@article{bb121300, AUTHOR = "Shao, X.J. and Xiang, Z.L. and Li, Y.X. and Zhang, M.J.", TITLE = "Variational joint self-attention for image captioning", JOURNAL = IET-IPR, VOLUME = "16", YEAR = "2022", NUMBER = "8", PAGES = "2075-2086", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117414"} @article{bb121301, AUTHOR = "Li, Y.C. and Wu, C. and Li, L. and Liu, Y.H. and Zhu, J.", TITLE = "Caption Generation From Road Images for Traffic Scene Modeling", JOURNAL = ITS, VOLUME = "23", YEAR = "2022", NUMBER = "7", MONTH = "July", PAGES = "7805-7816", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117415"} @article{bb121302, AUTHOR = "Wang, Y.H. and Xu, N. and Liu, A.A. and Li, W.H. and Zhang, Y.D.", TITLE = "High-Order Interaction Learning for Image Captioning", JOURNAL = CirSysVideo, VOLUME = "32", YEAR = "2022", NUMBER = "7", MONTH = "July", PAGES = "4417-4430", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117416"} @article{bb121303, AUTHOR = "Guo, D.D. and Lu, R.Y. and Chen, B. and Zeng, Z.Q. and Zhou, M.Y.", TITLE = "Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning", JOURNAL = IJCV, VOLUME = "130", YEAR = "2022", NUMBER = "8", MONTH = "August", PAGES = "1920-1937", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117417"} @article{bb121304, AUTHOR = "Demirel, B. and Cinbis, R.G.", TITLE = "Caption generation on scenes with seen and unseen object categories", JOURNAL = IVC, VOLUME = "124", YEAR = "2022", PAGES = "104515", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117418"} @article{bb121305, AUTHOR = "Liu, Z.Y. and Dong, A.M. and Yu, J.G. and Han, Y.B. and Zhou, Y. and Zhao, K.", TITLE = "Scene classification for remote sensing images with self-attention augmented CNN", JOURNAL = IET-IPR, VOLUME = "16", YEAR = "2022", NUMBER = "11", PAGES = "3085-3096", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117419"} @article{bb121306, AUTHOR = "Wu, X.X. and Zhao, W.T. and Luo, J.B.", TITLE = "Learning Cooperative Neural Modules for Stylized Image Captioning", JOURNAL = IJCV, VOLUME = "130", YEAR = "2022", NUMBER = "9", MONTH = "September", PAGES = "2305-2320", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117420"} @article{bb121307, AUTHOR = "Zhou, H. and Du, X.P. and Xia, L. and Li, S.", TITLE = "Self-Learning for Few-Shot Remote Sensing Image Captioning", JOURNAL = RS, VOLUME = "14", YEAR = "2022", NUMBER = "18", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117421"} @article{bb121308, AUTHOR = "Stefanini, M. and Cornia, M. and Baraldi, L. and Cascianelli, S. and Fiameni, G. and Cucchiara, R.", TITLE = "From Show to Tell: A Survey on Deep Learning-Based Image Captioning", JOURNAL = PAMI, VOLUME = "45", YEAR = "2023", NUMBER = "1", MONTH = "January", PAGES = "539-559", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117422"} @article{bb121309, AUTHOR = "Wu, Y. and Jiang, L. and Yang, Y.", TITLE = "Switchable Novel Object Captioner", JOURNAL = PAMI, VOLUME = "45", YEAR = "2023", NUMBER = "1", MONTH = "January", PAGES = "1162-1173", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117423"} @article{bb121310, AUTHOR = "Hochberg, D.C. and Greenspan, H. and Giryes, R.", TITLE = "A Self Supervised StyleGAN for Image Annotation and Classification With Extremely Limited Labels", JOURNAL = MedImg, VOLUME = "41", YEAR = "2022", NUMBER = "12", MONTH = "December", PAGES = "3509-3519", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117424"} @article{bb121311, AUTHOR = "Yang, X. and Zhang, H.W. and Gao, C.Y. and Cai, J.F.", TITLE = "Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning", JOURNAL = IJCV, VOLUME = "131", YEAR = "2023", NUMBER = "1", MONTH = "January", PAGES = "82-100", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117425"} @inproceedings{bb121312, AUTHOR = "Yang, X. and Zhang, H.W. and Cai, J.F.", TITLE = "Learning to Collocate Neural Modules for Image Captioning", BOOKTITLE = ICCV19, YEAR = "2019", PAGES = "4249-4259", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117426"} @article{bb121313, AUTHOR = "Wang, J. and Xu, W.J. and Wang, Q.Z. and Chan, A.B.", TITLE = "On Distinctive Image Captioning via Comparing and Reweighting", JOURNAL = PAMI, VOLUME = "45", YEAR = "2023", NUMBER = "2", MONTH = "February", PAGES = "2088-2103", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117427"} @article{bb121314, AUTHOR = "Ma, Y.W. and Ji, J.Y. and Sun, X.S. and Zhou, Y. and Ji, R.R.", TITLE = "Towards local visual modeling for image captioning", JOURNAL = PR, VOLUME = "138", YEAR = "2023", PAGES = "109420", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117428"} @article{bb121315, AUTHOR = "Barati, A. and Farsi, H. and Mohamadzadeh, S.", TITLE = "Integration of the latent variable knowledge into deep image captioning with Bayesian modeling", JOURNAL = IET-IPR, VOLUME = "17", YEAR = "2023", NUMBER = "7", PAGES = "2256-2271", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117429"} @article{bb121316, AUTHOR = "Feng, J.L. and Zhao, J.P.", TITLE = "Effectively Utilizing the Category Labels for Image Captioning", JOURNAL = IEICE, VOLUME = "E106-D", YEAR = "2023", NUMBER = "5", MONTH = "May", PAGES = "617-624", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117430"} @article{bb121317, AUTHOR = "Wang, D.P. and Hu, Z.Z. and Zhou, Y. and Hong, R.C. and Wang, M.", TITLE = "A Text-Guided Generation and Refinement Model for Image Captioning", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "2966-2977", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117431"} @article{bb121318, AUTHOR = "Wang, Q. and Huang, W. and Zhang, X.T. and Li, X.L.", TITLE = "GLCM: Global-Local Captioning Model for Remote Sensing Image Captioning", JOURNAL = Cyber, VOLUME = "53", YEAR = "2023", NUMBER = "11", MONTH = "November", PAGES = "6910-6922", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117432"} @article{bb121319, AUTHOR = "Ji, J.Y. and Huang, X.Y. and Sun, X.S. and Zhou, Y. and Luo, G. and Cao, L.J. and Liu, J.Z. and Shao, L. and Ji, R.R.", TITLE = "Multi-Branch Distance-Sensitive Self-Attention Network for Image Captioning", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "3962-3974", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117433"} @article{bb121320, AUTHOR = "Cornia, M. and Baraldi, L. and Tal, A. and Cucchiara, R.", TITLE = "Fully-attentive iterative networks for region-based controllable image and video captioning", JOURNAL = CVIU, VOLUME = "237", YEAR = "2023", PAGES = "103857", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117434"} @article{bb121321, AUTHOR = "Li, Y.P. and Zhang, X.R. and Cheng, X. and Tang, X. and Jiao, L.C.", TITLE = "Learning consensus-aware semantic knowledge for remote sensing image captioning", JOURNAL = PR, VOLUME = "145", YEAR = "2024", PAGES = "109893", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117435"} @article{bb121322, AUTHOR = "Al Qatf, M. and Wang, X. and Hawbani, A. and Abdussalam, A. and Alsamhi, S.H.", TITLE = "Image Captioning With Novel Topics Guidance and Retrieval-Based Topics Re-Weighting", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "5984-5999", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117436"} @article{bb121323, AUTHOR = "Zhu, P.P. and Wang, X. and Luo, Y. and Sun, Z.L. and Zheng, W.S. and Wang, Y. and Chen, C.", TITLE = "Unpaired Image Captioning by Image-Level Weakly-Supervised Visual Concept Recognition", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "6702-6716", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117437"} @article{bb121324, AUTHOR = "Hu, N.N. and Ming, Y. and Fan, C.X. and Feng, F. and Lyu, B.Y.", TITLE = "TSFNet: Triple-Steam Image Captioning", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "6904-6916", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117438"} @article{bb121325, AUTHOR = "Gonzalez Chavez, O. and Ruiz, G. and Moctezuma, D. and Ramirez delReal, T.", TITLE = "Are metrics measuring what they should? An evaluation of Image Captioning task metrics", JOURNAL = SP:IC, VOLUME = "120", YEAR = "2024", PAGES = "117071", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117439"} @article{bb121326, AUTHOR = "Padate, R. and Jain, A. and Kalla, M. and Sharma, A.", TITLE = "A Widespread Assessment and Open Issues on Image Captioning Models", JOURNAL = IJIG, VOLUME = "23", YEAR = "2023", NUMBER = "6 2023", PAGES = "2350057", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117440"} @article{bb121327, AUTHOR = "Shao, Z. and Han, J.G. and Debattista, K. and Pang, Y.W.", TITLE = "Textual Context-Aware Dense Captioning With Diverse Words", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "8753-8766", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117441"} @article{bb121328, AUTHOR = "Cheng, J. and Wu, F. and Liu, L. and Zhang, Q. and Rutkowski, L. and Tao, D.C.", TITLE = "InDecGAN: Learning to Generate Complex Images From Captions via Independent Object-Level Decomposition and Enhancement", JOURNAL = MultMed, VOLUME = "25", YEAR = "2023", PAGES = "8279-8293", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117442"} @article{bb121329, AUTHOR = "Ding, N. and Deng, C.R. and Tan, M.K. and Du, Q. and Ge, Z.W. and Wu, Q.", TITLE = "Image Captioning With Controllable and Adaptive Length Levels", JOURNAL = PAMI, VOLUME = "46", YEAR = "2024", NUMBER = "2", MONTH = "February", PAGES = "764-779", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117443"} @inproceedings{bb121330, 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#TT117444"} @article{bb121331, AUTHOR = "Zhu, P.P. and Wang, X. and Zhu, L. and Sun, Z.L. and Zheng, W.S. and Wang, Y. and Chen, C.W.", TITLE = "Prompt-Based Learning for Unpaired Image Captioning", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "379-393", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117445"} @inproceedings{bb121332, 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#TT117446"} @inproceedings{bb121333, 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#TT117447"} @inproceedings{bb121334, AUTHOR = "Wei, Y.C. and Li, L. and Geng, S.L.", TITLE = "Remote Sensing Image Captioning Using Hire-MLP", BOOKTITLE = CVIDL23, YEAR = "2023", PAGES = "109-112", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117448"} @inproceedings{bb121335, AUTHOR = "Fan, J. and Liang, Y. and Liu, L. and Huang, S. and Zhang, L.", TITLE = "RCA-NOC: Relative Contrastive Alignment for Novel Object Captioning", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "15464-15474", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117449"} @inproceedings{bb121336, AUTHOR = "Li, R. and Sun, S.Y. and Elhoseiny, M. and Torr, P.", TITLE = "OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "20236-20246", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117450"} @inproceedings{bb121337, 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#TT117451"} @inproceedings{bb121338, 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#TT117452"} @inproceedings{bb121339, AUTHOR = "Barraco, M. and Sarto, S. and Cornia, M. and Baraldi, L. and Cucchiara, R.", TITLE = "With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning", BOOKTITLE = ICCV23, YEAR = "2023", PAGES = "3009-3019", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117453"} @inproceedings{bb121340, 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#TT117454"} @inproceedings{bb121341, 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#TT117455"} @inproceedings{bb121342, AUTHOR = "Kim, Y. and Kim, J. and Lee, B.K. and Shin, S. and Ro, Y.M.", TITLE = "Mitigating Dataset Bias in Image Captioning Through Clip Confounder-Free Captioning Network", BOOKTITLE = ICIP23, YEAR = "2023", PAGES = "1720-1724", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117456"} @inproceedings{bb121343, 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#TT117457"} @inproceedings{bb121344, 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#TT117458"} @inproceedings{bb121345, 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#TT117459"} @inproceedings{bb121346, 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#TT117460"} @inproceedings{bb121347, 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#TT117461"} @inproceedings{bb121348, AUTHOR = "Chen, S.J. and Zhu, H.Y. and Chen, X. and Lei, Y.J. and Yu, G. and Chen, T.", TITLE = "End-to-End 3D Dense Captioning with Vote2Cap-DETR", BOOKTITLE = CVPR23, YEAR = "2023", PAGES = "11124-11133", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117462"} @inproceedings{bb121349, 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#TT117463"} @inproceedings{bb121350, 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#TT117464"} @inproceedings{bb121351, AUTHOR = "Zhang, Y. and Wang, J. and Wu, H. and Xu, W.J.", TITLE = "Distinctive Image Captioning via Clip Guided Group Optimization", BOOKTITLE = CMHRI22, YEAR = "2022", PAGES = "223-238", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117465"} @inproceedings{bb121352, AUTHOR = "Qiu, Y. and Yamamoto, S. and Yamada, R. and Suzuki, R. and Kataoka, H. and Iwata, K. and Satoh, Y.", TITLE = "3D Change Localization and Captioning from Dynamic Scans of Indoor Scenes", BOOKTITLE = WACV23, YEAR = "2023", PAGES = "1176-1185", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117466"} @inproceedings{bb121353, 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#TT117467"} @inproceedings{bb121354, AUTHOR = "Sui, J.H. and Yu, H.M. and Liang, X.Y. and Ping, P.", TITLE = "Image Caption Method Based on Graph Attention Network with Global Context", BOOKTITLE = ICIVC22, YEAR = "2022", PAGES = "480-487", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117468"} @inproceedings{bb121355, AUTHOR = "Barraco, M. and Stefanini, M. and Cornia, M. and Cascianelli, S. and Baraldi, L. and Cucchiara, R.", TITLE = "CaMEL: Mean Teacher Learning for Image Captioning", BOOKTITLE = "ICPR22", YEAR = "2022", PAGES = "4087-4094", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117469"} @inproceedings{bb121356, 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#TT117470"} @inproceedings{bb121357, AUTHOR = "Meng, Z. and Yang, D. and Cao, X.F. and Shah, A. and Lim, S.N.", TITLE = "Object-Centric Unsupervised Image Captioning", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXVI:219-235", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117471"} @inproceedings{bb121358, 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#TT117472"} @inproceedings{bb121359, AUTHOR = "Jiao, Y. and Chen, S.X. and Jie, Z. and Chen, J.J. and Ma, L. and Jiang, Y.G.", TITLE = "MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes", BOOKTITLE = ECCV22, YEAR = "2022", PAGES = "XXXV:528-545", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117473"} @inproceedings{bb121360, 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#TT117474"} @inproceedings{bb121361, 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#TT117475"} @inproceedings{bb121362, 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#TT117476"} @inproceedings{bb121363, 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#TT117477"} @inproceedings{bb121364, AUTHOR = "Popattia, M. and Rafi, M. and Qureshi, R. and Nawaz, S.", TITLE = "Guiding Attention using Partial-Order Relationships for Image Captioning", BOOKTITLE = MULA22, YEAR = "2022", PAGES = "4670-4679", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117478"} @inproceedings{bb121365, 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#TT117479"} @inproceedings{bb121366, 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#TT117480"} @inproceedings{bb121367, AUTHOR = "Chen, S. and Song, Z. and Haque, M. and Liu, C. and Yang, W.", TITLE = "NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models", BOOKTITLE = CVPR22, YEAR = "2022", PAGES = "15344-15353", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117481"} @inproceedings{bb121368, 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#TT117482"} @inproceedings{bb121369, 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#TT117483"} @inproceedings{bb121370, 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#TT117484"} @inproceedings{bb121371, 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#TT117485"} @inproceedings{bb121372, 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#TT117486"} @inproceedings{bb121373, 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#TT117487"} @inproceedings{bb121374, 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#TT117488"} @inproceedings{bb121375, 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#TT117489"} @inproceedings{bb121376, 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#TT117490"} @inproceedings{bb121377, 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#TT117491"} @inproceedings{bb121378, 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#TT117492"} @inproceedings{bb121379, 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#TT117493"} @inproceedings{bb121380, 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#TT117494"} @inproceedings{bb121381, 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#TT117495"} @inproceedings{bb121382, 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#TT117496"} @inproceedings{bb121383, 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#TT117497"} @inproceedings{bb121384, 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#TT117498"} @inproceedings{bb121385, 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#TT117499"} @inproceedings{bb121386, 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#TT117500"} @inproceedings{bb121387, 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#TT117501"} @inproceedings{bb121388, 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#TT117502"} @inproceedings{bb121389, 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#TT117503"} @inproceedings{bb121390, 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#TT117504"} @inproceedings{bb121391, 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#TT117505"} @inproceedings{bb121392, 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#TT117506"} @inproceedings{bb121393, AUTHOR = "Cetinic, E.", TITLE = "Iconographic Image Captioning for Artworks", BOOKTITLE = FAPER20, YEAR = "2020", PAGES = "502-516", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117507"} @inproceedings{bb121394, 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#TT117508"} @inproceedings{bb121395, 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#TT117509"} @inproceedings{bb121396, 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#TT117510"} @inproceedings{bb121397, 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#TT117511"} @inproceedings{bb121398, 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#TT117512"} @inproceedings{bb121399, 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#TT117513"}