@article{bb114700,
AUTHOR = "Chaudhary, C. and Goyal, P. and Prasad, D.N. and Chen, Y.P.",
TITLE = "Enhancing the Quality of Image Tagging Using a Visio-Textual
Knowledge Base",
JOURNAL = MultMed,
VOLUME = "22",
YEAR = "2020",
NUMBER = "4",
MONTH = "April",
PAGES = "897-911",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110925"}
@article{bb114701,
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#TT110926"}
@article{bb114702,
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#TT110927"}
@article{bb114703,
AUTHOR = "Deng, Z.R. and Jiang, Z.Q. and Lan, R. and Huang, W.M. and Luo, X.N.",
TITLE = "Image captioning using DenseNet network and adaptive attention",
JOURNAL = SP:IC,
VOLUME = "85",
YEAR = "2020",
PAGES = "115836",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110928"}
@article{bb114704,
AUTHOR = "Ji, J. and Xu, C. and Zhang, X. and Wang, B. and Song, X.",
TITLE = "Spatio-Temporal Memory Attention for Image Captioning",
JOURNAL = IP,
VOLUME = "29",
YEAR = "2020",
PAGES = "7615-7628",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110929"}
@article{bb114705,
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#TT110930"}
@article{bb114706,
AUTHOR = "Khatchatoorian, A.G. and Jamzad, M.",
TITLE = "Architecture to improve the accuracy of automatic image annotation
systems",
JOURNAL = IET-CV,
VOLUME = "14",
YEAR = "2020",
NUMBER = "5",
MONTH = "August",
PAGES = "214-223",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110931"}
@article{bb114707,
AUTHOR = "Theodosiou, Z. and Tsapatsoulis, N.",
TITLE = "Image annotation: the effects of content, lexicon and annotation method",
JOURNAL = MultInfoRetr,
VOLUME = "9",
YEAR = "2020",
NUMBER = "3",
MONTH = "September",
PAGES = "191-203",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110932"}
@article{bb114708,
AUTHOR = "Che, W.B. and Fan, X.P. and Xiong, R.Q. and Zhao, D.B.",
TITLE = "Visual Relationship Embedding Network for Image Paragraph Generation",
JOURNAL = MultMed,
VOLUME = "22",
YEAR = "2020",
NUMBER = "9",
MONTH = "September",
PAGES = "2307-2320",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110933"}
@article{bb114709,
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#TT110934"}
@article{bb114710,
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#TT110935"}
@article{bb114711,
AUTHOR = "Shilpa, M. and He, J. and Zhao, Y. 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#TT110936"}
@article{bb114712,
AUTHOR = "Zhang, J. and Mei, K. and Zheng, Y. and Fan, J.",
TITLE = "Integrating Part of Speech Guidance for Image Captioning",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "92-104",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110937"}
@inproceedings{bb114713,
AUTHOR = "Sharif, N. and Jalwana, M.A.A.K. and Bennamoun, M. and Liu, W. and Shah, S.A.A.",
TITLE = "Leveraging Linguistically-aware Object Relations and NASNet for Image
Captioning",
BOOKTITLE = IVCNZ20,
YEAR = "2020",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110938"}
@article{bb114714,
AUTHOR = "Gouthaman, K.V. and Nambiar, A. and Srinivas, K.S. and Mittal, A.",
TITLE = "Linguistically-aware attention for reducing the semantic gap in
vision-language tasks",
JOURNAL = PR,
VOLUME = "112",
YEAR = "2021",
PAGES = "107812",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110939"}
@article{bb114715,
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#TT110940"}
@article{bb114716,
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#TT110941"}
@article{bb114717,
AUTHOR = "Zhang, J. and Li, K.K. and Wang, Z.",
TITLE = "Parallel-fusion LSTM with synchronous semantic and visual information
for image captioning",
JOURNAL = JVCIR,
VOLUME = "75",
YEAR = "2021",
PAGES = "103044",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110942"}
@article{bb114718,
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#TT110943"}
@article{bb114719,
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#TT110944"}
@article{bb114720,
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#TT110945"}
@article{bb114721,
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#TT110946"}
@article{bb114722,
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#TT110947"}
@article{bb114723,
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#TT110948"}
@article{bb114724,
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#TT110949"}
@article{bb114725,
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#TT110950"}
@article{bb114726,
AUTHOR = "He, S. and Lu, Y.Y. and Chen, S.N.",
TITLE = "Image Captioning Algorithm Based on Multi-Branch CNN and Bi-LSTM",
JOURNAL = IEICE,
VOLUME = "E104-D",
YEAR = "2021",
NUMBER = "7",
MONTH = "July",
PAGES = "941-947",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110951"}
@article{bb114727,
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#TT110952"}
@article{bb114728,
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#TT110953"}
@article{bb114729,
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#TT110954"}
@article{bb114730,
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#TT110955"}
@article{bb114731,
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#TT110956"}
@article{bb114732,
AUTHOR = "Haghighi, F. and Taher, M.R.H. and Zhou, Z.W. and Gotway, M.B. and Liang, J.M.",
TITLE = "Transferable Visual Words: Exploiting the Semantics of Anatomical
Patterns for Self-Supervised Learning",
JOURNAL = MedImg,
VOLUME = "40",
YEAR = "2021",
NUMBER = "10",
MONTH = "October",
PAGES = "2857-2868",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110957"}
@article{bb114733,
AUTHOR = "Wang, Q. and Huang, W. and Zhang, X. 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#TT110958"}
@article{bb114734,
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#TT110959"}
@article{bb114735,
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#TT110960"}
@article{bb114736,
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#TT110961"}
@article{bb114737,
AUTHOR = "Zha, Z.J. and Liu, D. and Zhang, H. 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#TT110962"}
@article{bb114738,
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#TT110963"}
@inproceedings{bb114739,
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#TT110964"}
@article{bb114740,
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#TT110965"}
@article{bb114741,
AUTHOR = "Ben, H.X. and Pan, Y. and Li, Y. and Yao, T. and Hong, R. 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#TT110966"}
@inproceedings{bb114742,
AUTHOR = "Li, Y. and Yao, T. and Pan, Y. 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#TT110967"}
@article{bb114743,
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#TT110968"}
@article{bb114744,
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#TT110969"}
@article{bb114745,
AUTHOR = "Yang, X. and Zhang, H. 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#TT110970"}
@inproceedings{bb114746,
AUTHOR = "Yang, X. and Tang, K. and Zhang, H. 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#TT110971"}
@article{bb114747,
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#TT110972"}
@article{bb114748,
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#TT110973"}
@article{bb114749,
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#TT110974"}
@article{bb114750,
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#TT110975"}
@article{bb114751,
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#TT110976"}
@article{bb114752,
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#TT110977"}
@article{bb114753,
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#TT110978"}
@article{bb114754,
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#TT110979"}
@article{bb114755,
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#TT110980"}
@article{bb114756,
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#TT110981"}
@article{bb114757,
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#TT110982"}
@article{bb114758,
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#TT110983"}
@article{bb114759,
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#TT110984"}
@article{bb114760,
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#TT110985"}
@article{bb114761,
AUTHOR = "Kim, D.J. and Oh, T.H. and Choi, J. and Kweon, I.S.",
TITLE = "Dense Relational Image Captioning via Multi-Task Triple-Stream
Networks",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "11",
MONTH = "November",
PAGES = "7348-7362",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110986"}
@inproceedings{bb114762,
AUTHOR = "Kim, D.J. and Choi, J. and Oh, T.H. and Kweon, I.S.",
TITLE = "Dense Relational Captioning: Triple-Stream Networks for
Relationship-Based Captioning",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6264-6273",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110987"}
@article{bb114763,
AUTHOR = "Cao, S. and An, G. and Zheng, Z.X. and Wang, Z.Y.",
TITLE = "Vision-Enhanced and Consensus-Aware Transformer for Image Captioning",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "10",
MONTH = "October",
PAGES = "7005-7018",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110988"}
@article{bb114764,
AUTHOR = "Nguyen, T.S. and Fernando, B.",
TITLE = "Effective Multimodal Encoding for Image Paragraph Captioning",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "6381-6395",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110989"}
@article{bb114765,
AUTHOR = "Jiang, W.T. and Zhou, W. and Hu, H.F.",
TITLE = "Double-Stream Position Learning Transformer Network for Image
Captioning",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "11",
MONTH = "November",
PAGES = "7706-7718",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110990"}
@article{bb114766,
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#TT110991"}
@article{bb114767,
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#TT110992"}
@article{bb114768,
AUTHOR = "Hu, J.T. and Yang, Y. and Yao, L. and An, Y.Z. and Pan, L.",
TITLE = "Position-guided transformer for image captioning",
JOURNAL = IVC,
VOLUME = "128",
YEAR = "2022",
PAGES = "104575",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110993"}
@article{bb114769,
AUTHOR = "Wang, Z.G. and Shi, S. and Zhai, Z.R. and Wu, Y. and Yang, R.",
TITLE = "ArCo: Attention-reinforced transformer with contrastive learning for
image captioning",
JOURNAL = IVC,
VOLUME = "128",
YEAR = "2022",
PAGES = "104570",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110994"}
@article{bb114770,
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#TT110995"}
@article{bb114771,
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#TT110996"}
@inproceedings{bb114772,
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#TT110997"}
@article{bb114773,
AUTHOR = "Li, Z.X. and Wei, J. and Huang, F.C. and Ma, H.F.",
TITLE = "Modeling graph-structured contexts for image captioning",
JOURNAL = IVC,
VOLUME = "129",
YEAR = "2023",
PAGES = "104591",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT110998"}
@article{bb114774,
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#TT110999"}
@article{bb114775,
AUTHOR = "Duan, Y.Q. and Wang, Z. and Li, Y. and Wang, J.Y.",
TITLE = "Cross-domain multi-style merge for image captioning",
JOURNAL = CVIU,
VOLUME = "228",
YEAR = "2023",
PAGES = "103617",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111000"}
@article{bb114776,
AUTHOR = "Wu, X.X. and Li, T.",
TITLE = "Sentimental Visual Captioning using Multimodal Transformer",
JOURNAL = IJCV,
VOLUME = "131",
YEAR = "2023",
NUMBER = "1",
MONTH = "January",
PAGES = "1073-1090",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111001"}
@article{bb114777,
AUTHOR = "Ma, Y. 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#TT111002"}
@inproceedings{bb114778,
AUTHOR = "Wang, T.J.J. and Laaksonen, J. and Langer, T. and Arponen, H. and Bishop, T.E.",
TITLE = "Learning by Hallucinating:
Vision-Language Pre-training with Weak Supervision",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "1073-1083",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111003"}
@inproceedings{bb114779,
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#TT111004"}
@inproceedings{bb114780,
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#TT111005"}
@inproceedings{bb114781,
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#TT111006"}
@inproceedings{bb114782,
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#TT111007"}
@inproceedings{bb114783,
AUTHOR = "Lou, L.S. and Lu, K. and Xue, J.",
TITLE = "Improved Transformer with Parallel Encoders for Image Captioning",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "4072-4075",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111008"}
@inproceedings{bb114784,
AUTHOR = "Wang, Y.H. and Shang, L.",
TITLE = "Generating Spatial-aware Captions for TextCaps",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "379-385",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111009"}
@inproceedings{bb114785,
AUTHOR = "Feng, Y. and Maeda, K. and Ogawa, T. and Haseyama, M.",
TITLE = "Human-Centric Image Retrieval with Gaze-Based Image Captioning",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "3828-3832",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111010"}
@inproceedings{bb114786,
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#TT111011"}
@inproceedings{bb114787,
AUTHOR = "Yang, X. and Wang, Y. and Chen, H. and Li, J.",
TITLE = "CSTNET: Enhancing Global-To-Local Interactions for Image Captioning",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "1861-1865",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111012"}
@inproceedings{bb114788,
AUTHOR = "Hu, W.Z. and Wang, L. and Xu, L.",
TITLE = "Spatial-Semantic Attention for Grounded Image Captioning",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "61-65",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111013"}
@inproceedings{bb114789,
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#TT111014"}
@inproceedings{bb114790,
AUTHOR = "Nguyen, V.Q. and Suganuma, M. and Okatani, T.",
TITLE = "GRIT: Faster and Better Image Captioning Transformer Using Dual Visual
Features",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:167-184",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111015"}
@inproceedings{bb114791,
AUTHOR = "Wang, Z. and Chen, L. and Ma, W. 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#TT111016"}
@inproceedings{bb114792,
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#TT111017"}
@inproceedings{bb114793,
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#TT111018"}
@inproceedings{bb114794,
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#TT111019"}
@inproceedings{bb114795,
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#TT111020"}
@inproceedings{bb114796,
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#TT111021"}
@inproceedings{bb114797,
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#TT111022"}
@inproceedings{bb114798,
AUTHOR = "Barraco, M. and Cornia, M. and Cascianelli, S. and Baraldi, L. and Cucchiara, R.",
TITLE = "The Unreasonable Effectiveness of CLIP Features for Image Captioning:
An Experimental Analysis",
BOOKTITLE = MULA22,
YEAR = "2022",
PAGES = "4661-4669",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT111023"}
@inproceedings{bb114799,
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#TT111024"}
Last update:Mar 27, 2023 at 09:32:08