@inproceedings{bb136100,
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#TT132092"}
@inproceedings{bb136101,
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#TT132093"}
@inproceedings{bb136102,
AUTHOR = "Fan, J.S. and Liang, Y.Y. and Liu, L. and Huang, S.L. 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#TT132094"}
@inproceedings{bb136103,
AUTHOR = "Li, R. and Sun, S.Y. and Elhoseiny, M. and Torr, P.H.S.",
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#TT132095"}
@inproceedings{bb136104,
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#TT132096"}
@inproceedings{bb136105,
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#TT132097"}
@inproceedings{bb136106,
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#TT132098"}
@inproceedings{bb136107,
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#TT132099"}
@inproceedings{bb136108,
AUTHOR = "Kim, Y. and Kim, J.H. 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#TT132100"}
@inproceedings{bb136109,
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#TT132101"}
@inproceedings{bb136110,
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#TT132102"}
@inproceedings{bb136111,
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#TT132103"}
@inproceedings{bb136112,
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#TT132104"}
@inproceedings{bb136113,
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#TT132105"}
@inproceedings{bb136114,
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#TT132106"}
@inproceedings{bb136115,
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#TT132107"}
@inproceedings{bb136116,
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#TT132108"}
@inproceedings{bb136117,
AUTHOR = "Zhang, Y.Y. and Wang, J.N. 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#TT132109"}
@inproceedings{bb136118,
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#TT132110"}
@inproceedings{bb136119,
AUTHOR = "Meng, Z.H. 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#TT132111"}
@inproceedings{bb136120,
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#TT132112"}
@inproceedings{bb136121,
AUTHOR = "Jiao, Y. and Chen, S.X. and Jie, Z.Q. 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#TT132113"}
@inproceedings{bb136122,
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#TT132114"}
@inproceedings{bb136123,
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#TT132115"}
@inproceedings{bb136124,
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#TT132116"}
@inproceedings{bb136125,
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#TT132117"}
@inproceedings{bb136126,
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#TT132118"}
@inproceedings{bb136127,
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#TT132119"}
@inproceedings{bb136128,
AUTHOR = "Chen, S. and Song, Z.H. 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#TT132120"}
@inproceedings{bb136129,
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#TT132121"}
@inproceedings{bb136130,
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#TT132122"}
@inproceedings{bb136131,
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#TT132123"}
@inproceedings{bb136132,
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#TT132124"}
@inproceedings{bb136133,
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#TT132125"}
@inproceedings{bb136134,
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#TT132126"}
@inproceedings{bb136135,
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#TT132127"}
@inproceedings{bb136136,
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#TT132128"}
@inproceedings{bb136137,
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#TT132129"}
@inproceedings{bb136138,
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#TT132130"}
@inproceedings{bb136139,
AUTHOR = "Qiu, J.Y. and Yang, Y.D. and Wang, X.C. and Tao, D.C.",
TITLE = "Scene Essence",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "8318-8329",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT132131"}
@inproceedings{bb136140,
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#TT132132"}
@inproceedings{bb136141,
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#TT132133"}
@inproceedings{bb136142,
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#TT132134"}
@inproceedings{bb136143,
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#TT132135"}
@inproceedings{bb136144,
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#TT132136"}
@inproceedings{bb136145,
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#TT132137"}
@inproceedings{bb136146,
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#TT132138"}
@inproceedings{bb136147,
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#TT132139"}
@inproceedings{bb136148,
AUTHOR = "Cetinic, E.",
TITLE = "Iconographic Image Captioning for Artworks",
BOOKTITLE = FAPER20,
YEAR = "2020",
PAGES = "502-516",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT132140"}
@inproceedings{bb136149,
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#TT132141"}
@inproceedings{bb136150,
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#TT132142"}
@inproceedings{bb136151,
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#TT132143"}
@inproceedings{bb136152,
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#TT132144"}
@inproceedings{bb136153,
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#TT132145"}
@inproceedings{bb136154,
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#TT132146"}
@inproceedings{bb136155,
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#TT132147"}
@inproceedings{bb136156,
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#TT132148"}
@inproceedings{bb136157,
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#TT132149"}
@inproceedings{bb136158,
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#TT132150"}
@inproceedings{bb136159,
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#TT132151"}
@inproceedings{bb136160,
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#TT132152"}
@inproceedings{bb136161,
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#TT132153"}
@inproceedings{bb136162,
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#TT132154"}
@inproceedings{bb136163,
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#TT132155"}
@inproceedings{bb136164,
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#TT132156"}
@inproceedings{bb136165,
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#TT132157"}
@inproceedings{bb136166,
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#TT132158"}
@inproceedings{bb136167,
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#TT132159"}
@inproceedings{bb136168,
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#TT132160"}
@inproceedings{bb136169,
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#TT132161"}
@inproceedings{bb136170,
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#TT132162"}
@inproceedings{bb136171,
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#TT132163"}
@inproceedings{bb136172,
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#TT132164"}
@inproceedings{bb136173,
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#TT132165"}
@inproceedings{bb136174,
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#TT132166"}
@inproceedings{bb136175,
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#TT132167"}
@inproceedings{bb136176,
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#TT132168"}
@inproceedings{bb136177,
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#TT132169"}
@inproceedings{bb136178,
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#TT132170"}
@inproceedings{bb136179,
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#TT132171"}
@inproceedings{bb136180,
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#TT132172"}
@inproceedings{bb136181,
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#TT132173"}
@inproceedings{bb136182,
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#TT132174"}
@inproceedings{bb136183,
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#TT132175"}
@inproceedings{bb136184,
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#TT132176"}
@inproceedings{bb136185,
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#TT132177"}
@inproceedings{bb136186,
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#TT132178"}
@inproceedings{bb136187,
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#TT132179"}
@inproceedings{bb136188,
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#TT132180"}
@inproceedings{bb136189,
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#TT132181"}
@inproceedings{bb136190,
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#TT132182"}
@inproceedings{bb136191,
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#TT132183"}
@inproceedings{bb136192,
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#TT132184"}
@inproceedings{bb136193,
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#TT132185"}
@inproceedings{bb136194,
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#TT132186"}
@inproceedings{bb136195,
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#TT132187"}
@inproceedings{bb136196,
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#TT132188"}
@inproceedings{bb136197,
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#TT132189"}
@inproceedings{bb136198,
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#TT132190"}
@inproceedings{bb136199,
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#TT132191"}
Last update:Apr 23, 2026 at 15:05:02