@article{bb121500, AUTHOR = "Wu, C.L. and Wei, Y.W. and Chu, X.L. and Su, F. and Wang, L.Q.", TITLE = "Modeling visual and word-conditional semantic attention for image captioning", JOURNAL = SP:IC, VOLUME = "67", YEAR = "2018", PAGES = "100-107", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117614"} @article{bb121501, AUTHOR = "Zhang, M. and Yang, Y. and Zhang, H. and Ji, Y. and Shen, H.T. and Chua, T.", TITLE = "More is Better: Precise and Detailed Image Captioning Using Online Positive Recall and Missing Concepts Mining", JOURNAL = IP, VOLUME = "28", YEAR = "2019", NUMBER = "1", MONTH = "January", PAGES = "32-44", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117615"} @article{bb121502, AUTHOR = "Gella, S. and Keller, F. and Lapata, M.", TITLE = "Disambiguating Visual Verbs", JOURNAL = PAMI, VOLUME = "41", YEAR = "2019", NUMBER = "2", MONTH = "February", PAGES = "311-322", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117616"} @article{bb121503, AUTHOR = "Xu, N. and Liu, A.A. and Liu, J. and Nie, W.Z. and Su, Y.T.", TITLE = "Scene graph captioner: Image captioning based on structural visual representation", JOURNAL = JVCIR, VOLUME = "58", YEAR = "2019", PAGES = "477-485", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117617"} @article{bb121504, AUTHOR = "He, X.W. and Shi, B.G. and Bai, X. and Xia, G.S. and Zhang, Z.X. and Dong, W.S.", TITLE = "Image Caption Generation with Part of Speech Guidance", JOURNAL = PRL, VOLUME = "119", YEAR = "2019", PAGES = "229-237", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117618"} @article{bb121505, AUTHOR = "Xiao, X.Y. and Wang, L.F. and Ding, K. and Xiang, S.M. and Pan, C.", TITLE = "Dense semantic embedding network for image captioning", JOURNAL = PR, VOLUME = "90", YEAR = "2019", PAGES = "285-296", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117619"} @article{bb121506, AUTHOR = "Zhang, X.R. and Wang, X. and Tang, X. and Zhou, H.Y. and Li, C.", TITLE = "Description Generation for Remote Sensing Images Using Attribute Attention Mechanism", JOURNAL = RS, VOLUME = "11", YEAR = "2019", NUMBER = "6", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117620"} @article{bb121507, AUTHOR = "Ding, S.T. and Qu, S. and Xi, Y.L. and Sangaiah, A.K. and Wan, S.H.", TITLE = "Image caption generation with high-level image features", JOURNAL = PRL, VOLUME = "123", YEAR = "2019", PAGES = "89-95", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117621"} @article{bb121508, AUTHOR = "Liu, X.X. and Xu, Q.Y. and Wang, N.", TITLE = "A survey on deep neural network-based image captioning", JOURNAL = VC, VOLUME = "35", YEAR = "2019", NUMBER = "3", MONTH = "March", PAGES = "445-470", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117622"} @article{bb121509, AUTHOR = "Hossain, M.Z. and Sohel, F. and Shiratuddin, M.F. and Laga, H.", TITLE = "A Comprehensive Survey of Deep Learning for Image Captioning", JOURNAL = Surveys, VOLUME = "51", YEAR = "2019", NUMBER = "6", MONTH = "February", PAGES = "Article No 118", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117623"} @article{bb121510, AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.", TITLE = "High-Quality Image Captioning With Fine-Grained and Semantic-Guided Visual Attention", JOURNAL = MultMed, VOLUME = "21", YEAR = "2019", NUMBER = "7", MONTH = "July", PAGES = "1681-1693", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117624"} @inproceedings{bb121511, AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.", TITLE = "Fine-Grained and Semantic-Guided Visual Attention for Image Captioning", BOOKTITLE = WACV18, YEAR = "2018", PAGES = "1709-1717", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117625"} @article{bb121512, AUTHOR = "Li, X. and Jiang, S.", TITLE = "Know More Say Less: Image Captioning Based on Scene Graphs", JOURNAL = MultMed, VOLUME = "21", YEAR = "2019", NUMBER = "8", MONTH = "August", PAGES = "2117-2130", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117626"} @article{bb121513, AUTHOR = "Sharif, N. and White, L. and Bennamoun, M. and Liu, W. and Shah, S.A.A.", TITLE = "LCEval: Learned Composite Metric for Caption Evaluation", JOURNAL = IJCV, VOLUME = "127", YEAR = "2019", NUMBER = "10", MONTH = "October", PAGES = "1586-1610", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117627"} @article{bb121514, AUTHOR = "Zhang, Z.Y. and Diao, W.H. and Zhang, W.K. and Yan, M.L. and Gao, X. and Sun, X.", TITLE = "LAM: Remote Sensing Image Captioning with Label-Attention Mechanism", JOURNAL = RS, VOLUME = "11", YEAR = "2019", NUMBER = "20", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117628"} @article{bb121515, AUTHOR = "Fu, K. and Li, Y. and Zhang, W.K. and Yu, H.F. and Sun, X.", TITLE = "Boosting Memory with a Persistent Memory Mechanism for Remote Sensing Image Captioning", JOURNAL = RS, VOLUME = "12", YEAR = "2020", NUMBER = "11", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117629"} @article{bb121516, AUTHOR = "Tan, J.H. and Chan, C.S. and Chuah, J.H.", TITLE = "COMIC: Toward A Compact Image Captioning Model With Attention", JOURNAL = MultMed, VOLUME = "21", YEAR = "2019", NUMBER = "10", MONTH = "October", PAGES = "2686-2696", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117630"} @article{bb121517, AUTHOR = "Zhou, L. and Zhang, Y. and Jiang, Y. and Zhang, T. and Fan, W.", TITLE = "Re-Caption: Saliency-Enhanced Image Captioning Through Two-Phase Learning", JOURNAL = IP, VOLUME = "29", YEAR = "2020", NUMBER = "1", PAGES = "694-709", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117631"} @article{bb121518, AUTHOR = "Yang, L. and Hu, H.F.", TITLE = "Visual Skeleton and Reparative Attention for Part-of-Speech image captioning system", JOURNAL = CVIU, VOLUME = "189", YEAR = "2019", PAGES = "102819", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117632"} @article{bb121519, AUTHOR = "Wang, J.B. and Wang, W. and Wang, L. and Wang, Z.Y. and Feng, D.D. and Tan, T.N.", TITLE = "Learning Visual Relationship and Context-Aware Attention for Image Captioning", JOURNAL = PR, VOLUME = "98", YEAR = "2020", PAGES = "107075", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117633"} @article{bb121520, AUTHOR = "Xiao, X. and Wang, L. and Ding, K. and Xiang, S. and Pan, C.", TITLE = "Deep Hierarchical Encoder-Decoder Network for Image Captioning", JOURNAL = MultMed, VOLUME = "21", YEAR = "2019", NUMBER = "11", MONTH = "November", PAGES = "2942-2956", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117634"} @article{bb121521, AUTHOR = "Jiang, T. and Zhang, Z. and Yang, Y.", TITLE = "Modeling coverage with semantic embedding for image caption generation", JOURNAL = VC, VOLUME = "35", YEAR = "2018", NUMBER = "11", MONTH = "November", PAGES = "1655-1665", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117635"} @article{bb121522, AUTHOR = "Lu, X. and Wang, B. and Zheng, X.", TITLE = "Sound Active Attention Framework for Remote Sensing Image Captioning", JOURNAL = GeoRS, VOLUME = "58", YEAR = "2020", NUMBER = "3", MONTH = "March", PAGES = "1985-2000", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117636"} @article{bb121523, AUTHOR = "Li, Y.Y. and Fang, S.K. and Jiao, L.C. and Liu, R.J. and Shang, R.H.", TITLE = "A Multi-Level Attention Model for Remote Sensing Image Captions", JOURNAL = RS, VOLUME = "12", YEAR = "2020", NUMBER = "6", PAGES = "xx-yy", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117637"} @article{bb121524, AUTHOR = "Chen, X.H. and Zhang, M.X. and Wang, Z. and Zuo, L. and Li, B. and Yang, Y.", TITLE = "Leveraging unpaired out-of-domain data for image captioning", JOURNAL = PRL, VOLUME = "132", YEAR = "2020", PAGES = "132-140", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117638"} @article{bb121525, AUTHOR = "Xu, N. and Zhang, H. and Liu, A. and Nie, W. and Su, Y. and Nie, J. and Zhang, Y.", TITLE = "Multi-Level Policy and Reward-Based Deep Reinforcement Learning Framework for Image Captioning", JOURNAL = MultMed, VOLUME = "22", YEAR = "2020", NUMBER = "5", MONTH = "May", PAGES = "1372-1383", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117639"} @article{bb121526, AUTHOR = "Guo, L. and Liu, J. and Lu, S. and Lu, H.", TITLE = "Show, Tell, and Polish: Ruminant Decoding for Image Captioning", JOURNAL = MultMed, VOLUME = "22", YEAR = "2020", NUMBER = "8", MONTH = "August", PAGES = "2149-2162", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117640"} @article{bb121527, AUTHOR = "Feng, Q. and Wu, Y. and Fan, H. and Yan, C. and Xu, M. and Yang, Y.", TITLE = "Cascaded Revision Network for Novel Object Captioning", JOURNAL = CirSysVideo, VOLUME = "30", YEAR = "2020", NUMBER = "10", MONTH = "October", PAGES = "3413-3421", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117641"} @article{bb121528, AUTHOR = "Wei, H.Y. and Li, Z.X. and Zhang, C.L. and Ma, H.F.", TITLE = "The synergy of double attention: Combine sentence-level and word-level attention for image captioning", JOURNAL = CVIU, VOLUME = "201", YEAR = "2020", PAGES = "103068", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117642"} @article{bb121529, AUTHOR = "Shilpa, M. and He, J. and Zhao, Y.J. and Sun, B. and Yu, L.J.", TITLE = "Feedback evaluations to promote image captioning", JOURNAL = IET-IPR, VOLUME = "14", YEAR = "2020", NUMBER = "13", MONTH = "November", PAGES = "3021-3027", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117643"} @article{bb121530, AUTHOR = "Liu, H. and Zhang, S. and Lin, K. and Wen, J. and Li, J. and Hu, X.", TITLE = "Vocabulary-Wide Credit Assignment for Training Image Captioning Models", JOURNAL = IP, VOLUME = "30", YEAR = "2021", PAGES = "2450-2460", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117644"} @article{bb121531, AUTHOR = "Xu, N. and Tian, H.S. and Wang, Y.H. and Nie, W.Z. and Song, D. and Liu, A.A. and Liu, W.", TITLE = "Coupled-dynamic learning for vision and language: Exploring Interaction between different tasks", JOURNAL = PR, VOLUME = "113", YEAR = "2021", PAGES = "107829", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117645"} @article{bb121532, AUTHOR = "Yang, L. and Wang, H. and Tang, P. and Li, Q.", TITLE = "CaptionNet: A Tailor-made Recurrent Neural Network for Generating Image Descriptions", JOURNAL = MultMed, VOLUME = "23", YEAR = "2021", PAGES = "835-845", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117646"} @article{bb121533, AUTHOR = "Liu, A.A. and Wang, Y.H. and Xu, N. and Liu, S. and Li, X.", TITLE = "Scene-Graph-Guided message passing network for dense captioning", JOURNAL = PRL, VOLUME = "145", YEAR = "2021", PAGES = "187-193", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117647"} @article{bb121534, AUTHOR = "Zhang, L. and Zhang, Y.S. and Zhao, X. and Zou, Z.X.", TITLE = "Image captioning via proximal policy optimization", JOURNAL = IVC, VOLUME = "108", YEAR = "2021", PAGES = "104126", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117648"} @article{bb121535, AUTHOR = "Ji, J.Z. and Du, Z.R. and Zhang, X.D.", TITLE = "Divergent-convergent attention for image captioning", JOURNAL = PR, VOLUME = "115", YEAR = "2021", PAGES = "107928", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117649"} @article{bb121536, AUTHOR = "Wei, Y.W. and Wu, C.L. and Jia, Z.Y. and Hu, X. and Guo, S. and Shi, H.T.", TITLE = "Past is important: Improved image captioning by looking back in time", JOURNAL = SP:IC, VOLUME = "94", YEAR = "2021", PAGES = "116183", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117650"} @article{bb121537, AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.", TITLE = "Exploring region relationships implicitly: Image captioning with visual relationship attention", JOURNAL = IVC, VOLUME = "109", YEAR = "2021", PAGES = "104146", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117651"} @article{bb121538, AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.", TITLE = "Exploring Pairwise Relationships Adaptively From Linguistic Context in Image Captioning", JOURNAL = MultMed, VOLUME = "24", YEAR = "2022", PAGES = "3101-3113", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117652"} @article{bb121539, AUTHOR = "Li, X.L. and Zhang, X.T. and Huang, W. and Wang, Q.", TITLE = "Truncation Cross Entropy Loss for Remote Sensing Image Captioning", JOURNAL = GeoRS, VOLUME = "59", YEAR = "2021", NUMBER = "6", MONTH = "June", PAGES = "5246-5257", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117653"} @article{bb121540, AUTHOR = "Zhong, X. and Nie, G.Z. and Huang, W.X. and Liu, W.X. and Ma, B. and Lin, C.W.", TITLE = "Attention-guided image captioning with adaptive global and local feature fusion", JOURNAL = JVCIR, VOLUME = "78", YEAR = "2021", PAGES = "103138", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117654"} @article{bb121541, AUTHOR = "Sumbul, G. and Nayak, S. and Demir, B.", TITLE = "SD-RSIC: Summarization-Driven Deep Remote Sensing Image Captioning", JOURNAL = GeoRS, VOLUME = "59", YEAR = "2021", NUMBER = "8", MONTH = "August", PAGES = "6922-6934", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117655"} @article{bb121542, AUTHOR = "Wu, J. and Chen, T.S. and Wu, H.F. and Yang, Z. and Luo, G.C. and Lin, L.", TITLE = "Fine-Grained Image Captioning With Global-Local Discriminative Objective", JOURNAL = MultMed, VOLUME = "23", YEAR = "2021", PAGES = "2413-2427", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117656"} @article{bb121543, AUTHOR = "Wu, L.X. and Xu, M. and Sang, L. and Yao, T. and Mei, T.", TITLE = "Noise Augmented Double-Stream Graph Convolutional Networks for Image Captioning", JOURNAL = CirSysVideo, VOLUME = "31", YEAR = "2021", NUMBER = "8", MONTH = "August", PAGES = "3118-3127", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117657"} @article{bb121544, AUTHOR = "Nivedita, M. and Chandrashekar, P. and Mahapatra, S. and Phamila, Y.A.V. and Selvaperumal, S.K.", TITLE = "Image Captioning for Video Surveillance System using Neural Networks", JOURNAL = IJIG, VOLUME = "21", YEAR = "2021", NUMBER = "4", MONTH = "October", PAGES = "2150044", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117658"} @article{bb121545, AUTHOR = "Wang, Q. and Huang, W. and Zhang, X.T. and Li, X.L.", TITLE = "Word-Sentence Framework for Remote Sensing Image Captioning", JOURNAL = GeoRS, VOLUME = "59", YEAR = "2021", NUMBER = "12", MONTH = "December", PAGES = "10532-10543", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117659"} @article{bb121546, AUTHOR = "Wan, B.Y. and Jiang, W.H. and Fang, Y.M. and Zhu, M.W. and Li, Q. and Liu, Y.", TITLE = "Revisiting image captioning via maximum discrepancy competition", JOURNAL = PR, VOLUME = "122", YEAR = "2022", PAGES = "108358", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117660"} @article{bb121547, AUTHOR = "Chen, T.Y. and Li, Z.X. and Wu, J.L. and Ma, H.F. and Su, B.P.", TITLE = "Improving image captioning with Pyramid Attention and SC-GAN", JOURNAL = IVC, VOLUME = "117", YEAR = "2022", PAGES = "104340", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117661"} @article{bb121548, AUTHOR = "Zhou, Y.J. and Long, J.F. and Xu, S.P. and Shang, L.", TITLE = "Attribute-driven image captioning via soft-switch pointer", JOURNAL = PRL, VOLUME = "152", YEAR = "2021", PAGES = "34-41", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117662"} @article{bb121549, AUTHOR = "Zha, Z.J. and Liu, D. and Zhang, H.W. and Zhang, Y.D. and Wu, F.", TITLE = "Context-Aware Visual Policy Network for Fine-Grained Image Captioning", JOURNAL = PAMI, VOLUME = "44", YEAR = "2022", NUMBER = "2", MONTH = "February", PAGES = "710-722", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117663"} @article{bb121550, AUTHOR = "Wang, Q.Z. and Wan, J. and Chan, A.B.", TITLE = "On Diversity in Image Captioning: Metrics and Methods", JOURNAL = PAMI, VOLUME = "44", YEAR = "2022", NUMBER = "2", MONTH = "February", PAGES = "1035-1049", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117664"} @inproceedings{bb121551, AUTHOR = "Wang, J. and Xu, W.J. and Wang, Q.Z. and Chan, A.B.", TITLE = "Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets", BOOKTITLE = ECCV20, YEAR = "2020", PAGES = "I:370-386", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117665"} @article{bb121552, AUTHOR = "Luo, G.F. and Cheng, L.J. and Jing, C. and Zhao, C. and Song, G.Z.", TITLE = "A thorough review of models, evaluation metrics, and datasets on image captioning", JOURNAL = IET-IPR, VOLUME = "16", YEAR = "2022", NUMBER = "2", PAGES = "311-332", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117666"} @article{bb121553, AUTHOR = "Ben, H.X. and Pan, Y.W. and Li, Y. and Yao, T. and Hong, R.C. and Wang, M. and Mei, T.", TITLE = "Unpaired Image Captioning With semantic-Constrained Self-Learning", JOURNAL = MultMed, VOLUME = "24", YEAR = "2022", PAGES = "904-916", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117667"} @article{bb121554, AUTHOR = "Song, P.P. and Guo, D. and Zhou, J.X. and Xu, M.L. and Wang, M.", TITLE = "Memorial GAN With Joint Semantic Optimization for Unpaired Image Captioning", JOURNAL = Cyber, VOLUME = "53", YEAR = "2023", NUMBER = "7", MONTH = "July", PAGES = "4388-4399", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117668"} @inproceedings{bb121555, AUTHOR = "Li, Y. and Yao, T. and Pan, Y.W. and Chao, H.Y. and Mei, T.", TITLE = "Pointing Novel Objects in Image Captioning", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "12489-12498", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117669"} @article{bb121556, AUTHOR = "Liu, M.F. and Hu, H.J. and Li, L.J. and Yu, Y. and Guan, W.L.", TITLE = "Chinese Image Caption Generation via Visual Attention and Topic Modeling", JOURNAL = Cyber, VOLUME = "52", YEAR = "2022", NUMBER = "2", MONTH = "February", PAGES = "1247-1257", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117670"} @article{bb121557, AUTHOR = "Yang, Q.Q. and Ni, Z. and Ren, P.", TITLE = "Meta captioning: A meta learning based remote sensing image captioning framework", JOURNAL = PandRS, VOLUME = "186", YEAR = "2022", PAGES = "190-200", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117671"} @article{bb121558, AUTHOR = "Yang, X. and Zhang, H.W. and Cai, J.F.", TITLE = "Auto-Encoding and Distilling Scene Graphs for Image Captioning", JOURNAL = PAMI, VOLUME = "44", YEAR = "2022", NUMBER = "5", MONTH = "May", PAGES = "2313-2327", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117672"} @article{bb121559, AUTHOR = "Yang, X. and Zhang, H.W. and Cai, J.F.", TITLE = "Deconfounded Image Captioning: A Causal Retrospect", JOURNAL = PAMI, VOLUME = "45", YEAR = "2023", NUMBER = "11", MONTH = "November", PAGES = "12996-13010", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117673"} @inproceedings{bb121560, AUTHOR = "Yang, X. and Tang, K. and Zhang, H.W. and Cai, J.F.", TITLE = "Auto-Encoding Scene Graphs for Image Captioning", BOOKTITLE = CVPR19, YEAR = "2019", PAGES = "10677-10686", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117674"} @article{bb121561, AUTHOR = "Yang, Z.P. and Wang, P.B. and Chu, T.S. and Yang, J.", TITLE = "Human-Centric Image Captioning", JOURNAL = PR, VOLUME = "126", YEAR = "2022", PAGES = "108545", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117675"} @article{bb121562, AUTHOR = "Li, X. and Zhang, W.K. and Sun, X. and Gao, X.", TITLE = "Without detection: Two-step clustering features with local-global attention for image captioning", JOURNAL = IET-CV, VOLUME = "16", YEAR = "2022", NUMBER = "3", PAGES = "280-294", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117676"} @article{bb121563, AUTHOR = "Yu, L.T. and Zhang, J. and Wu, Q.", TITLE = "Dual Attention on Pyramid Feature Maps for Image Captioning", JOURNAL = MultMed, VOLUME = "24", YEAR = "2022", NUMBER = "2022", PAGES = "1775-1786", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117677"} @article{bb121564, AUTHOR = "Zhang, M. and Chen, J.X. and Li, P.F. and Jiang, M. and Zhou, Z.", TITLE = "Topic scene graphs for image captioning", JOURNAL = IET-CV, VOLUME = "16", YEAR = "2022", NUMBER = "4", PAGES = "364-375", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117678"} @article{bb121565, AUTHOR = "Yu, Q. and Zhang, C.X. and Weng, L. and Xiang, S.M. and Pan, C.H.", TITLE = "Scene captioning with deep fusion of images and point clouds", JOURNAL = PRL, VOLUME = "158", YEAR = "2022", PAGES = "9-15", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117679"} @article{bb121566, AUTHOR = "Chaudhari, C.P. and Devane, S.", TITLE = "Improved Framework using Rider Optimization Algorithm for Precise Image Caption Generation", JOURNAL = IJIG, VOLUME = "22", YEAR = "2022", NUMBER = "2", MONTH = "April", PAGES = "2250021", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117680"} @article{bb121567, 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#TT117681"} @article{bb121568, 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#TT117682"} @article{bb121569, 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#TT117683"} @article{bb121570, 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#TT117684"} @article{bb121571, 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#TT117685"} @article{bb121572, 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#TT117686"} @article{bb121573, 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#TT117687"} @article{bb121574, 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#TT117688"} @article{bb121575, 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#TT117689"} @article{bb121576, 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#TT117690"} @article{bb121577, 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#TT117691"} @inproceedings{bb121578, 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#TT117692"} @article{bb121579, 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#TT117693"} @article{bb121580, 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#TT117694"} @article{bb121581, 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#TT117695"} @article{bb121582, 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#TT117696"} @article{bb121583, 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#TT117697"} @article{bb121584, 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#TT117698"} @article{bb121585, 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#TT117699"} @article{bb121586, 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#TT117700"} @article{bb121587, 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#TT117701"} @article{bb121588, 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#TT117702"} @article{bb121589, 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#TT117703"} @article{bb121590, 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#TT117704"} @article{bb121591, 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#TT117705"} @article{bb121592, 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#TT117706"} @article{bb121593, 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#TT117707"} @article{bb121594, 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#TT117708"} @inproceedings{bb121595, 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#TT117709"} @article{bb121596, 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#TT117710"} @article{bb121597, AUTHOR = "Liu, A.A. and Zhai, Y.C. and Xu, N. and Tian, H. and Nie, W.Z. and Zhang, Y.D.", TITLE = "Event-Aware Retrospective Learning for Knowledge-Based Image Captioning", JOURNAL = MultMed, VOLUME = "26", YEAR = "2024", PAGES = "4898-4911", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117711"} @article{bb121598, AUTHOR = "Song, L.F. and Li, F. and Wang, Y. and Liu, Y. and Wang, Y. and Xiang, S.M.", TITLE = "Image captioning: Semantic selection unit with stacked residual attention", JOURNAL = IVC, VOLUME = "144", YEAR = "2024", PAGES = "104965", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117712"} @article{bb121599, AUTHOR = "Ajankar, S. and Dutta, T.", TITLE = "Image-Relevant Entities Knowledge-Aware News Image Captioning", JOURNAL = MultMedMag, VOLUME = "31", YEAR = "2024", NUMBER = "1", MONTH = "January", PAGES = "88-98", BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117713"}