@inproceedings{bb121600, AUTHOR = "Sabir, A.", TITLE = "Word to Sentence Visual Semantic Similarity for Caption Generation: Lessons Learned", BOOKTITLE = MVA23, YEAR = "2023", PAGES = "1-5", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117714"} @inproceedings{bb121601, AUTHOR = "Verma, A. and Agarwal, S. and Arya, K.V. and Petrlik, I. and Esparza, R. and Rodriguez, C.", TITLE = "Image Captioning with Reinforcement Learning", BOOKTITLE = ICCVMI23, YEAR = "2023", PAGES = "1-7", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117715"} @inproceedings{bb121602, AUTHOR = "Wei, Y.C. and Li, L. and Geng, S.L.", TITLE = "Remote Sensing Image Captioning Using Hire-MLP", BOOKTITLE = CVIDL23, YEAR = "2023", PAGES = "109-112", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117716"} @inproceedings{bb121603, AUTHOR = "Fan, J. and Liang, Y. and Liu, L. and Huang, S. and Zhang, L.", TITLE = "RCA-NOC: Relative Contrastive Alignment for Novel Object Captioning", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "15464-15474", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117717"} @inproceedings{bb121604, AUTHOR = "Li, R. and Sun, S.Y. and Elhoseiny, M. and Torr, P.", TITLE = "OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "20236-20246", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117718"} @inproceedings{bb121605, AUTHOR = "Hu, A. and Chen, S.Z. and Zhang, L. and Jin, Q.", TITLE = "Explore and Tell: Embodied Visual Captioning in 3D Environments", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "2482-2491", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117719"} @inproceedings{bb121606, AUTHOR = "Kang, W. and Mun, J. and Lee, S.J. and Roh, B.", TITLE = "Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "2930-2940", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117720"} @inproceedings{bb121607, AUTHOR = "Barraco, M. and Sarto, S. and Cornia, M. and Baraldi, L. and Cucchiara, R.", TITLE = "With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "3009-3019", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117721"} @inproceedings{bb121608, AUTHOR = "Fei, J.J. and Wang, T. and Zhang, J. and He, Z.Y. and Wang, C.J. and Zheng, F.", TITLE = "Transferable Decoding with Visual Entities for Zero-Shot Image Captioning", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "3113-3123", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117722"} @inproceedings{bb121609, AUTHOR = "Kornblith, S. and Li, L. and Wang, Z. and Nguyen, T.", TITLE = "Guiding image captioning models toward more specific captions", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "15213-15223", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117723"} @inproceedings{bb121610, AUTHOR = "Kim, Y. and Kim, J. and Lee, B.K. and Shin, S. and Ro, Y.M.", TITLE = "Mitigating Dataset Bias in Image Captioning Through Clip Confounder-Free Captioning Network", BOOKTITLE = ICIP23, YEAR = "2023", PAGES = "1720-1724", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117724"} @inproceedings{bb121611, AUTHOR = "Dessi, R. and Bevilacqua, M. and Gualdoni, E. and Rakotonirina, N.C. and Franzon, F. and Baroni, M.", TITLE = "Cross-Domain Image Captioning with Discriminative Finetuning", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "6935-6944", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117725"} @inproceedings{bb121612, AUTHOR = "Vo, D.M. and Luong, Q.A. and Sugimoto, A. and Nakayama, H.", TITLE = "A-CAP: Anticipation Captioning with Commonsense Knowledge", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "10824-10833", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117726"} @inproceedings{bb121613, AUTHOR = "Kuo, C.W. and Kira, Z.", TITLE = "HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "11039-11049", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117727"} @inproceedings{bb121614, AUTHOR = "Ramos, R. and Martins, B. and Elliott, D. and Kementchedjhieva, Y.", TITLE = "Smallcap: Lightweight Image Captioning Prompted with Retrieval Augmentation", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "2840-2849", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117728"} @inproceedings{bb121615, AUTHOR = "Hirota, Y. and Nakashima, Y. and Garcia, N.", TITLE = "Model-Agnostic Gender Debiased Image Captioning", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "15191-15200", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117729"} @inproceedings{bb121616, AUTHOR = "Chen, S.J. and Zhu, H.Y. and Chen, X. and Lei, Y.J. and Yu, G. and Chen, T.", TITLE = "End-to-End 3D Dense Captioning with Vote2Cap-DETR", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "11124-11133", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117730"} @inproceedings{bb121617, AUTHOR = "Tran, H.T.T. and Okatani, T.", TITLE = "Bright as the Sun: In-depth Analysis of Imagination-driven Image Captioning", BOOKTITLE = ACCV22, YEAR = "2022", PAGES = "IV:675-691", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117731"} @inproceedings{bb121618, AUTHOR = "Phueaksri, I. and Kastner, M.A. and Kawanishi, Y. and Komamizu, T. and Ide, I.", TITLE = "Towards Captioning an Image Collection from a Combined Scene Graph Representation Approach", BOOKTITLE = MMMod23, YEAR = "2023", PAGES = "I: 178-190", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117732"} @inproceedings{bb121619, AUTHOR = "Zhang, Y. and Wang, J. and Wu, H. and Xu, W.J.", TITLE = "Distinctive Image Captioning via Clip Guided Group Optimization", BOOKTITLE = CMHRI22, YEAR = "2022", PAGES = "223-238", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117733"} @inproceedings{bb121620, AUTHOR = "Qiu, Y. and Yamamoto, S. and Yamada, R. and Suzuki, R. and Kataoka, H. and Iwata, K. and Satoh, Y.", TITLE = "3D Change Localization and Captioning from Dynamic Scans of Indoor Scenes", BOOKTITLE = WACV23, YEAR = "2023", PAGES = "1176-1185", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117734"} @inproceedings{bb121621, AUTHOR = "Honda, U. and Watanabe, T. and Matsumoto, Y.", TITLE = "Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning", BOOKTITLE = WACV23, YEAR = "2023", PAGES = "1124-1134", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117735"} @inproceedings{bb121622, AUTHOR = "Sui, J.H. and Yu, H.M. and Liang, X.Y. and Ping, P.", TITLE = "Image Caption Method Based on Graph Attention Network with Global Context", BOOKTITLE = ICIVC22, YEAR = "2022", PAGES = "480-487", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117736"} @inproceedings{bb121623, AUTHOR = "Barraco, M. and Stefanini, M. and Cornia, M. and Cascianelli, S. and Baraldi, L. and Cucchiara, R.", TITLE = "CaMEL: Mean Teacher Learning for Image Captioning", BOOKTITLE = "ICPR22", YEAR = "2022", PAGES = "4087-4094", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117737"} @inproceedings{bb121624, AUTHOR = "Arguello, P. and Lopez, J. and Hinojosa, C. and Arguello, H.", TITLE = "Optics Lens Design for Privacy-Preserving Scene Captioning", BOOKTITLE = ICIP22, YEAR = "2022", PAGES = "3551-3555", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117738"} @inproceedings{bb121625, AUTHOR = "Meng, Z. and Yang, D. and Cao, X.F. and Shah, A. and Lim, S.N.", TITLE = "Object-Centric Unsupervised Image Captioning", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXVI:219-235", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117739"} @inproceedings{bb121626, AUTHOR = "Wang, Z. and Chen, L. and Ma, W.B. and Han, G.X. and Niu, Y. and Shao, J. and Xiao, J.", TITLE = "Explicit Image Caption Editing", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXVI:113-129", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117740"} @inproceedings{bb121627, AUTHOR = "Jiao, Y. and Chen, S.X. and Jie, Z. and Chen, J.J. and Ma, L. and Jiang, Y.G.", TITLE = "MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXV:528-545", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117741"} @inproceedings{bb121628, AUTHOR = "Nagrani, A. and Seo, P.H. and Seybold, B. and Hauth, A. and Manen, S. and Sun, C. and Schmid, C.", TITLE = "Learning Audio-Video Modalities from Image Captions", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XIV:407-426", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117742"} @inproceedings{bb121629, AUTHOR = "Tewel, Y. and Shalev, Y. and Schwartz, I. and Wolf, L.B.", TITLE = "ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "17897-17907", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117743"} @inproceedings{bb121630, AUTHOR = "Truong, P. and Danelljan, M. and Yu, F. and Van Gool, L.J.", TITLE = "Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "8698-8708", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117744"} @inproceedings{bb121631, AUTHOR = "Chan, D.M. and Myers, A. and Vijayanarasimhan, S. and Ross, D.A. and Seybold, B. and Canny, J.F.", TITLE = "What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics", BOOKTITLE = VDU22, YEAR = "2022", PAGES = "4739-4748", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117745"} @inproceedings{bb121632, AUTHOR = "Popattia, M. and Rafi, M. and Qureshi, R. and Nawaz, S.", TITLE = "Guiding Attention using Partial-Order Relationships for Image Captioning", BOOKTITLE = MULA22, YEAR = "2022", PAGES = "4670-4679", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117746"} @inproceedings{bb121633, AUTHOR = "Mohamed, Y. and Khan, F.F. and Haydarov, K. and Elhoseiny, M.", TITLE = "It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "21231-21240", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117747"} @inproceedings{bb121634, AUTHOR = "Chen, J. and Guo, H. and Yi, K. and Li, B.Y. and Elhoseiny, M.", TITLE = "VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "18009-18019", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117748"} @inproceedings{bb121635, AUTHOR = "Chen, S. and Song, Z. and Haque, M. and Liu, C. and Yang, W.", TITLE = "NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "15344-15353", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117749"} @inproceedings{bb121636, AUTHOR = "Hirota, Y. and Nakashima, Y. and Garcia, N.", TITLE = "Quantifying Societal Bias Amplification in Image Captioning", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "13440-13449", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117750"} @inproceedings{bb121637, AUTHOR = "Beddiar, D. and Oussalah, M. and Tapio, S.", TITLE = "Explainability for Medical Image Captioning", BOOKTITLE = IPTA22, YEAR = "2022", PAGES = "1-6", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117751"} @inproceedings{bb121638, AUTHOR = "Bounab, Y. and Oussalah, M. and Ferdenache, A.", TITLE = "Reconciling Image Captioning and User's Comments for Urban Tourism", BOOKTITLE = IPTA20, YEAR = "2020", PAGES = "1-6", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117752"} @inproceedings{bb121639, AUTHOR = "Zha, Z.W. and Zhou, P.F. and Bai, C.", TITLE = "Exploring Implicit and Explicit Relations with the Dual Relation-Aware Network for Image Captioning", BOOKTITLE = MMMod22, YEAR = "2022", PAGES = "II:97-108", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117753"} @inproceedings{bb121640, AUTHOR = "Ruta, D. and Motiian, S. and Faieta, B. and Lin, Z. and Jin, H.L. and Filipkowski, A. and Gilbert, A. and Collomosse, J.", TITLE = "ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "11906-11915", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117754"} @inproceedings{bb121641, AUTHOR = "Nguyen, K. and Tripathi, S. and Du, B. and Guha, T. and Nguyen, T.Q.", TITLE = "In Defense of Scene Graphs for Image Captioning", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "1387-1396", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117755"} @inproceedings{bb121642, AUTHOR = "Shi, J. and Li, Y. and Wang, S.J.", TITLE = "Partial Off-policy Learning: Balance Accuracy and Diversity for Human-Oriented Image Captioning", BOOKTITLE = ICCV21, YEAR = "2021", PAGES = "2167-2176", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117756"} @inproceedings{bb121643, AUTHOR = "Alahmadi, R. and Hahn, J.", TITLE = "Improve Image Captioning by Estimating the Gazing Patterns from the Caption", BOOKTITLE = WACV22, YEAR = "2022", PAGES = "2453-2462", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117757"} @inproceedings{bb121644, AUTHOR = "Biten, A.F. and Gomez, L. and Karatzas, D.", TITLE = "Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning", BOOKTITLE = WACV22, YEAR = "2022", PAGES = "2473-2482", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117758"} @inproceedings{bb121645, AUTHOR = "Deb, T. and Sadmanee, A. and Bhaumik, K.K. and Ali, A.A. and Amin, M.A. and Rahman, A.K.M.M.", TITLE = "Variational Stacked Local Attention Networks for Diverse Video Captioning", BOOKTITLE = WACV22, YEAR = "2022", PAGES = "2493-2502", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117759"} @inproceedings{bb121646, AUTHOR = "Sharif, N. and White, L. and Bennamoun, M. and Liu, W. and Shah, S.A.A.", TITLE = "WEmbSim: A Simple yet Effective Metric for Image Captioning", BOOKTITLE = DICTA20, YEAR = "2020", PAGES = "1-8", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117760"} @inproceedings{bb121647, AUTHOR = "Qiu, J.Y. and Yang, Y.D. and Wang, X. and Tao, D.C.", TITLE = "Scene Essence", BOOKTITLE = CVPR21, YEAR = "2021", PAGES = "8318-8329", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117761"} @inproceedings{bb121648, AUTHOR = "Hosseinzadeh, M. and Wang, Y.", TITLE = "Image Change Captioning by Learning from an Auxiliary Task", BOOKTITLE = CVPR21, YEAR = "2021", PAGES = "2724-2733", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117762"} @inproceedings{bb121649, AUTHOR = "Chen, L. and Jiang, Z.H. and Xiao, J. and Liu, W.", TITLE = "Human-like Controllable Image Captioning with Verb-specific Semantic Roles", BOOKTITLE = CVPR21, YEAR = "2021", PAGES = "16841-16851", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117763"} @inproceedings{bb121650, AUTHOR = "Chen, D.Z.Y. and Gholami, A. and Nießner, M. and Chang, A.X.", TITLE = "Scan2Cap: Context-aware Dense Captioning in RGB-D Scans", BOOKTITLE = CVPR21, YEAR = "2021", PAGES = "3192-3202", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117764"} @inproceedings{bb121651, AUTHOR = "Luong, Q.A. and Vo, D.M. and Sugimoto, A.", TITLE = "Saliency based Subject Selection for Diverse Image Captioning", BOOKTITLE = MVA21, YEAR = "2021", PAGES = "1-5", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117765"} @inproceedings{bb121652, AUTHOR = "Sharif, N. and Bennamoun, M. and Liu, W. and Shah, S.A.A.", TITLE = "SubICap: Towards Subword-informed Image Captioning", BOOKTITLE = WACV21, YEAR = "2021", PAGES = "3539-3540", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117766"} @inproceedings{bb121653, AUTHOR = "Umemura, K. and Kastner, M.A. and Ide, I. and Kawanishi, Y. and Hirayama, T. and Doman, K. and Deguchi, D. and Murase, H.", TITLE = "Tell as You Imagine: Sentence Imageability-aware Image Captioning", BOOKTITLE = MMMod21, YEAR = "2021", PAGES = "II:62-73", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117767"} @inproceedings{bb121654, AUTHOR = "Hallonquist, N. and German, D. and Younes, L.", TITLE = "Graph Discovery for Visual Test Generation", BOOKTITLE = ICPR21, YEAR = "2021", PAGES = "7500-7507", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117768"} @inproceedings{bb121655, AUTHOR = "Li, X.J. and Yang, C. and Chen, S.L. and Zhu, C. and Yin, X.C.", TITLE = "Semantic Bilinear Pooling for Fine-Grained Recognition", BOOKTITLE = ICPR21, YEAR = "2021", PAGES = "3660-3666", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117769"} @inproceedings{bb121656, AUTHOR = "Chavhan, R. and Banerjee, B. and Zhu, X.X. and Chaudhuri, S.", TITLE = "A Novel Actor Dual-Critic Model for Remote Sensing Image Captioning", BOOKTITLE = ICPR21, YEAR = "2021", PAGES = "4918-4925", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117770"} @inproceedings{bb121657, AUTHOR = "Kalimuthu, M. and Mogadala, A. and Mosbach, M. and Klakow, D.", TITLE = "Fusion Models for Improved Image Captioning", BOOKTITLE = MMDLCA20, YEAR = "2020", PAGES = "381-395", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117771"} @inproceedings{bb121658, AUTHOR = "Cetinic, E.", TITLE = "Iconographic Image Captioning for Artworks", BOOKTITLE = FAPER20, YEAR = "2020", PAGES = "502-516", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117772"} @inproceedings{bb121659, AUTHOR = "Huang, Y.Q. and Chen, J.S.", TITLE = "Show, Conceive and Tell: Image Captioning with Prospective Linguistic Information", BOOKTITLE = ACCV20, YEAR = "2020", PAGES = "VI:478-494", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117773"} @inproceedings{bb121660, AUTHOR = "Deng, C.R. and Ding, N. and Tan, M.K. and Wu, Q.", TITLE = "Length-controllable Image Captioning", BOOKTITLE = ECCV20, YEAR = "2020", PAGES = "XIII:712-729", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117774"} @inproceedings{bb121661, AUTHOR = "Gurari, D. and Zhao, Y.N. and Zhang, M. and Bhattacharya, N.", TITLE = "Captioning Images Taken by People Who Are Blind", BOOKTITLE = ECCV20, YEAR = "2020", PAGES = "XVII:417-434", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117775"} @inproceedings{bb121662, AUTHOR = "Zhong, Y.W. and Wang, L.W. and Chen, J.S. and Yu, D. and Li, Y.", TITLE = "Comprehensive Image Captioning via Scene Graph Decomposition", BOOKTITLE = ECCV20, YEAR = "2020", PAGES = "XIV:211-229", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117776"} @inproceedings{bb121663, AUTHOR = "Wang, Z. and Feng, B. and Narasimhan, K. and Russakovsky, O.", TITLE = "Towards Unique and Informative Captioning of Images", BOOKTITLE = ECCV20, YEAR = "2020", PAGES = "VII:629-644", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117777"} @inproceedings{bb121664, AUTHOR = "Sidorov, O. and Hu, R.H. and Rohrbach, M. and Singh, A.", TITLE = "Textcaps: A Dataset for Image Captioning with Reading Comprehension", BOOKTITLE = ECCV20, YEAR = "2020", PAGES = "II:742-758", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117778"} @inproceedings{bb121665, AUTHOR = "Durand, T.", TITLE = "Learning User Representations for Open Vocabulary Image Hashtag Prediction", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "9766-9775", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117779"} @inproceedings{bb121666, AUTHOR = "Prabhudesai, M. and Tung, H.Y.F. and Javed, S.A. and Sieb, M. and Harley, A.W. and Fragkiadaki, K.", TITLE = "Embodied Language Grounding With 3D Visual Feature Representations", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "2217-2226", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117780"} @inproceedings{bb121667, AUTHOR = "Li, Z. and Tran, Q. and Mai, L. and Lin, Z. and Yuille, A.L.", TITLE = "Context-Aware Group Captioning via Self-Attention and Contrastive Features", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "3437-3447", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117781"} @inproceedings{bb121668, AUTHOR = "Zhou, Y. and Wang, M. and Liu, D. and Hu, Z. and Zhang, H.", TITLE = "More Grounded Image Captioning by Distilling Image-Text Matching Model", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "4776-4785", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117782"} @inproceedings{bb121669, AUTHOR = "Sammani, F. and Melas Kyriazi, L.", TITLE = "Show, Edit and Tell: A Framework for Editing Image Captions", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "4807-4815", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117783"} @inproceedings{bb121670, AUTHOR = "Chen, S. and Jin, Q. and Wang, P. and Wu, Q.", TITLE = "Say As You Wish: Fine-Grained Control of Image Caption Generation With Abstract Scene Graphs", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "9959-9968", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117784"} @inproceedings{bb121671, AUTHOR = "Guo, L. and Liu, J. and Zhu, X. and Yao, P. and Lu, S. and Lu, H.", TITLE = "Normalized and Geometry-Aware Self-Attention Network for Image Captioning", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "10324-10333", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117785"} @inproceedings{bb121672, 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#TT117786"} @inproceedings{bb121673, AUTHOR = "Pan, Y. and Yao, T. and Li, Y. and Mei, T.", TITLE = "X-Linear Attention Networks for Image Captioning", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "10968-10977", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117787"} @inproceedings{bb121674, AUTHOR = "Park, G. and Han, C. and Kim, D. and Yoon, W.J.", TITLE = "MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding", BOOKTITLE = WACV20, YEAR = "2020", PAGES = "1507-1515", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117788"} @inproceedings{bb121675, 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#TT117789"} @inproceedings{bb121676, AUTHOR = "He, S. and Tavakoli, H.R. and Borji, A. and Pugeault, N.", TITLE = "Human Attention in Image Captioning: Dataset and Analysis", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "8528-8537", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117790"} @inproceedings{bb121677, AUTHOR = "Huang, L. and Wang, W. and Chen, J. and Wei, X.", TITLE = "Attention on Attention for Image Captioning", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "4633-4642", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117791"} @inproceedings{bb121678, 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#TT117792"} @inproceedings{bb121679, 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#TT117793"} @inproceedings{bb121680, 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#TT117794"} @inproceedings{bb121681, 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#TT117795"} @inproceedings{bb121682, 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#TT117796"} @inproceedings{bb121683, 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#TT117797"} @inproceedings{bb121684, 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#TT117798"} @inproceedings{bb121685, 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#TT117799"} @inproceedings{bb121686, 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#TT117800"} @inproceedings{bb121687, 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#TT117801"} @inproceedings{bb121688, 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#TT117802"} @inproceedings{bb121689, 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#TT117803"} @inproceedings{bb121690, 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#TT117804"} @inproceedings{bb121691, 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#TT117805"} @inproceedings{bb121692, 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#TT117806"} @inproceedings{bb121693, 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#TT117807"} @inproceedings{bb121694, 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#TT117808"} @inproceedings{bb121695, 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#TT117809"} @inproceedings{bb121696, 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#TT117810"} @inproceedings{bb121697, 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#TT117811"} @inproceedings{bb121698, 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#TT117812"} @inproceedings{bb121699, 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#TT117813"}