@inproceedings{bb121700,
        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#TT117814"}

@inproceedings{bb121701,
        AUTHOR = "Gao, J.L. and Wang, S.Q. 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#TT117815"}

@inproceedings{bb121702,
        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#TT117816"}

@inproceedings{bb121703,
        AUTHOR = "Qin, Y. and Du, J.J. and Zhang, Y.H. 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#TT117817"}

@inproceedings{bb121704,
        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#TT117818"}

@inproceedings{bb121705,
        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#TT117819"}

@inproceedings{bb121706,
        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#TT117820"}

@inproceedings{bb121707,
        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#TT117821"}

@inproceedings{bb121708,
        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#TT117822"}

@inproceedings{bb121709,
        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#TT117823"}

@inproceedings{bb121710,
        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#TT117824"}

@inproceedings{bb121711,
        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#TT117825"}

@inproceedings{bb121712,
        AUTHOR = "Wang, W.X. 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#TT117826"}

@inproceedings{bb121713,
        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#TT117827"}

@inproceedings{bb121714,
        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#TT117828"}

@inproceedings{bb121715,
        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#TT117829"}

@inproceedings{bb121716,
        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#TT117830"}

@inproceedings{bb121717,
        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#TT117831"}

@inproceedings{bb121718,
        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#TT117832"}

@inproceedings{bb121719,
        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#TT117833"}

@inproceedings{bb121720,
        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#TT117834"}

@inproceedings{bb121721,
        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#TT117835"}

@inproceedings{bb121722,
        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#TT117836"}

@inproceedings{bb121723,
        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#TT117837"}

@inproceedings{bb121724,
        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#TT117838"}

@inproceedings{bb121725,
        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#TT117839"}

@inproceedings{bb121726,
        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#TT117840"}

@inproceedings{bb121727,
        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#TT117841"}

@inproceedings{bb121728,
        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#TT117842"}

@inproceedings{bb121729,
        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#TT117843"}

@inproceedings{bb121730,
        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#TT117844"}

@inproceedings{bb121731,
        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#TT117845"}

@inproceedings{bb121732,
        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#TT117846"}

@inproceedings{bb121733,
        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#TT117847"}

@inproceedings{bb121734,
        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#TT117848"}

@inproceedings{bb121735,
        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#TT117849"}

@inproceedings{bb121736,
        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#TT117850"}

@inproceedings{bb121737,
        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#TT117851"}

@inproceedings{bb121738,
        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#TT117852"}

@inproceedings{bb121739,
        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#TT117853"}

@inproceedings{bb121740,
        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#TT117854"}

@inproceedings{bb121741,
        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#TT117855"}

@inproceedings{bb121742,
        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#TT117856"}

@inproceedings{bb121743,
        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#TT117857"}

@inproceedings{bb121744,
        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#TT117858"}

@inproceedings{bb121745,
        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#TT117859"}

@inproceedings{bb121746,
        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#TT117860"}

@inproceedings{bb121747,
        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#TT117861"}

@inproceedings{bb121748,
        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#TT117862"}

@inproceedings{bb121749,
        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#TT117863"}

@inproceedings{bb121750,
        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#TT117864"}

@inproceedings{bb121751,
        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#TT117865"}

@inproceedings{bb121752,
        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#TT117866"}

@inproceedings{bb121753,
        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#TT117867"}

@inproceedings{bb121754,
        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#TT117868"}

@inproceedings{bb121755,
        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#TT117869"}

@inproceedings{bb121756,
        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#TT117870"}

@inproceedings{bb121757,
        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#TT117871"}

@inproceedings{bb121758,
        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#TT117872"}

@inproceedings{bb121759,
        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#TT117873"}

@inproceedings{bb121760,
        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#TT117874"}

@inproceedings{bb121761,
        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#TT117875"}

@inproceedings{bb121762,
        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#TT117876"}

@inproceedings{bb121763,
        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#TT117877"}

@inproceedings{bb121764,
        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#TT117878"}

@inproceedings{bb121765,
        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#TT117879"}

@inproceedings{bb121766,
        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#TT117880"}

@inproceedings{bb121767,
        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#TT117881"}

@inproceedings{bb121768,
        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#TT117882"}

@inproceedings{bb121769,
        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#TT117883"}

@inproceedings{bb121770,
        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#TT117884"}

@inproceedings{bb121771,
        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#TT117885"}

@inproceedings{bb121772,
        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#TT117886"}

@inproceedings{bb121773,
        AUTHOR = "Kottur, S. and Vedantam, R. and Moura, J.M.F. and Parikh, D.",
        TITLE = "VisualWord2Vec (Vis-W2V):
Learning Visually Grounded Word Embeddings Using Abstract Scenes",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4985-4994",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117887"}

@inproceedings{bb121774,
        AUTHOR = "Zhu, Y. and Groth, O. and Bernstein, M. and Fei Fei, L.",
        TITLE = "Visual7W: Grounded Question Answering in Images",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4995-5004",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117888"}

@inproceedings{bb121775,
        AUTHOR = "Zhang, P. and Goyal, Y. and Summers Stay, D. and Batra, D. and Parikh, D.",
        TITLE = "Yin and Yang: Balancing and Answering Binary Visual Questions",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "5014-5022",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117889"}

@inproceedings{bb121776,
        AUTHOR = "Park, D.H. and Darrell, T.J. and Rohrbach, A.",
        TITLE = "Robust Change Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4623-4632",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117890"}

@inproceedings{bb121777,
        AUTHOR = "Venugopalan, S. and Hendricks, L.A. and Rohrbach, M. and Mooney, R. and Darrell, T.J. and Saenko, K.",
        TITLE = "Captioning Images with Diverse Objects",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1170-1178",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117891"}

@inproceedings{bb121778,
        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#TT117892"}

@inproceedings{bb121779,
        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#TT117893"}

@inproceedings{bb121780,
        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#TT117894"}

@inproceedings{bb121781,
        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#TT117895"}

@inproceedings{bb121782,
        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#TT117896"}

@inproceedings{bb121783,
        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#TT117897"}

@inproceedings{bb121784,
        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#TT117898"}

@inproceedings{bb121785,
        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#TT117899"}

@inproceedings{bb121786,
        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#TT117900"}

@inproceedings{bb121787,
        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#TT117901"}

@inproceedings{bb121788,
        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#TT117902"}

@article{bb121789,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "Dense Sampling Low-Level Statistics of Local Features",
        JOURNAL = IEICE,
        VOLUME = "E93-D",
        YEAR = "2010",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1727-1736",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117903"}

@inproceedings{bb121790,
        AUTHOR = "Kuniyoshi, Y. and Harada, T. and Nakayama, H.",
        TITLE = "Dense Sampling Low-Level Statistics of Local Features",
        BOOKTITLE = CIVR09,
        YEAR = "2009",
        PAGES = "Article No 17",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117903"}

@inproceedings{bb121791,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "Global Gaussian approach for scene categorization using information
geometry",
        BOOKTITLE = CVPR10,
        YEAR = "2010",
        PAGES = "2336-2343",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117904"}

@inproceedings{bb121792,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "AI Goggles: Real-time Description and Retrieval in the Real World with
Online Learning",
        BOOKTITLE = CRV09,
        YEAR = "2009",
        PAGES = "184-191",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117905"}

@inproceedings{bb121793,
        AUTHOR = "Ushiku, Y. and Yamaguchi, M. and Mukuta, Y. and Harada, T.",
        TITLE = "Common Subspace for Model and Similarity:
Phrase Learning for Caption Generation from Images",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "2668-2676",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117906"}

@inproceedings{bb121794,
        AUTHOR = "Harada, T. and Nakayama, H. and Kuniyoshi, Y.",
        TITLE = "Improving Local Descriptors by Embedding Global and Local Spatial
Information",
        BOOKTITLE = ECCV10,
        YEAR = "2010",
        PAGES = "IV: 736-749",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117907"}

@inproceedings{bb121795,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "Evaluation of dimensionality reduction methods for image
auto-annotation",
        BOOKTITLE = BMVC10,
        YEAR = "2010",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117908"}

@inproceedings{bb121796,
        AUTHOR = "Jin, J. and Nakayama, H.",
        TITLE = "Annotation order matters:
Recurrent Image Annotator for arbitrary length image tagging",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "2452-2457",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117909"}

@article{bb121797,
        AUTHOR = "Tariq, A. and Foroosh, H.",
        TITLE = "A Context-Driven Extractive Framework for Generating Realistic Image
Descriptions",
        JOURNAL = IP,
        VOLUME = "26",
        YEAR = "2017",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "619-632",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117910"}

@article{bb121798,
        AUTHOR = "Cheng, Q. and Zhang, Q. and Fu, P. and Tu, C.H. and Li, S.",
        TITLE = "A survey and analysis on automatic image annotation",
        JOURNAL = PR,
        VOLUME = "79",
        YEAR = "2018",
        PAGES = "242-259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117911"}

@article{bb121799,
        AUTHOR = "Ben Rejeb, I. and Ouni, S. and Barhoumi, W. and Zagrouba, E.",
        TITLE = "Fuzzy VA-Files for multi-label image annotation based on visual content
of regions",
        JOURNAL = SIViP,
        VOLUME = "12",
        YEAR = "2018",
        NUMBER = "5",
        MONTH = "July",
        PAGES = "877-884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ian2.html#TT117912"}