@inproceedings{bb105700,
AUTHOR = "Zhou, Y. and Wang, M. and Liu, D. and Hu, Z. and Zhang, H.",
TITLE = "More Grounded Image Captioning by Distilling Image-Text Matching
Model",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "4776-4785",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102041"}
@inproceedings{bb105701,
AUTHOR = "Sammani, F. and Melas Kyriazi, L.",
TITLE = "Show, Edit and Tell: A Framework for Editing Image Captions",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "4807-4815",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102042"}
@inproceedings{bb105702,
AUTHOR = "Chen, S. and Jin, Q. and Wang, P. and Wu, Q.",
TITLE = "Say As You Wish: Fine-Grained Control of Image Caption Generation
With Abstract Scene Graphs",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "9959-9968",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102043"}
@inproceedings{bb105703,
AUTHOR = "Guo, L. and Liu, J. and Zhu, X. and Yao, P. and Lu, S. and Lu, H.",
TITLE = "Normalized and Geometry-Aware Self-Attention Network for Image
Captioning",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "10324-10333",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102044"}
@inproceedings{bb105704,
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/match607ic1.html#TT102045"}
@inproceedings{bb105705,
AUTHOR = "Chen, J. and Jin, Q.",
TITLE = "Better Captioning With Sequence-Level Exploration",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "10887-10896",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102046"}
@inproceedings{bb105706,
AUTHOR = "Pan, Y. and Yao, T. and Li, Y. and Mei, T.",
TITLE = "X-Linear Attention Networks for Image Captioning",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "10968-10977",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102047"}
@inproceedings{bb105707,
AUTHOR = "Tran, A. and Mathews, A. and Xie, L.",
TITLE = "Transform and Tell: Entity-Aware News Image Captioning",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "13032-13042",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102048"}
@inproceedings{bb105708,
AUTHOR = "Park, G. and Han, C. and Kim, D. and Yoon, W.J.",
TITLE = "MHSAN: Multi-Head Self-Attention Network for Visual Semantic
Embedding",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "1507-1515",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102049"}
@inproceedings{bb105709,
AUTHOR = "Chen, C. and Zhang, R. and Koh, E. and Kim, S. and Cohen, S. and Rossi, R.",
TITLE = "Figure Captioning with Relation Maps for Reasoning",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "1526-1534",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102050"}
@inproceedings{bb105710,
AUTHOR = "He, S. and Tavakoli, H.R. and Borji, A. and Pugeault, N.",
TITLE = "Human Attention in Image Captioning: Dataset and Analysis",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "8528-8537",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102051"}
@inproceedings{bb105711,
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/match607ic1.html#TT102052"}
@inproceedings{bb105712,
AUTHOR = "Huang, L. and Wang, W. and Chen, J. and Wei, X.",
TITLE = "Attention on Attention for Image Captioning",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "4633-4642",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102053"}
@inproceedings{bb105713,
AUTHOR = "Yang, X. and Zhang, H. and Cai, J.",
TITLE = "Learning to Collocate Neural Modules for Image Captioning",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "4249-4259",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102054"}
@inproceedings{bb105714,
AUTHOR = "Yao, T. and Pan, Y. and Li, Y. and Mei, T.",
TITLE = "Hierarchy Parsing for Image Captioning",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "2621-2629",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102055"}
@inproceedings{bb105715,
AUTHOR = "Liu, L. and Tang, J. and Wan, X. and Guo, Z.",
TITLE = "Generating Diverse and Descriptive Image Captions Using Visual
Paraphrases",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "4239-4248",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102056"}
@inproceedings{bb105716,
AUTHOR = "Ke, L. and Pei, W. and Li, R. and Shen, X. and Tai, Y.",
TITLE = "Reflective Decoding Network for Image Captioning",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "8887-8896",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102057"}
@inproceedings{bb105717,
AUTHOR = "Vered, G. and Oren, G. and Atzmon, Y. and Chechik, G.",
TITLE = "Joint Optimization for Cooperative Image Captioning",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "8897-8906",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102058"}
@inproceedings{bb105718,
AUTHOR = "Ge, H. and Yan, Z. and Zhang, K. and Zhao, M. and Sun, L.",
TITLE = "Exploring Overall Contextual Information for Image Captioning in
Human-Like Cognitive Style",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "1754-1763",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102059"}
@inproceedings{bb105719,
AUTHOR = "Agrawal, H. and Desai, K. and Wang, Y. and Chen, X. and Jain, R. and Johnson, M. and Batra, D. and Parikh, D. and Lee, S. and Anderson, P.",
TITLE = "nocaps: novel object captioning at scale",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "8947-8956",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102060"}
@inproceedings{bb105720,
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/match607ic1.html#TT102061"}
@inproceedings{bb105721,
AUTHOR = "Hu, H. and Misra, I. and van der Maaten, L.",
TITLE = "Evaluating Text-to-Image Matching using Binary Image Selection
(BISON)",
BOOKTITLE = CLVL19,
YEAR = "2019",
PAGES = "1887-1890",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102062"}
@inproceedings{bb105722,
AUTHOR = "Nguyen, A. and Tran, Q.D. and Do, T. and Reid, I. and Caldwell, D.G. and Tsagarakis, N.G.",
TITLE = "Object Captioning and Retrieval with Natural Language",
BOOKTITLE = ACVR19,
YEAR = "2019",
PAGES = "2584-2592",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102063"}
@inproceedings{bb105723,
AUTHOR = "Gu, J. and Joty, S. and Cai, J. and Zhao, H. and Yang, X. and Wang, G.",
TITLE = "Unpaired Image Captioning via Scene Graph Alignments",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "10322-10331",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102064"}
@inproceedings{bb105724,
AUTHOR = "Shen, T. and Kar, A. and Fidler, S.",
TITLE = "Learning to Caption Images Through a Lifetime by Asking Questions",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "10392-10401",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102065"}
@inproceedings{bb105725,
AUTHOR = "Tanaka, M. and Itamochi, T. and Narioka, K. and Sato, I. and Ushiku, Y. and Harada, T.",
TITLE = "Generating Easy-to-Understand Referring Expressions for Target
Identifications",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "5793-5802",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102066"}
@inproceedings{bb105726,
AUTHOR = "Aneja, J. and Agrawal, H. and Batra, D. and Schwing, A.G.",
TITLE = "Sequential Latent Spaces for Modeling the Intention During Diverse
Image Captioning",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "4260-4269",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102067"}
@inproceedings{bb105727,
AUTHOR = "Gupta, T. and Schwing, A.G. and Hoiem, D.",
TITLE = "ViCo: Word Embeddings From Visual Co-Occurrences",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "7424-7433",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102068"}
@inproceedings{bb105728,
AUTHOR = "Deshpande, A. and Aneja, J. and Wang, L. and Schwing, A.G. and Forsyth, D.",
TITLE = "Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "10687-10696",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102069"}
@inproceedings{bb105729,
AUTHOR = "Wei, H.Y. and Li, Z.X. and Zhang, C.L.",
TITLE = "Image Captioning Based on Visual and Semantic Attention",
BOOKTITLE = MMMod20,
YEAR = "2020",
PAGES = "I:151-162",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102070"}
@inproceedings{bb105730,
AUTHOR = "Dognin, P. and Melnyk, I. and Mroueh, Y. and Ross, J. and Sercu, T.",
TITLE = "Adversarial Semantic Alignment for Improved Image Captions",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "10455-10463",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102071"}
@inproceedings{bb105731,
AUTHOR = "Yang, X. and Tang, K. and Zhang, H. 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#TT102072"}
@inproceedings{bb105732,
AUTHOR = "Fukui, H. and Hirakawa, T. and Yamashita, T. and Fujiyoshi, H.",
TITLE = "Attention Branch Network: Learning of Attention Mechanism for Visual
Explanation",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "10697-10706",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102073"}
@inproceedings{bb105733,
AUTHOR = "Biten, A.F. and Gomez, L. and Rusinol, M. and Karatzas, D.",
TITLE = "Good News, Everyone! Context Driven Entity-Aware Captioning for News
Images",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "12458-12467",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102074"}
@inproceedings{bb105734,
AUTHOR = "Suris, D. and Epstein, D. and Ji, H. and Chang, S.F. and Vondrick, C.",
TITLE = "Learning to Learn Words from Visual Scenes",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XXIX: 434-452",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102075"}
@inproceedings{bb105735,
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/match607ic1.html#TT102076"}
@inproceedings{bb105736,
AUTHOR = "Li, Y. and Yao, T. and Pan, Y. 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#TT102077"}
@inproceedings{bb105737,
AUTHOR = "Bracha, L. and Chechik, G.",
TITLE = "Informative Object Annotations: Tell Me Something I Don't Know",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "12499-12507",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102078"}
@inproceedings{bb105738,
AUTHOR = "Shuster, K. and Humeau, S. and Hu, H. and Bordes, A. and Weston, J.",
TITLE = "Engaging Image Captioning via Personality",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "12508-12518",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102079"}
@inproceedings{bb105739,
AUTHOR = "Feng, Y. and Ma, L. and Liu, W. and Luo, J.B.",
TITLE = "Unsupervised Image Captioning",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "4120-4129",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102080"}
@inproceedings{bb105740,
AUTHOR = "Xu, Y. and Wu, B.Y. and Shen, F. and Fan, Y.B. and Zhang, Y. and Shen, H.T. and Liu, W.",
TITLE = "Exact Adversarial Attack to Image Captioning via Structured Output
Learning With Latent Variables",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "4130-4139",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102081"}
@inproceedings{bb105741,
AUTHOR = "Wang, Q.Z. and Chan, A.B.",
TITLE = "Describing Like Humans: On Diversity in Image Captioning",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "4190-4198",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102082"}
@inproceedings{bb105742,
AUTHOR = "Guo, L.T. and Liu, J. and Yao, P. and Li, J.W. and Lu, H.Q.",
TITLE = "MSCap: Multi-Style Image Captioning With Unpaired Stylized Text",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "4199-4208",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102083"}
@inproceedings{bb105743,
AUTHOR = "Zhang, L. and Zhang, J.M. and Lin, Z. and Lu, H.C. and He, Y.",
TITLE = "CapSal: Leveraging Captioning to Boost Semantics for Salient Object
Detection",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6017-6026",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102084"}
@inproceedings{bb105744,
AUTHOR = "Yin, G.J. and Sheng, L. and Liu, B. and Yu, N.H. and Wang, X.G. and Shao, J.",
TITLE = "Context and Attribute Grounded Dense Captioning",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6234-6243",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102085"}
@inproceedings{bb105745,
AUTHOR = "Kim, D.J. and Choi, J. and Oh, T.H. and Kweon, I.S.",
TITLE = "Dense Relational Captioning: Triple-Stream Networks for
Relationship-Based Captioning",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6264-6273",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102086"}
@inproceedings{bb105746,
AUTHOR = "Gao, J.L. and Wang, S. and Wang, S.S. and Ma, S.W. and Gao, W.",
TITLE = "Self-Critical N-Step Training for Image Captioning",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6293-6301",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102087"}
@inproceedings{bb105747,
AUTHOR = "Cornia, M. and Baraldi, L. and Cucchiara, R.",
TITLE = "Show, Control and Tell: A Framework for Generating Controllable and
Grounded Captions",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "8299-8308",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102088"}
@inproceedings{bb105748,
AUTHOR = "Qin, Y. and Du, J.J. and Zhang, Y. and Lu, H.T.",
TITLE = "Look Back and Predict Forward in Image Captioning",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "8359-8367",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102089"}
@inproceedings{bb105749,
AUTHOR = "Zheng, Y. and Li, Y. and Wang, S.J.",
TITLE = "Intention Oriented Image Captions With Guiding Objects",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "8387-8396",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102090"}
@inproceedings{bb105750,
AUTHOR = "Huang, Y. and Li, C. and Li, T. and Wan, W. and Chen, J.",
TITLE = "Image Captioning with Attribute Refinement",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "1820-1824",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102091"}
@inproceedings{bb105751,
AUTHOR = "Lee, J. and Lee, Y. and Seong, S. and Kim, K. and Kim, S. and Kim, J.",
TITLE = "Capturing Long-Range Dependencies in Video Captioning",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "1880-1884",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102092"}
@inproceedings{bb105752,
AUTHOR = "Shi, J. and Li, Y. and Wang, S.",
TITLE = "Cascade Attention: Multiple Feature Based Learning for Image
Captioning",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "1970-1974",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102093"}
@inproceedings{bb105753,
AUTHOR = "Wang, Y. and Shen, Y. and Xiong, H. and Lin, W.",
TITLE = "Adaptive Hard Example Mining for Image Captioning",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "3342-3346",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102094"}
@inproceedings{bb105754,
AUTHOR = "Xiao, H. and Shi, J.",
TITLE = "A Novel Attribute Selection Mechanism for Video Captioning",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "619-623",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102095"}
@inproceedings{bb105755,
AUTHOR = "Lim, J.H. and Chan, C.S.",
TITLE = "Mask Captioning Network",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102096"}
@inproceedings{bb105756,
AUTHOR = "Wang, Q.Z. and Chan, A.B.",
TITLE = "Gated Hierarchical Attention for Image Captioning",
BOOKTITLE = ACCV18,
YEAR = "2018",
PAGES = "IV:21-37",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102097"}
@inproceedings{bb105757,
AUTHOR = "Wang, W. and Chen, Z.H. and Hu, H.F.",
TITLE = "Multivariate Attention Network for Image Captioning",
BOOKTITLE = ACCV18,
YEAR = "2018",
PAGES = "VI:587-602",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102098"}
@inproceedings{bb105758,
AUTHOR = "Ghanimifard, M. and Dobnik, S.",
TITLE = "Knowing When to Look for What and Where: Evaluating Generation of
Spatial Descriptions with Adaptive Attention",
BOOKTITLE = VL18,
YEAR = "2018",
PAGES = "IV:153-161",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102099"}
@inproceedings{bb105759,
AUTHOR = "Kim, B. and Lee, Y.H. and Jung, H. and Cho, C.",
TITLE = "Distinctive-Attribute Extraction for Image Captioning",
BOOKTITLE = VL18,
YEAR = "2018",
PAGES = "IV:133-144",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102100"}
@inproceedings{bb105760,
AUTHOR = "Tanti, M. and Gatt, A. and Muscat, A.",
TITLE = "Pre-gen Metrics: Predicting Caption Quality Metrics Without Generating
Captions",
BOOKTITLE = VL18,
YEAR = "2018",
PAGES = "IV:114-123",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102101"}
@inproceedings{bb105761,
AUTHOR = "Tanti, M. and Gatt, A. and Camilleri, K.P.",
TITLE = "Quantifying the Amount of Visual Information Used by Neural Caption
Generators",
BOOKTITLE = VL18,
YEAR = "2018",
PAGES = "IV:124-132",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102102"}
@inproceedings{bb105762,
AUTHOR = "Ren, L. and Qi, G. and Hua, K.",
TITLE = "Improving Diversity of Image Captioning Through Variational
Autoencoders and Adversarial Learning",
BOOKTITLE = WACV19,
YEAR = "2019",
PAGES = "263-272",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102103"}
@inproceedings{bb105763,
AUTHOR = "Zhou, Y. and Sun, Y. and Honavar, V.",
TITLE = "Improving Image Captioning by Leveraging Knowledge Graphs",
BOOKTITLE = WACV19,
YEAR = "2019",
PAGES = "283-293",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102104"}
@inproceedings{bb105764,
AUTHOR = "Rapson, C.J. and Seet, B. and Naeem, M.A. and Lee, J.E. and Al Sarayreh, M. and Klette, R.",
TITLE = "Reducing the Pain: A Novel Tool for Efficient Ground-Truth Labelling
in Images",
BOOKTITLE = IVCNZ18,
YEAR = "2018",
PAGES = "1-9",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102105"}
@inproceedings{bb105765,
AUTHOR = "Lu, J.S. and Yang, J.W. and Batra, D. and Parikh, D.",
TITLE = "Neural Baby Talk",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7219-7228",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102106"}
@inproceedings{bb105766,
AUTHOR = "Wu, B.Y. and Chen, W.D. and Sun, P. and Liu, W. and Ghanem, B. and Lyu, S.W.",
TITLE = "Tagging Like Humans: Diverse and Distinct Image Annotation",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7967-7975",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102107"}
@inproceedings{bb105767,
AUTHOR = "Wu, X.J. and Zhang, L. and Li, F.Z. and Wang, B.J.",
TITLE = "A Novel Model for Multi-label Image Annotation",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "1953-1958",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102108"}
@inproceedings{bb105768,
AUTHOR = "Jiu, M. and Sahbi, H. and Qi, L.",
TITLE = "Deep Context Networks for Image Annotation",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "2422-2427",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102109"}
@inproceedings{bb105769,
AUTHOR = "Khademi, M. and Schulte, O.",
TITLE = "Image Caption Generation with Hierarchical Contextual Visual Spatial
Attention",
BOOKTITLE = Cognitive18,
YEAR = "2018",
PAGES = "2024-20248",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102110"}
@inproceedings{bb105770,
AUTHOR = "Yan, S. and Wu, F. and Smith, J.S. and Lu, W. and Zhang, B.",
TITLE = "Image Captioning using Adversarial Networks and Reinforcement
Learning",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "248-253",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102111"}
@inproceedings{bb105771,
AUTHOR = "Wang, F. and Gong, X. and Huang, L.",
TITLE = "Time-Dependent Pre-attention Model for Image Captioning",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "3297-3302",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102112"}
@inproceedings{bb105772,
AUTHOR = "Luo, R. and Shakhnarovich, G. and Cohen, S. and Price, B.",
TITLE = "Discriminability Objective for Training Descriptive Captions",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "6964-6974",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102113"}
@inproceedings{bb105773,
AUTHOR = "Cui, Y. and Yang, G. and Veit, A. and Huang, X. and Belongie, S.",
TITLE = "Learning to Evaluate Image Captioning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "5804-5812",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102114"}
@inproceedings{bb105774,
AUTHOR = "Aneja, J. and Deshpande, A. and Schwing, A.G.",
TITLE = "Convolutional Image Captioning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "5561-5570",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102115"}
@inproceedings{bb105775,
AUTHOR = "Chen, F. and Ji, R. and Sun, X. and Wu, Y. and Su, J.",
TITLE = "GroupCap: Group-Based Image Captioning with Structured Relevance and
Diversity Constraints",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "1345-1353",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102116"}
@inproceedings{bb105776,
AUTHOR = "Chen, X. and Ma, L. and Jiang, W. and Yao, J. and Liu, W.",
TITLE = "Regularizing RNNs for Caption Generation by Reconstructing the Past
with the Present",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7995-8003",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102117"}
@inproceedings{bb105777,
AUTHOR = "Yao, T. and Pan, Y.W. and Li, Y. and Mei, T.",
TITLE = "Exploring Visual Relationship for Image Captioning",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XIV: 711-727",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102118"}
@inproceedings{bb105778,
AUTHOR = "Shah, S.A.A.",
TITLE = "NNEval: Neural Network Based Evaluation Metric for Image Captioning",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "VIII: 39-55",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102119"}
@inproceedings{bb105779,
AUTHOR = "Jiang, W.H. and Ma, L. and Jiang, Y.G. and Liu, W. and Zhang, T.",
TITLE = "Recurrent Fusion Network for Image Captioning",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "II: 510-526",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102120"}
@inproceedings{bb105780,
AUTHOR = "Chatterjee, M. and Schwing, A.G.",
TITLE = "Diverse and Coherent Paragraph Generation from Images",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "II: 747-763",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102121"}
@inproceedings{bb105781,
AUTHOR = "Chen, S. and Zhao, Q.",
TITLE = "Boosted Attention: Leveraging Human Attention for Image Captioning",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XI: 72-88",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102122"}
@inproceedings{bb105782,
AUTHOR = "Dai, B. and Ye, D. and Lin, D.",
TITLE = "Rethinking the Form of Latent States in Image Captioning",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "VI: 294-310",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102123"}
@inproceedings{bb105783,
AUTHOR = "Liu, X. and Li, H.S. and Shao, J. and Chen, D.P. and Wang, X.G.",
TITLE = "Show, Tell and Discriminate:
Image Captioning by Self-retrieval with Partially Labeled Data",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XV: 353-369",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102124"}
@inproceedings{bb105784,
AUTHOR = "Fang, F. and Wang, H. and Tang, P.",
TITLE = "Image Captioning with Word Level Attention",
BOOKTITLE = ICIP18,
YEAR = "2018",
PAGES = "1278-1282",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102125"}
@inproceedings{bb105785,
AUTHOR = "Zhu, Z. and Xue, Z. and Yuan, Z.",
TITLE = "Topic-Guided Attention for Image Captioning",
BOOKTITLE = ICIP18,
YEAR = "2018",
PAGES = "2615-2619",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102126"}
@inproceedings{bb105786,
AUTHOR = "Gomez Garay, A. and Raducanu, B. and Salas, J.",
TITLE = "Dense Captioning of Natural Scenes in Spanish",
BOOKTITLE = MCPR18,
YEAR = "2018",
PAGES = "145-154",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102127"}
@inproceedings{bb105787,
AUTHOR = "Yao, L. and Ballas, N. and Cho, K. and Smith, J. and Bengio, Y.",
TITLE = "Oracle Performance for Visual Captioning",
BOOKTITLE = BMVC16,
YEAR = "2016",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102128"}
@inproceedings{bb105788,
AUTHOR = "Khatchatoorian, A.G. and Jamzad, M.",
TITLE = "Post Rectifying Methods to Improve the Accuracy of Image Annotation",
BOOKTITLE = DICTA17,
YEAR = "2017",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102129"}
@inproceedings{bb105789,
AUTHOR = "Dong, H. and Zhang, J.Q. and McIlwraith, D. and Guo, Y.",
TITLE = "I2T2I: Learning text to image synthesis with textual data
augmentation",
BOOKTITLE = ICIP17,
YEAR = "2017",
PAGES = "2015-2019",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102130"}
@inproceedings{bb105790,
AUTHOR = "Pellegrin, L. and Escalante, H.J. and Montes y Gomez, M. and Villegas, M. and Gonzalez, F.A.",
TITLE = "A Flexible Framework for the Evaluation of Unsupervised Image
Annotation",
BOOKTITLE = CIARP17,
YEAR = "2017",
PAGES = "508-516",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102131"}
@inproceedings{bb105791,
AUTHOR = "Jia, Y.H. and Bai, L. and Wang, P. and Guo, J.L. and Xie, Y.X.",
TITLE = "Deep Convolutional Neural Network for Correlating Images and Sentences",
BOOKTITLE = MMMod18,
YEAR = "2018",
PAGES = "I:154-165",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102132"}
@inproceedings{bb105792,
AUTHOR = "Liu, J.Y. and Wang, L. and Yang, M.H.",
TITLE = "Referring Expression Generation and Comprehension via Attributes",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "4866-4874",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102133"}
@inproceedings{bb105793,
AUTHOR = "Dai, B. and Fidler, S. and Urtasun, R. and Lin, D.",
TITLE = "Towards Diverse and Natural Image Descriptions via a Conditional GAN",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "2989-2998",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102134"}
@inproceedings{bb105794,
AUTHOR = "Niu, Z.X. and Zhou, M. and Wang, L. and Gao, X. 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/match607ic1.html#TT102135"}
@inproceedings{bb105795,
AUTHOR = "Liang, X. and Hu, Z. and Zhang, H. and Gan, C. and Xing, E.P.",
TITLE = "Recurrent Topic-Transition GAN for Visual Paragraph Generation",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "3382-3391",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102136"}
@inproceedings{bb105796,
AUTHOR = "Shetty, R. and Rohrbach, M. and Hendricks, L.A. and Fritz, M. and Schiele, B.",
TITLE = "Speaking the Same Language:
Matching Machine to Human Captions by Adversarial Training",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "4155-4164",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102137"}
@inproceedings{bb105797,
AUTHOR = "Liu, S. and Zhu, Z. and Ye, N. and Guadarrama, S. and Murphy, K.",
TITLE = "Improved Image Captioning via Policy Gradient optimization of SPIDEr",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "873-881",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102138"}
@inproceedings{bb105798,
AUTHOR = "Gu, J.X. and Joty, S. and Cai, J.F. and Wang, G.",
TITLE = "Unpaired Image Captioning by Language Pivoting",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "I: 519-535",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102139"}
@inproceedings{bb105799,
AUTHOR = "Gu, J.X. and Wang, G. and Cai, J.F. and Chen, T.H.",
TITLE = "An Empirical Study of Language CNN for Image Captioning",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "1231-1240",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT102140"}
Last update:Oct 16, 2021 at 11:54:21