@inproceedings{bb116500, 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#TT112686"} @inproceedings{bb116501, 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#TT112687"} @inproceedings{bb116502, 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#TT112688"} @inproceedings{bb116503, 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#TT112689"} @inproceedings{bb116504, 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#TT112690"} @inproceedings{bb116505, 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#TT112691"} @inproceedings{bb116506, 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#TT112692"} @inproceedings{bb116507, 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#TT112693"} @inproceedings{bb116508, 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#TT112694"} @inproceedings{bb116509, AUTHOR = "Lahtinen, T. and Turtiainen, H. and Costin, A.", TITLE = "Brima: Low-Overhead Browser-Only Image Annotation Tool (Preprint)", BOOKTITLE = ICIP21, YEAR = "2021", PAGES = "2633-2637", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112695"} @inproceedings{bb116510, 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#TT112696"} @inproceedings{bb116511, AUTHOR = "Lotfi, F. and Jamzad, M. and Beigy, H.", TITLE = "Automatic Image Annotation using Tag Relations and Graph Convolutional Networks", BOOKTITLE = IPRIA21, YEAR = "2021", PAGES = "1-6", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112697"} @inproceedings{bb116512, 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#TT112698"} @inproceedings{bb116513, 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#TT112699"} @inproceedings{bb116514, 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#TT112700"} @inproceedings{bb116515, AUTHOR = "Xu, G.H. and Niu, S.C. and Tan, M.K. and Luo, Y.C. and Du, Q. and Wu, Q.", TITLE = "Towards Accurate Text-based Image Captioning with Content Diversity Exploration", BOOKTITLE = CVPR21, YEAR = "2021", PAGES = "12632-12641", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112701"} @inproceedings{bb116516, 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#TT112702"} @inproceedings{bb116517, 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#TT112703"} @inproceedings{bb116518, 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#TT112704"} @inproceedings{bb116519, AUTHOR = "Chen, X.Y. and Jiang, M. and Zhao, Q.", TITLE = "Self-Distillation for Few-Shot Image Captioning", BOOKTITLE = WACV21, YEAR = "2021", PAGES = "545-555", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112705"} @inproceedings{bb116520, 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#TT112706"} @inproceedings{bb116521, 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#TT112707"} @inproceedings{bb116522, 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#TT112708"} @inproceedings{bb116523, 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#TT112709"} @inproceedings{bb116524, 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#TT112710"} @inproceedings{bb116525, AUTHOR = "Cetinic, E.", TITLE = "Iconographic Image Captioning for Artworks", BOOKTITLE = FAPER20, YEAR = "2020", PAGES = "502-516", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112711"} @inproceedings{bb116526, 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#TT112712"} @inproceedings{bb116527, 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#TT112713"} @inproceedings{bb116528, 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#TT112714"} @inproceedings{bb116529, AUTHOR = "Jiu, M. and Sahbi, H.", TITLE = "End-to-End Deep Kernel Map Design for Image Annotation", BOOKTITLE = ICIP20, YEAR = "2020", PAGES = "1546-1550", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112715"} @inproceedings{bb116530, 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#TT112716"} @inproceedings{bb116531, 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#TT112717"} @inproceedings{bb116532, 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#TT112718"} @inproceedings{bb116533, 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#TT112719"} @inproceedings{bb116534, 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#TT112720"} @inproceedings{bb116535, 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#TT112721"} @inproceedings{bb116536, 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#TT112722"} @inproceedings{bb116537, 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#TT112723"} @inproceedings{bb116538, 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#TT112724"} @inproceedings{bb116539, 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#TT112725"} @inproceedings{bb116540, 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#TT112726"} @inproceedings{bb116541, 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#TT112727"} @inproceedings{bb116542, AUTHOR = "Tran, A. and Mathews, A. and Xie, L.", TITLE = "Transform and Tell: Entity-Aware News Image Captioning", BOOKTITLE = CVPR20, YEAR = "2020", PAGES = "13032-13042", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112728"} @inproceedings{bb116543, 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#TT112729"} @inproceedings{bb116544, 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#TT112730"} @inproceedings{bb116545, 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#TT112731"} @inproceedings{bb116546, 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#TT112732"} @inproceedings{bb116547, 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#TT112733"} @inproceedings{bb116548, 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#TT112734"} @inproceedings{bb116549, 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#TT112735"} @inproceedings{bb116550, 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#TT112736"} @inproceedings{bb116551, 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#TT112737"} @inproceedings{bb116552, 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#TT112738"} @inproceedings{bb116553, AUTHOR = "Hu, H. and Misra, I. and van der Maaten, L.", TITLE = "Evaluating Text-to-Image Matching using Binary Image Selection (BISON)", BOOKTITLE = CLVL19, YEAR = "2019", PAGES = "1887-1890", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112739"} @inproceedings{bb116554, 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#TT112740"} @inproceedings{bb116555, 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#TT112741"} @inproceedings{bb116556, 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#TT112742"} @inproceedings{bb116557, AUTHOR = "Tanaka, M. and Itamochi, T. and Narioka, K. and Sato, I. and Ushiku, Y. and Harada, T.", TITLE = "Generating Easy-to-Understand Referring Expressions for Target Identifications", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "5793-5802", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112743"} @inproceedings{bb116558, 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#TT112744"} @inproceedings{bb116559, AUTHOR = "Gupta, T. and Schwing, A.G. and Hoiem, D.", TITLE = "ViCo: Word Embeddings From Visual Co-Occurrences", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "7424-7433", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112745"} @inproceedings{bb116560, 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#TT112746"} @inproceedings{bb116561, 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#TT112747"} @inproceedings{bb116562, 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#TT112748"} @inproceedings{bb116563, 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#TT112749"} @inproceedings{bb116564, 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#TT112750"} @inproceedings{bb116565, 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#TT112751"} @inproceedings{bb116566, AUTHOR = "Bracha, L. and Chechik, G.", TITLE = "Informative Object Annotations: Tell Me Something I Don't Know", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "12499-12507", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112752"} @inproceedings{bb116567, 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#TT112753"} @inproceedings{bb116568, 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#TT112754"} @inproceedings{bb116569, 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#TT112755"} @inproceedings{bb116570, 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#TT112756"} @inproceedings{bb116571, 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#TT112757"} @inproceedings{bb116572, 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#TT112758"} @inproceedings{bb116573, 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#TT112759"} @inproceedings{bb116574, 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#TT112760"} @inproceedings{bb116575, 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#TT112761"} @inproceedings{bb116576, 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#TT112762"} @inproceedings{bb116577, 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#TT112763"} @inproceedings{bb116578, 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#TT112764"} @inproceedings{bb116579, 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#TT112765"} @inproceedings{bb116580, 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#TT112766"} @inproceedings{bb116581, 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#TT112767"} @inproceedings{bb116582, 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#TT112768"} @inproceedings{bb116583, 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#TT112769"} @inproceedings{bb116584, 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#TT112770"} @inproceedings{bb116585, 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#TT112771"} @inproceedings{bb116586, 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#TT112772"} @inproceedings{bb116587, 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#TT112773"} @inproceedings{bb116588, 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#TT112774"} @inproceedings{bb116589, 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#TT112775"} @inproceedings{bb116590, 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#TT112776"} @inproceedings{bb116591, 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#TT112777"} @inproceedings{bb116592, AUTHOR = "Rapson, C.J. and Seet, B. and Naeem, M.A. and Lee, J.E. and Al Sarayreh, M. and Klette, R.", TITLE = "Reducing the Pain: A Novel Tool for Efficient Ground-Truth Labelling in Images", BOOKTITLE = IVCNZ18, YEAR = "2018", PAGES = "1-9", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112778"} @inproceedings{bb116593, 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#TT112779"} @inproceedings{bb116594, AUTHOR = "Wu, B.Y. and Chen, W.D. and Sun, P. and Liu, W. and Ghanem, B. and Lyu, S.W.", TITLE = "Tagging Like Humans: Diverse and Distinct Image Annotation", BOOKTITLE = CVPR18, YEAR = "2018", PAGES = "7967-7975", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112780"} @inproceedings{bb116595, AUTHOR = "Wu, X.J. and Zhang, L. and Li, F.Z. and Wang, B.J.", TITLE = "A Novel Model for Multi-label Image Annotation", BOOKTITLE = ICPR18, YEAR = "2018", PAGES = "1953-1958", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112781"} @inproceedings{bb116596, AUTHOR = "Jiu, M. and Sahbi, H. and Qi, L.", TITLE = "Deep Context Networks for Image Annotation", BOOKTITLE = ICPR18, YEAR = "2018", PAGES = "2422-2427", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT112782"} @inproceedings{bb116597, 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#TT112783"} @inproceedings{bb116598, 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#TT112784"} @inproceedings{bb116599, 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#TT112785"}