@inproceedings{bb110600,
        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#TT106891"}

@inproceedings{bb110601,
        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#TT106892"}

@inproceedings{bb110602,
        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#TT106893"}

@inproceedings{bb110603,
        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#TT106894"}

@inproceedings{bb110604,
        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#TT106895"}

@inproceedings{bb110605,
        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#TT106896"}

@inproceedings{bb110606,
        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#TT106897"}

@inproceedings{bb110607,
        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#TT106898"}

@inproceedings{bb110608,
        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#TT106899"}

@inproceedings{bb110609,
        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#TT106900"}

@inproceedings{bb110610,
        AUTHOR = "Xu, Y. and Wu, B.Y. and Shen, F.M. 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#TT106901"}

@inproceedings{bb110611,
        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#TT106902"}

@inproceedings{bb110612,
        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#TT106903"}

@inproceedings{bb110613,
        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#TT106904"}

@inproceedings{bb110614,
        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#TT106905"}

@inproceedings{bb110615,
        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#TT106906"}

@inproceedings{bb110616,
        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#TT106907"}

@inproceedings{bb110617,
        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#TT106908"}

@inproceedings{bb110618,
        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#TT106909"}

@inproceedings{bb110619,
        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#TT106910"}

@inproceedings{bb110620,
        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#TT106911"}

@inproceedings{bb110621,
        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#TT106912"}

@inproceedings{bb110622,
        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#TT106913"}

@inproceedings{bb110623,
        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#TT106914"}

@inproceedings{bb110624,
        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#TT106915"}

@inproceedings{bb110625,
        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#TT106916"}

@inproceedings{bb110626,
        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#TT106917"}

@inproceedings{bb110627,
        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#TT106918"}

@inproceedings{bb110628,
        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#TT106919"}

@inproceedings{bb110629,
        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#TT106920"}

@inproceedings{bb110630,
        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#TT106921"}

@inproceedings{bb110631,
        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#TT106922"}

@inproceedings{bb110632,
        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#TT106923"}

@inproceedings{bb110633,
        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#TT106924"}

@inproceedings{bb110634,
        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#TT106925"}

@inproceedings{bb110635,
        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#TT106926"}

@inproceedings{bb110636,
        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#TT106927"}

@inproceedings{bb110637,
        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#TT106928"}

@inproceedings{bb110638,
        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#TT106929"}

@inproceedings{bb110639,
        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#TT106930"}

@inproceedings{bb110640,
        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#TT106931"}

@inproceedings{bb110641,
        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#TT106932"}

@inproceedings{bb110642,
        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#TT106933"}

@inproceedings{bb110643,
        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#TT106934"}

@inproceedings{bb110644,
        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#TT106935"}

@inproceedings{bb110645,
        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#TT106936"}

@inproceedings{bb110646,
        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#TT106937"}

@inproceedings{bb110647,
        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#TT106938"}

@inproceedings{bb110648,
        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#TT106939"}

@inproceedings{bb110649,
        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#TT106940"}

@inproceedings{bb110650,
        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#TT106941"}

@inproceedings{bb110651,
        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#TT106942"}

@inproceedings{bb110652,
        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#TT106943"}

@inproceedings{bb110653,
        AUTHOR = "Liu, X.H. 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#TT106944"}

@inproceedings{bb110654,
        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#TT106945"}

@inproceedings{bb110655,
        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#TT106946"}

@inproceedings{bb110656,
        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#TT106947"}

@inproceedings{bb110657,
        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#TT106948"}

@inproceedings{bb110658,
        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#TT106949"}

@inproceedings{bb110659,
        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#TT106950"}

@inproceedings{bb110660,
        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#TT106951"}

@inproceedings{bb110661,
        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#TT106952"}

@inproceedings{bb110662,
        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#TT106953"}

@inproceedings{bb110663,
        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#TT106954"}

@inproceedings{bb110664,
        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#TT106955"}

@inproceedings{bb110665,
        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#TT106956"}

@inproceedings{bb110666,
        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#TT106957"}

@inproceedings{bb110667,
        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#TT106958"}

@inproceedings{bb110668,
        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#TT106959"}

@inproceedings{bb110669,
        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#TT106960"}

@inproceedings{bb110670,
        AUTHOR = "Pedersoli, M. and Lucas, T. and Schmid, C. and Verbeek, J.",
        TITLE = "Areas of Attention for Image Captioning",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1251-1259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106961"}

@inproceedings{bb110671,
        AUTHOR = "Zhang, Z. and Wu, J.J. and Li, Q. and Huang, Z. and Traer, J. and McDermott, J.H. and Tenenbaum, J.B. and Freeman, W.T.",
        TITLE = "Generative Modeling of Audible Shapes for Object Perception",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1260-1269",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106962"}

@inproceedings{bb110672,
        AUTHOR = "Liu, Z.J. and Freeman, W.T. and Tenenbaum, J.B. and Wu, J.J.",
        TITLE = "Physical Primitive Decomposition",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XII: 3-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106963"}

@inproceedings{bb110673,
        AUTHOR = "Wu, J.J. and Lim, J. and Zhang, H.Y. and Tenenbaum, J.B. and Freeman, W.T.",
        TITLE = "Physics 101: Learning Physical Object Properties from Unlabeled Videos",
        BOOKTITLE = BMVC16,
        YEAR = "2016",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106964"}

@inproceedings{bb110674,
        AUTHOR = "Tavakoliy, H.R. and Shetty, R. and Borji, A. and Laaksonen, J.",
        TITLE = "Paying Attention to Descriptions Generated by Image Captioning Models",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2506-2515",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106965"}

@inproceedings{bb110675,
        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/match607ic1.html#TT106966"}

@inproceedings{bb110676,
        AUTHOR = "Tripathi, A. and Gupta, A. and Chaudhary, S. and Lall, B.",
        TITLE = "Image Annotation Using Latent Components and Transmedia Association",
        BOOKTITLE = PReMI17,
        YEAR = "2017",
        PAGES = "493-500",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106967"}

@inproceedings{bb110677,
        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/match607ic1.html#TT106968"}

@inproceedings{bb110678,
        AUTHOR = "Wu, B.Y. and Jia, F. and Liu, W. and Ghanem, B.",
        TITLE = "Diverse Image Annotation",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6194-6202",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106969"}

@inproceedings{bb110679,
        AUTHOR = "Krause, J. and Johnson, J. and Krishna, R. and Fei Fei, L.",
        TITLE = "A Hierarchical Approach for Generating Descriptive Image Paragraphs",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3337-3345",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106970"}

@inproceedings{bb110680,
        AUTHOR = "Vedantam, R. and Bengio, S. and Murphy, K. and Parikh, D. and Chechik, G.",
        TITLE = "Context-Aware Captions from Context-Agnostic Supervision",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1070-1079",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106971"}

@inproceedings{bb110681,
        AUTHOR = "Gan, Z. and Gan, C. and He, X. and Pu, Y. and Tran, K. and Gao, J. and Carin, L. and Deng, L.",
        TITLE = "Semantic Compositional Networks for Visual Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1141-1150",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106972"}

@inproceedings{bb110682,
        AUTHOR = "Ren, Z. and Wang, X. and Zhang, N. and Lv, X. and Li, L.J.",
        TITLE = "Deep Reinforcement Learning-Based Image Captioning with Embedding
Reward",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1151-1159",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106973"}

@inproceedings{bb110683,
        AUTHOR = "Rennie, S.J. and Marcheret, E. and Mroueh, Y. and Ross, J. and Goel, V.",
        TITLE = "Self-Critical Sequence Training for Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1179-1195",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106974"}

@inproceedings{bb110684,
        AUTHOR = "Yang, L. and Tang, K. and Yang, J. and Li, L.J.",
        TITLE = "Dense Captioning with Joint Inference and Visual Context",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1978-1987",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106975"}

@inproceedings{bb110685,
        AUTHOR = "Lu, J. and Xiong, C. and Parikh, D. and Socher, R.",
        TITLE = "Knowing When to Look: Adaptive Attention via a Visual Sentinel for
Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3242-3250",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106976"}

@inproceedings{bb110686,
        AUTHOR = "Yao, T. and Pan, Y. and Li, Y. and Mei, T.",
        TITLE = "Incorporating Copying Mechanism in Image Captioning for Learning
Novel Objects",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "5263-5271",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106977"}

@inproceedings{bb110687,
        AUTHOR = "Chen, L. and Zhang, H. and Xiao, J. and Nie, L. and Shao, J. and Liu, W. and Chua, T.S.",
        TITLE = "SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks
for Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6298-6306",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106978"}

@inproceedings{bb110688,
        AUTHOR = "Sun, Q. and Lee, S. and Batra, D.",
        TITLE = "Bidirectional Beam Search: Forward-Backward Inference in Neural
Sequence Models for Fill-in-the-Blank Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "7215-7223",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106979"}

@inproceedings{bb110689,
        AUTHOR = "Wang, Y. and Lin, Z. and Shen, X. and Cohen, S. and Cottrell, G.W.",
        TITLE = "Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "7378-7387",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106980"}

@inproceedings{bb110690,
        AUTHOR = "Zanfir, M. and Marinoiu, E. and Sminchisescu, C.",
        TITLE = "Spatio-Temporal Attention Models for Grounded Video Captioning",
        BOOKTITLE = ACCV16,
        YEAR = "2016",
        PAGES = "IV: 104-119",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106981"}

@inproceedings{bb110691,
        AUTHOR = "Chen, T.H. and Zeng, K.H. and Hsu, W.T. and Sun, M.",
        TITLE = "Video Captioning via Sentence Augmentation and Spatio-Temporal
Attention",
        BOOKTITLE = Assist16,
        YEAR = "2016",
        PAGES = "I: 269-286",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106982"}

@inproceedings{bb110692,
        AUTHOR = "Tan, Y.H. and Chan, C.S.",
        TITLE = "phi-LSTM: A Phrase-Based Hierarchical LSTM Model for Image Captioning",
        BOOKTITLE = ACCV16,
        YEAR = "2016",
        PAGES = "V: 101-117",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106983"}

@inproceedings{bb110693,
        AUTHOR = "Weiland, L. and Hulpus, I. and Ponzetto, S.P. and Dietz, L.",
        TITLE = "Using Object Detection, NLP, and Knowledge Bases to Understand the
Message of Images",
        BOOKTITLE = MMMod17,
        YEAR = "2017",
        PAGES = "II: 405-418",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106984"}

@inproceedings{bb110694,
        AUTHOR = "Liu, Y. and Guo, Y.M. and Lew, M.S.",
        TITLE = "What Convnets Make for Image Captioning?",
        BOOKTITLE = MMMod17,
        YEAR = "2017",
        PAGES = "I: 416-428",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106985"}

@inproceedings{bb110695,
        AUTHOR = "Tran, K. and He, X. and Zhang, L. and Sun, J.",
        TITLE = "Rich Image Captioning in the Wild",
        BOOKTITLE = DeepLearn-C16,
        YEAR = "2016",
        PAGES = "434-441",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106986"}

@inproceedings{bb110696,
        AUTHOR = "Wang, Y.L. and Wang, S.H. and Tang, J.L. and Liu, H. and Li, B.X.",
        TITLE = "PPP: Joint Pointwise and Pairwise Image Label Prediction",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "6005-6013",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106987"}

@inproceedings{bb110697,
        AUTHOR = "Sadhu, A. and Gupta, T. and Yatskar, M. and Nevatia, R. and Kembhavi, A.",
        TITLE = "Visual Semantic Role Labeling for Video Understanding",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "5585-5596",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106988"}

@inproceedings{bb110698,
        AUTHOR = "Yatskar, M. and Ordonez, V. and Zettlemoyer, L. and Farhadi, A.",
        TITLE = "Commonly Uncommon: Semantic Sparsity in Situation Recognition",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6335-6344",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106989"}

@inproceedings{bb110699,
        AUTHOR = "Yatskar, M. and Zettlemoyer, L. and Farhadi, A.",
        TITLE = "Situation Recognition: Visual Semantic Role Labeling for Image
Understanding",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "5534-5542",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT106990"}

Last update:Sep 1, 2022 at 11:00:56