@inproceedings{bb135400,
        AUTHOR = "Nebbia, G. and Kovashka, A.",
        TITLE = "Image-caption difficulty for efficient weakly-supervised object
detection from in-the-wild data",
        BOOKTITLE = L3D-IVU24,
        YEAR = "2024",
        PAGES = "2596-2605",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131393"}

@inproceedings{bb135401,
        AUTHOR = "Sakaino, H. and Phuong, T.N. and Duy, V.N.",
        TITLE = "PV-Cap: 3D Dynamic Scene Understanding Through Open Physics-based
Vocabulary",
        BOOKTITLE = AICity24,
        YEAR = "2024",
        PAGES = "7932-7942",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131394"}

@inproceedings{bb135402,
        AUTHOR = "Kong, F. and Chen, Y.B. and Cai, J.R. and Modolo, D.",
        TITLE = "Hyperbolic Learning with Synthetic Captions for Open-World Detection",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "16762-16771",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131395"}

@inproceedings{bb135403,
        AUTHOR = "Zeng, Z.Q. and Xie, Y. and Zhang, H. and Chen, C. and Chen, B. and Wang, Z.J.",
        TITLE = "MeaCap: Memory-Augmented Zero-shot Image Captioning",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "14100-14110",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131396"}

@inproceedings{bb135404,
        AUTHOR = "Wada, Y. and Kaneda, K. and Saito, D. and Sugiura, K.",
        TITLE = "Polos: Multimodal Metric Learning from Human Feedback for Image
Captioning",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "13559-13568",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131397"}

@inproceedings{bb135405,
        AUTHOR = "Huang, X.K. and Wang, J.F. and Tang, Y.S. and Zhang, Z. and Hu, H. and Lu, J.W. and Wang, L.J. and Liu, Z.C.",
        TITLE = "Segment and Caption Anything",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "13405-13417",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131398"}

@inproceedings{bb135406,
        AUTHOR = "Ge, Y.H. and Zeng, X.H. and Huffman, J.S. and Lin, T.Y. and Liu, M.Y. and Cui, Y.",
        TITLE = "Visual Fact Checker: Enabling High-Fidelity Detailed Caption
Generation",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "14033-14042",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131399"}

@inproceedings{bb135407,
        AUTHOR = "Ruan, J. and Wu, Y. and Wan, X.J. and Zhu, Y.S.",
        TITLE = "Describe Images in a Boring Way:
Towards Cross-Modal Sarcasm Generation",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "5689-5698",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131400"}

@inproceedings{bb135408,
        AUTHOR = "Hirsch, E. and Tal, A.",
        TITLE = "CLID: Controlled-Length Image Descriptions with Limited Data",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "5519-5529",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131401"}

@inproceedings{bb135409,
        AUTHOR = "Petryk, S. and Whitehead, S. and Gonzalez, J.E. and Darrell, T.J. and Rohrbach, A. and Rohrbach, M.",
        TITLE = "Simple Token-Level Confidence Improves Caption Correctness",
        BOOKTITLE = WACV24,
        YEAR = "2024",
        PAGES = "5730-5740",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131402"}

@inproceedings{bb135410,
        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#TT131403"}

@inproceedings{bb135411,
        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#TT131404"}

@inproceedings{bb135412,
        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#TT131405"}

@inproceedings{bb135413,
        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#TT131406"}

@inproceedings{bb135414,
        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#TT131407"}

@inproceedings{bb135415,
        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#TT131408"}

@inproceedings{bb135416,
        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#TT131409"}

@inproceedings{bb135417,
        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#TT131410"}

@inproceedings{bb135418,
        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#TT131411"}

@inproceedings{bb135419,
        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#TT131412"}

@inproceedings{bb135420,
        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#TT131413"}

@inproceedings{bb135421,
        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#TT131414"}

@inproceedings{bb135422,
        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#TT131415"}

@inproceedings{bb135423,
        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#TT131416"}

@inproceedings{bb135424,
        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#TT131417"}

@inproceedings{bb135425,
        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#TT131418"}

@inproceedings{bb135426,
        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#TT131419"}

@inproceedings{bb135427,
        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#TT131420"}

@inproceedings{bb135428,
        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#TT131421"}

@inproceedings{bb135429,
        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#TT131422"}

@inproceedings{bb135430,
        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#TT131423"}

@inproceedings{bb135431,
        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#TT131424"}

@inproceedings{bb135432,
        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#TT131425"}

@inproceedings{bb135433,
        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#TT131426"}

@inproceedings{bb135434,
        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#TT131427"}

@inproceedings{bb135435,
        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#TT131428"}

@inproceedings{bb135436,
        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#TT131429"}

@inproceedings{bb135437,
        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#TT131430"}

@inproceedings{bb135438,
        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#TT131431"}

@inproceedings{bb135439,
        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#TT131432"}

@inproceedings{bb135440,
        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#TT131433"}

@inproceedings{bb135441,
        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#TT131434"}

@inproceedings{bb135442,
        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#TT131435"}

@inproceedings{bb135443,
        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#TT131436"}

@inproceedings{bb135444,
        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#TT131437"}

@inproceedings{bb135445,
        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#TT131438"}

@inproceedings{bb135446,
        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#TT131439"}

@inproceedings{bb135447,
        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#TT131440"}

@inproceedings{bb135448,
        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#TT131441"}

@inproceedings{bb135449,
        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#TT131442"}

@inproceedings{bb135450,
        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#TT131443"}

@inproceedings{bb135451,
        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#TT131444"}

@inproceedings{bb135452,
        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#TT131445"}

@inproceedings{bb135453,
        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#TT131446"}

@inproceedings{bb135454,
        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#TT131447"}

@inproceedings{bb135455,
        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#TT131448"}

@inproceedings{bb135456,
        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#TT131449"}

@inproceedings{bb135457,
        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#TT131450"}

@inproceedings{bb135458,
        AUTHOR = "Cetinic, E.",
        TITLE = "Iconographic Image Captioning for Artworks",
        BOOKTITLE = FAPER20,
        YEAR = "2020",
        PAGES = "502-516",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT131451"}

@inproceedings{bb135459,
        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#TT131452"}

@inproceedings{bb135460,
        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#TT131453"}

@inproceedings{bb135461,
        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#TT131454"}

@inproceedings{bb135462,
        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#TT131455"}

@inproceedings{bb135463,
        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#TT131456"}

@inproceedings{bb135464,
        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#TT131457"}

@inproceedings{bb135465,
        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#TT131458"}

@inproceedings{bb135466,
        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#TT131459"}

@inproceedings{bb135467,
        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#TT131460"}

@inproceedings{bb135468,
        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#TT131461"}

@inproceedings{bb135469,
        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#TT131462"}

@inproceedings{bb135470,
        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#TT131463"}

@inproceedings{bb135471,
        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#TT131464"}

@inproceedings{bb135472,
        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#TT131465"}

@inproceedings{bb135473,
        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#TT131466"}

@inproceedings{bb135474,
        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#TT131467"}

@inproceedings{bb135475,
        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#TT131468"}

@inproceedings{bb135476,
        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#TT131469"}

@inproceedings{bb135477,
        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#TT131470"}

@inproceedings{bb135478,
        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#TT131471"}

@inproceedings{bb135479,
        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#TT131472"}

@inproceedings{bb135480,
        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#TT131473"}

@inproceedings{bb135481,
        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#TT131474"}

@inproceedings{bb135482,
        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#TT131475"}

@inproceedings{bb135483,
        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#TT131476"}

@inproceedings{bb135484,
        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#TT131477"}

@inproceedings{bb135485,
        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#TT131478"}

@inproceedings{bb135486,
        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#TT131479"}

@inproceedings{bb135487,
        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#TT131480"}

@inproceedings{bb135488,
        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#TT131481"}

@inproceedings{bb135489,
        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#TT131482"}

@inproceedings{bb135490,
        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#TT131483"}

@inproceedings{bb135491,
        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#TT131484"}

@inproceedings{bb135492,
        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#TT131485"}

@inproceedings{bb135493,
        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#TT131486"}

@inproceedings{bb135494,
        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#TT131487"}

@inproceedings{bb135495,
        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#TT131488"}

@inproceedings{bb135496,
        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#TT131489"}

@inproceedings{bb135497,
        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#TT131490"}

@inproceedings{bb135498,
        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#TT131491"}

@inproceedings{bb135499,
        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#TT131492"}

Last update:Feb 26, 2026 at 10:58:24