@inproceedings{bb133300,
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#TT129337"}
@inproceedings{bb133301,
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#TT129338"}
@inproceedings{bb133302,
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#TT129339"}
@inproceedings{bb133303,
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#TT129340"}
@inproceedings{bb133304,
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#TT129341"}
@inproceedings{bb133305,
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#TT129342"}
@inproceedings{bb133306,
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#TT129343"}
@inproceedings{bb133307,
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#TT129344"}
@inproceedings{bb133308,
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#TT129345"}
@inproceedings{bb133309,
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#TT129346"}
@inproceedings{bb133310,
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#TT129347"}
@inproceedings{bb133311,
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#TT129348"}
@inproceedings{bb133312,
AUTHOR = "Deshpande, A. and Aneja, J. and Wang, L.W. and Schwing, A.G. and Forsyth, D.A.",
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#TT129349"}
@inproceedings{bb133313,
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#TT129350"}
@inproceedings{bb133314,
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#TT129351"}
@inproceedings{bb133315,
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#TT129352"}
@inproceedings{bb133316,
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#TT129353"}
@inproceedings{bb133317,
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#TT129354"}
@inproceedings{bb133318,
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#TT129355"}
@inproceedings{bb133319,
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#TT129356"}
@inproceedings{bb133320,
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#TT129357"}
@inproceedings{bb133321,
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#TT129358"}
@inproceedings{bb133322,
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#TT129359"}
@inproceedings{bb133323,
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#TT129360"}
@inproceedings{bb133324,
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#TT129361"}
@inproceedings{bb133325,
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#TT129362"}
@inproceedings{bb133326,
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#TT129363"}
@inproceedings{bb133327,
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#TT129364"}
@inproceedings{bb133328,
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#TT129365"}
@inproceedings{bb133329,
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#TT129366"}
@inproceedings{bb133330,
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#TT129367"}
@inproceedings{bb133331,
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#TT129368"}
@inproceedings{bb133332,
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#TT129369"}
@inproceedings{bb133333,
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#TT129370"}
@inproceedings{bb133334,
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#TT129371"}
@inproceedings{bb133335,
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#TT129372"}
@inproceedings{bb133336,
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#TT129373"}
@inproceedings{bb133337,
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#TT129374"}
@inproceedings{bb133338,
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#TT129375"}
@inproceedings{bb133339,
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#TT129376"}
@inproceedings{bb133340,
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#TT129377"}
@inproceedings{bb133341,
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#TT129378"}
@inproceedings{bb133342,
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#TT129379"}
@inproceedings{bb133343,
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#TT129380"}
@inproceedings{bb133344,
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#TT129381"}
@inproceedings{bb133345,
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#TT129382"}
@inproceedings{bb133346,
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#TT129383"}
@inproceedings{bb133347,
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#TT129384"}
@inproceedings{bb133348,
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#TT129385"}
@inproceedings{bb133349,
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#TT129386"}
@inproceedings{bb133350,
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#TT129387"}
@inproceedings{bb133351,
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#TT129388"}
@inproceedings{bb133352,
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#TT129389"}
@inproceedings{bb133353,
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#TT129390"}
@inproceedings{bb133354,
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#TT129391"}
@inproceedings{bb133355,
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#TT129392"}
@inproceedings{bb133356,
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#TT129393"}
@inproceedings{bb133357,
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#TT129394"}
@inproceedings{bb133358,
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#TT129395"}
@inproceedings{bb133359,
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#TT129396"}
@inproceedings{bb133360,
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#TT129397"}
@inproceedings{bb133361,
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#TT129398"}
@inproceedings{bb133362,
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#TT129399"}
@inproceedings{bb133363,
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#TT129400"}
@inproceedings{bb133364,
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#TT129401"}
@inproceedings{bb133365,
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#TT129402"}
@inproceedings{bb133366,
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#TT129403"}
@inproceedings{bb133367,
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#TT129404"}
@inproceedings{bb133368,
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#TT129405"}
@inproceedings{bb133369,
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#TT129406"}
@inproceedings{bb133370,
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#TT129407"}
@inproceedings{bb133371,
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#TT129408"}
@inproceedings{bb133372,
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#TT129409"}
@inproceedings{bb133373,
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#TT129410"}
@inproceedings{bb133374,
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#TT129411"}
@inproceedings{bb133375,
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#TT129412"}
@inproceedings{bb133376,
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#TT129413"}
@inproceedings{bb133377,
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#TT129414"}
@inproceedings{bb133378,
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#TT129415"}
@inproceedings{bb133379,
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#TT129416"}
@inproceedings{bb133380,
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#TT129417"}
@inproceedings{bb133381,
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#TT129418"}
@inproceedings{bb133382,
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#TT129419"}
@inproceedings{bb133383,
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#TT129420"}
@inproceedings{bb133384,
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#TT129421"}
@inproceedings{bb133385,
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#TT129422"}
@inproceedings{bb133386,
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#TT129423"}
@inproceedings{bb133387,
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#TT129424"}
@inproceedings{bb133388,
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#TT129425"}
@inproceedings{bb133389,
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#TT129426"}
@article{bb133390,
AUTHOR = "Li, L.H. and Tang, S. and Zhang, Y.D. and Deng, L.X. and Tian, Q.",
TITLE = "GLA: Global-Local Attention for Image Description",
JOURNAL = MultMed,
VOLUME = "20",
YEAR = "2018",
NUMBER = "3",
MONTH = "March",
PAGES = "726-737",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129427"}
@article{bb133391,
AUTHOR = "Wu, C.L. and Wei, Y.W. and Chu, X.L. and Su, F. and Wang, L.Q.",
TITLE = "Modeling visual and word-conditional semantic attention for image
captioning",
JOURNAL = SP:IC,
VOLUME = "67",
YEAR = "2018",
PAGES = "100-107",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129428"}
@article{bb133392,
AUTHOR = "Xu, N. and Liu, A.A. and Liu, J. and Nie, W.Z. and Su, Y.T.",
TITLE = "Scene graph captioner:
Image captioning based on structural visual representation",
JOURNAL = JVCIR,
VOLUME = "58",
YEAR = "2019",
PAGES = "477-485",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129429"}
@article{bb133393,
AUTHOR = "Ding, S.T. and Qu, S. and Xi, Y.L. and Sangaiah, A.K. and Wan, S.H.",
TITLE = "Image caption generation with high-level image features",
JOURNAL = PRL,
VOLUME = "123",
YEAR = "2019",
PAGES = "89-95",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129430"}
@article{bb133394,
AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
TITLE = "High-Quality Image Captioning With Fine-Grained and Semantic-Guided
Visual Attention",
JOURNAL = MultMed,
VOLUME = "21",
YEAR = "2019",
NUMBER = "7",
MONTH = "July",
PAGES = "1681-1693",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129431"}
@inproceedings{bb133395,
AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
TITLE = "Fine-Grained and Semantic-Guided Visual Attention for Image
Captioning",
BOOKTITLE = WACV18,
YEAR = "2018",
PAGES = "1709-1717",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129432"}
@article{bb133396,
AUTHOR = "Tan, J.H. and Chan, C.S. and Chuah, J.H.",
TITLE = "COMIC: Toward A Compact Image Captioning Model With Attention",
JOURNAL = MultMed,
VOLUME = "21",
YEAR = "2019",
NUMBER = "10",
MONTH = "October",
PAGES = "2686-2696",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129433"}
@article{bb133397,
AUTHOR = "Yang, L. and Hu, H.F.",
TITLE = "Visual Skeleton and Reparative Attention for Part-of-Speech image
captioning system",
JOURNAL = CVIU,
VOLUME = "189",
YEAR = "2019",
PAGES = "102819",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129434"}
@article{bb133398,
AUTHOR = "Wang, J.B. and Wang, W. and Wang, L. and Wang, Z.Y. and Feng, D.D. and Tan, T.N.",
TITLE = "Learning Visual Relationship and Context-Aware Attention for Image
Captioning",
JOURNAL = PR,
VOLUME = "98",
YEAR = "2020",
PAGES = "107075",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129435"}
@article{bb133399,
AUTHOR = "Wei, H.Y. and Li, Z.X. and Zhang, C.L. and Ma, H.F.",
TITLE = "The synergy of double attention: Combine sentence-level and
word-level attention for image captioning",
JOURNAL = CVIU,
VOLUME = "201",
YEAR = "2020",
PAGES = "103068",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607attic3.html#TT129436"}
Last update:Nov 10, 2025 at 14:27:42