        AUTHOR = "Zhang, Y. and Shi, X.Y. and Mi, S. and Yang, X.",
        TITLE = "Image captioning with transformer and knowledge graph",
        JOURNAL = PRL,
        VOLUME = "143",
        YEAR = "2021",
        PAGES = "43-49",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110479"}

@article{bb114241,
        AUTHOR = "Yan, C.G. and Hao, Y.M. and Li, L. and Yin, J. and Liu, A. and Mao, Z. and Chen, Z.Y. and Gao, X.Y.",
        TITLE = "Task-Adaptive Attention for Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "43-51",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110480"}

@article{bb114242,
        AUTHOR = "Yuan, J. and Zhu, S. and Huang, S.Y. and Zhang, H.W. and Xiao, Y.Q. and Li, Z.Y. and Wang, M.",
        TITLE = "Discriminative Style Learning for Cross-Domain Image Captioning",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "1723-1736",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110481"}

@inproceedings{bb114243,
        AUTHOR = "Zhou, Y. and Zhang, Y. and Hu, Z.Z. and Wang, M.",
        TITLE = "Semi-Autoregressive Transformer for Image Captioning",
        BOOKTITLE = CLVL21,
        YEAR = "2021",
        PAGES = "3132-3136",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110482"}

@article{bb114244,
        AUTHOR = "Ren, Z.H. and Gou, S.P. and Guo, Z. and Mao, S.S. and Li, R.M.",
        TITLE = "A Mask-Guided Transformer Network with Topic Token for Remote Sensing
Image Captioning",
        JOURNAL = RS,
        VOLUME = "14",
        YEAR = "2022",
        NUMBER = "12",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110483"}

@article{bb114245,
        AUTHOR = "Ji, J.Y. and Ma, Y. and Sun, X.S. and Zhou, Y. and Wu, Y.J. and Ji, R.R.",
        TITLE = "Knowing What to Learn: A Metric-Oriented Focal Mechanism for Image
Captioning",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "4321-4335",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110484"}

@article{bb114246,
        AUTHOR = "Li, X. and Zhang, W.K. and Sun, X. and Gao, X.",
        TITLE = "Semantic-meshed and content-guided transformer for image captioning",
        JOURNAL = IET-CV,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "5",
        PAGES = "431-444",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110485"}

@article{bb114247,
        AUTHOR = "Xian, T.T. and Li, Z.X. and Tang, Z.J. and Ma, H.F.",
        TITLE = "Adaptive Path Selection for Dynamic Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "5762-5775",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110486"}

@inproceedings{bb114248,
        AUTHOR = "Vo, D.M. and Chen, H. and Sugimoto, A. and Nakayama, H.",
        TITLE = "NOC-REK: Novel Object Captioning with Retrieved Vocabulary from
External Knowledge",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17979-17987",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110487"}

@inproceedings{bb114249,
        AUTHOR = "Yuan, Z.H. and Yan, X. and Liao, Y. and Guo, Y. and Li, G. and Cui, S.G. and Li, Z.",
        TITLE = "X-Trans2Cap:
Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "8553-8563",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110488"}

@inproceedings{bb114250,
        AUTHOR = "Liu, B. and Wang, D. and Yang, X. and Zhou, Y. and Yao, R. and Shao, Z.W. and Zhao, J.Q.",
        TITLE = "Show, Deconfound and Tell: Image Captioning with Causal Inference",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "18020-18029",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110489"}

@inproceedings{bb114251,
        AUTHOR = "Fang, Z.Y. and Wang, J.F. and Hu, X.W. and Liang, L. and Gan, Z. and Wang, L.J. and Yang, Y.Z. and Liu, Z.C.",
        TITLE = "Injecting Semantic Concepts into End-to-End Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17988-17998",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110490"}

@inproceedings{bb114252,
        AUTHOR = "Li, Y. and Pan, Y. and Yao, T. and Mei, T.",
        TITLE = "Comprehending and Ordering Semantics for Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17969-17978",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110491"}

@inproceedings{bb114253,
        AUTHOR = "Hu, X.W. and Gan, Z. and Wang, J.F. and Yang, Z.Y. and Liu, Z.C. and Lu, Y. and Wang, L.J.",
        TITLE = "Scaling Up Vision-Language Pretraining for Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17959-17968",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110492"}

@inproceedings{bb114254,
        AUTHOR = "Fei, Z.C. and Yan, X. and Wang, S. and Tian, Q.",
        TITLE = "DeeCap: Dynamic Early Exiting for Efficient Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "12206-12216",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110493"}

@inproceedings{bb114255,
        AUTHOR = "Wu, M.R. and Zhang, X.Y. and Sun, X.S. and Zhou, Y. and Chen, C. and Gu, J.X. and Sun, X. and Ji, R.R.",
        TITLE = "DIFNet: Boosting Visual Information Flow for Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17999-18008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110494"}

@inproceedings{bb114256,
        AUTHOR = "Rio Torto, I. and Cardoso, J.S. and Teixeira, L.F.",
        TITLE = "From Captions to Explanations: A Multimodal Transformer-based
Architecture for Natural Language Explanation Generation",
        BOOKTITLE = IbPRIA22,
        YEAR = "2022",
        PAGES = "54-65",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110495"}

@inproceedings{bb114257,
        AUTHOR = "Chen, H.S. and Wang, Y. and Yang, X. and Li, J.",
        TITLE = "Captioning Transformer With Scene Graph Guiding",
        BOOKTITLE = ICIP21,
        YEAR = "2021",
        PAGES = "2538-2542",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110496"}

@inproceedings{bb114258,
        AUTHOR = "Zhang, P.C. and Li, X.J. and Hu, X.W. and Yang, J.W. and Zhang, L. and Wang, L.J. and Choi, Y.J. and Gao, J.F.",
        TITLE = "VinVL: Revisiting Visual Representations in Vision-Language Models",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "5575-5584",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110497"}

@inproceedings{bb114259,
        AUTHOR = "Zhang, X.Y. and Sun, X.S. and Luo, Y.P. and Ji, J.Y. and Zhou, Y. and Wu, Y.J. and Huang, F.Y. and Ji, R.R.",
        TITLE = "RSTNet:
Captioning with Adaptive Attention on Visual and Non-Visual Words",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "15460-15469",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110498"}

@inproceedings{bb114260,
        AUTHOR = "He, S. and Liao, W.T. and Tavakoli, H.R. and Yang, M. and Rosenhahn, B. and Pugeault, N.",
        TITLE = "Image Captioning Through Image Transformer",
        BOOKTITLE = ACCV20,
        YEAR = "2020",
        PAGES = "IV:153-169",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110499"}

@inproceedings{bb114261,
        AUTHOR = "Cornia, M. and Stefanini, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "Meshed-Memory Transformer for Image Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10575-10584",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110500"}

@inproceedings{bb114262,
        AUTHOR = "Li, G. and Zhu, L. and Liu, P. and Yang, Y.",
        TITLE = "Entangled Transformer for Image Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "8927-8936",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT110501"}

@article{bb114263,
        AUTHOR = "Sharma, D. and Chattopadhyay, C.",
        TITLE = "High-level feature aggregation for fine-grained architectural floor
plan retrieval",
        JOURNAL = IET-CV,
        VOLUME = "12",
        YEAR = "2018",
        NUMBER = "5",
        MONTH = "August",
        PAGES = "702-709",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110502"}

@inproceedings{bb114264,
        AUTHOR = "Sharma, D. and Chattopadhyay, C. and Harit, G.",
        TITLE = "A unified framework for semantic matching of architectural floorplans",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "2422-2427",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110503"}

@article{bb114265,
        AUTHOR = "Ham, B. and Cho, M.S. and Schmid, C. and Ponce, J.",
        TITLE = "Proposal Flow: Semantic Correspondences from Object Proposals",
        JOURNAL = PAMI,
        VOLUME = "40",
        YEAR = "2018",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1711-1725",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110504"}

@inproceedings{bb114266,
        AUTHOR = "Ham, B. and Cho, M.S. and Schmid, C. and Ponce, J.",
        TITLE = "Proposal Flow",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "3475-3484",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110505"}

@article{bb114267,
        AUTHOR = "Xiao, T.H. and Liu, S.F. and de Mello, S. and Yu, Z.D. and Kautz, J. and Yang, M.H.",
        TITLE = "Learning Contrastive Representation for Semantic Correspondence",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1293-1309",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110506"}

@article{bb114268,
        AUTHOR = "Yang, M.H. and Kautz, J. and Yu, Z.D. and de Mello, S. and Liu, S.F. and Xiao, T.H.",
        TITLE = "Learning Contrastive Representation for Semantic Correspondence",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "1607-1607",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110506"}

@inproceedings{bb114269,
        AUTHOR = "Yuan, W.T. and Eckart, B. and Kim, K. and Jampani, V. and Fox, D. and Kautz, J.",
        TITLE = "DeepGMR: Learning Latent Gaussian Mixture Models for Registration",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "V:733-750",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110507"}

@inproceedings{bb114270,
        AUTHOR = "Eckart, B. and Kim, K. and Kautz, J.",
        TITLE = "HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XV: 730-746",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110508"}

@article{bb114271,
        AUTHOR = "He, J.F. and Zhang, T.Z. and Zheng, Y. and Xu, M.L. and Zhang, Y.D. and Wu, F.",
        TITLE = "Consistency Graph Modeling for Semantic Correspondence",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "4932-4946",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110509"}

@article{bb114272,
        AUTHOR = "Jeon, S. and Kim, S. and Min, D.B. and Sohn, K.H.",
        TITLE = "Pyramidal Semantic Correspondence Networks",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "9102-9118",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110510"}

@article{bb114273,
        AUTHOR = "Liu, H. and Wang, T. and Li, Y.D. and Lang, C. and Jin, Y. and Ling, H.B.",
        TITLE = "Joint Graph Learning and Matching for Semantic Feature Correspondence",
        JOURNAL = PR,
        VOLUME = "134",
        YEAR = "2023",
        PAGES = "109059",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110511"}

@article{bb114274,
        AUTHOR = "Sachdeva, R. and Cordeiro, F.R. and Belagiannis, V. and Reid, I.D. and Carneiro, G.",
        TITLE = "ScanMix: Learning from Severe Label Noise via Semantic Clustering and
Semi-Supervised Learning",
        JOURNAL = PR,
        VOLUME = "134",
        YEAR = "2023",
        PAGES = "109121",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110512"}

@article{bb114275,
        AUTHOR = "Xu, X. and Xu, X. and Shen, F.M. and Li, Y.J.",
        TITLE = "Semantic-Aligned Attention With Refining Feature Embedding for
Few-Shot Image Classification",
        JOURNAL = ITS,
        VOLUME = "23",
        YEAR = "2022",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "25458-25468",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110513"}

@article{bb114276,
        AUTHOR = "Yang, Z.Q. and Zhang, Y. and Du, Y.X. and Tong, C.",
        TITLE = "Semantic-aligned reinforced attention model for zero-shot learning",
        JOURNAL = IVC,
        VOLUME = "128",
        YEAR = "2022",
        PAGES = "104586",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110514"}

@article{bb114277,
        AUTHOR = "Wang, J. and Zhang, Z.Q. and Shi, Z.H. and Cai, J.Y. and Ji, S.W. and Wu, F.",
        TITLE = "Duality-Induced Regularizer for Semantic Matching Knowledge Graph
Embeddings",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "1652-1667",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110515"}

@article{bb114278,
        AUTHOR = "Liu, W.X. and Zhong, X. and Jia, X.M. and Jiang, K. and Lin, C.W.",
        TITLE = "Actor-Aware Alignment Network for Action Recognition",
        JOURNAL = SPLetters,
        VOLUME = "29",
        YEAR = "2022",
        PAGES = "2597-2601",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110516"}

@inproceedings{bb114279,
        AUTHOR = "Bachard, T. and Tom, A.J. and Maugey, T.",
        TITLE = "Semantic Alignment for Multi-Item Compression",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "2841-2845",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110517"}

@inproceedings{bb114280,
        AUTHOR = "Hu, Y.D. and Wang, R. and Zhang, K. and Gao, Y.",
        TITLE = "Semantic-Aware Fine-Grained Correspondence",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXI:97-115",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110518"}

@inproceedings{bb114281,
        AUTHOR = "Kim, J. and Ryoo, K. and Seo, J. and Lee, G. and Kim, D. and Cho, H. and Kim, S.",
        TITLE = "Semi-Supervised Learning of Semantic Correspondence with
Pseudo-Labels",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "19667-19677",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110519"}

@inproceedings{bb114282,
        AUTHOR = "Kim, S. and Min, J. and Cho, M.",
        TITLE = "TransforMatcher: Match-to-Match Attention for Semantic Correspondence",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "8687-8697",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110520"}

@inproceedings{bb114283,
        AUTHOR = "Ye, H.J. and Shi, Y. and Zhan, D.C.",
        TITLE = "Identifying Ambiguous Similarity Conditions via Semantic Matching",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "16589-16598",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110521"}

@inproceedings{bb114284,
        AUTHOR = "Huang, S. and Yang, L. and He, B. and Zhang, S.Y. and He, X.M. and Shrivastava, A.",
        TITLE = "Learning Semantic Correspondence with Sparse Annotations",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XIV:267-284",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110522"}

@inproceedings{bb114285,
        AUTHOR = "Aygun, M. and Aodha, O.M.",
        TITLE = "Demystifying Unsupervised Semantic Correspondence Estimation",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXX:125-142",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110523"}

@inproceedings{bb114286,
        AUTHOR = "Li, X. and Fan, D.P. and Yang, F. and Luo, A. and Cheng, H. and Liu, Z.C.",
        TITLE = "Probabilistic Model Distillation for Semantic Correspondence",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "7501-7510",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110524"}

@inproceedings{bb114287,
        AUTHOR = "Zhao, D.Y. and Song, Z.Y. and Ji, Z.H. and Zhao, G.M. and Ge, W.F. and Yu, Y.Z.",
        TITLE = "Multi-scale Matching Networks for Semantic Correspondence",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "3334-3344",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110525"}

@inproceedings{bb114288,
        AUTHOR = "Lee, J.Y. and de Gol, J. and Fragoso, V. and Sinha, S.N.",
        TITLE = "PatchMatch-Based Neighborhood Consensus for Semantic Correspondence",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "13148-13158",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110526"}

@inproceedings{bb114289,
        AUTHOR = "Liu, Y.B. and Zhu, L.C. and Yamada, M. and Yang, Y.",
        TITLE = "Semantic Correspondence as an Optimal Transport Problem",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "4462-4471",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110527"}

@inproceedings{bb114290,
        AUTHOR = "Laskar, Z. and Kannala, J.H.",
        TITLE = "Semi-supervised Semantic Matching",
        BOOKTITLE = DeepLearn-G18,
        YEAR = "2018",
        PAGES = "III:444-455",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110528"}

@inproceedings{bb114291,
        AUTHOR = "Laskar, Z. and Melekhov, I. and Tavakoli, H.R. and Ylioinas, J.",
        TITLE = "Geometric Image Correspondence Verification by Dense Pixel Matching",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "2510-2519",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110529"}

@inproceedings{bb114292,
        AUTHOR = "Laskar, Z. and Tavakoli, H.R. and Kannala, J.H.",
        TITLE = "Semantic Matching by Weakly Supervised 2D Point Set Registration",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "1061-1069",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110530"}

@inproceedings{bb114293,
        AUTHOR = "Lin, C. and Yao, H.X. and Yu, W. and Sun, X.S.",
        TITLE = "Cycle-Consistency Based Hierarchical Dense Semantic Correspondence",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "818-822",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110531"}

@inproceedings{bb114294,
        AUTHOR = "Han, K. and Rezende, R.S. and Ham, B. and Wong, K.Y.K. and Cho, M.S. and Schmid, C. and Ponce, J.",
        TITLE = "SCNet: Learning Semantic Correspondence",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1849-1858",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110532"}

@inproceedings{bb114295,
        AUTHOR = "Yang, F. and Li, X. and Cheng, H. and Li, J.P. and Chen, L.T.",
        TITLE = "Object-Aware Dense Semantic Correspondence",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "4151-4159",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110533"}

@inproceedings{bb114296,
        AUTHOR = "Bristow, H. and Valmadre, J. and Lucey, S.",
        TITLE = "Dense Semantic Correspondence Where Every Pixel is a Classifier",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "4024-4031",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT110534"}

@article{bb114297,
        AUTHOR = "Suetens, P. and Fua, P.V. and Hanson, A.J.",
        TITLE = "Some Computational Strategies for Object Recognition",
        JOURNAL = Surveys,
        VOLUME = "24",
        YEAR = "1992",
        NUMBER = "1",
        MONTH = "March",
        PAGES = "5-62",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607.html#TT110535"}

@article{bb114298,
        AUTHOR = "Lindenbaum, M.",
        TITLE = "Bounds on Shape-Recognition Performance",
        JOURNAL = PAMI,
        VOLUME = "17",
        YEAR = "1995",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "666-680",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607.html#TT110536"}

@article{bb114299,
        AUTHOR = "Lindenbaum, M. and Ben David, S.",
        TITLE = "VC-Dimension Analysis of Object Recognition Tasks",
        JOURNAL = JMIV,
        VOLUME = "10",
        YEAR = "1999",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "27-49",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607.html#TT110537"}

Last update:Jan 29, 2023 at 20:54:24