@inproceedings{bb121500,
        AUTHOR = "Wu, B.Y. and Jia, F. and Liu, W. and Ghanem, B.",
        TITLE = "Diverse Image Annotation",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6194-6202",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117614"}

@inproceedings{bb121501,
        AUTHOR = "Krause, J. and Johnson, J. and Krishna, R. and Fei Fei, L.",
        TITLE = "A Hierarchical Approach for Generating Descriptive Image Paragraphs",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3337-3345",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117615"}

@inproceedings{bb121502,
        AUTHOR = "Vedantam, R. and Bengio, S. and Murphy, K. and Parikh, D. and Chechik, G.",
        TITLE = "Context-Aware Captions from Context-Agnostic Supervision",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1070-1079",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117616"}

@inproceedings{bb121503,
        AUTHOR = "Gan, Z. and Gan, C. and He, X. and Pu, Y. and Tran, K. and Gao, J. and Carin, L. and Deng, L.",
        TITLE = "Semantic Compositional Networks for Visual Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1141-1150",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117617"}

@inproceedings{bb121504,
        AUTHOR = "Ren, Z. and Wang, X. and Zhang, N. and Lv, X. and Li, L.J.",
        TITLE = "Deep Reinforcement Learning-Based Image Captioning with Embedding
Reward",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1151-1159",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117618"}

@inproceedings{bb121505,
        AUTHOR = "Rennie, S.J. and Marcheret, E. and Mroueh, Y. and Ross, J. and Goel, V.",
        TITLE = "Self-Critical Sequence Training for Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1179-1195",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117619"}

@inproceedings{bb121506,
        AUTHOR = "Yang, L. and Tang, K. and Yang, J. and Li, L.J.",
        TITLE = "Dense Captioning with Joint Inference and Visual Context",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1978-1987",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117620"}

@inproceedings{bb121507,
        AUTHOR = "Lu, J. and Xiong, C. and Parikh, D. and Socher, R.",
        TITLE = "Knowing When to Look: Adaptive Attention via a Visual Sentinel for
Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3242-3250",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117621"}

@inproceedings{bb121508,
        AUTHOR = "Yao, T. and Pan, Y. and Li, Y. and Mei, T.",
        TITLE = "Incorporating Copying Mechanism in Image Captioning for Learning
Novel Objects",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "5263-5271",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117622"}

@inproceedings{bb121509,
        AUTHOR = "Chen, L. and Zhang, H. and Xiao, J. and Nie, L. and Shao, J. and Liu, W. and Chua, T.S.",
        TITLE = "SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks
for Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6298-6306",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117623"}

@inproceedings{bb121510,
        AUTHOR = "Sun, Q. and Lee, S. and Batra, D.",
        TITLE = "Bidirectional Beam Search: Forward-Backward Inference in Neural
Sequence Models for Fill-in-the-Blank Image Captioning",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "7215-7223",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117624"}

@inproceedings{bb121511,
        AUTHOR = "Wang, Y. and Lin, Z. and Shen, X. and Cohen, S. and Cottrell, G.W.",
        TITLE = "Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "7378-7387",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117625"}

@inproceedings{bb121512,
        AUTHOR = "Zanfir, M. and Marinoiu, E. and Sminchisescu, C.",
        TITLE = "Spatio-Temporal Attention Models for Grounded Video Captioning",
        BOOKTITLE = ACCV16,
        YEAR = "2016",
        PAGES = "IV: 104-119",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117626"}

@inproceedings{bb121513,
        AUTHOR = "Chen, T.H. and Zeng, K.H. and Hsu, W.T. and Sun, M.",
        TITLE = "Video Captioning via Sentence Augmentation and Spatio-Temporal
Attention",
        BOOKTITLE = Assist16,
        YEAR = "2016",
        PAGES = "I: 269-286",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117627"}

@inproceedings{bb121514,
        AUTHOR = "Weiland, L. and Hulpus, I. and Ponzetto, S.P. and Dietz, L.",
        TITLE = "Using Object Detection, NLP, and Knowledge Bases to Understand the
Message of Images",
        BOOKTITLE = MMMod17,
        YEAR = "2017",
        PAGES = "II: 405-418",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117628"}

@inproceedings{bb121515,
        AUTHOR = "Liu, Y. and Guo, Y.M. and Lew, M.S.",
        TITLE = "What Convnets Make for Image Captioning?",
        BOOKTITLE = MMMod17,
        YEAR = "2017",
        PAGES = "I: 416-428",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117629"}

@inproceedings{bb121516,
        AUTHOR = "Tran, K. and He, X. and Zhang, L. and Sun, J.",
        TITLE = "Rich Image Captioning in the Wild",
        BOOKTITLE = DeepLearn-C16,
        YEAR = "2016",
        PAGES = "434-441",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117630"}

@inproceedings{bb121517,
        AUTHOR = "Wang, Y.L. and Wang, S.H. and Tang, J.L. and Liu, H. and Li, B.X.",
        TITLE = "PPP: Joint Pointwise and Pairwise Image Label Prediction",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "6005-6013",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117631"}

@inproceedings{bb121518,
        AUTHOR = "Sadhu, A. and Gupta, T. and Yatskar, M. and Nevatia, R. and Kembhavi, A.",
        TITLE = "Visual Semantic Role Labeling for Video Understanding",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "5585-5596",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117632"}

@inproceedings{bb121519,
        AUTHOR = "Yatskar, M. and Ordonez, V. and Zettlemoyer, L. and Farhadi, A.",
        TITLE = "Commonly Uncommon: Semantic Sparsity in Situation Recognition",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6335-6344",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117633"}

@inproceedings{bb121520,
        AUTHOR = "Yatskar, M. and Zettlemoyer, L. and Farhadi, A.",
        TITLE = "Situation Recognition: Visual Semantic Role Labeling for Image
Understanding",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "5534-5542",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117634"}

@inproceedings{bb121521,
        AUTHOR = "Kottur, S. and Vedantam, R. and Moura, J.M.F. and Parikh, D.",
        TITLE = "VisualWord2Vec (Vis-W2V):
Learning Visually Grounded Word Embeddings Using Abstract Scenes",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4985-4994",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117635"}

@inproceedings{bb121522,
        AUTHOR = "Zhu, Y. and Groth, O. and Bernstein, M. and Fei Fei, L.",
        TITLE = "Visual7W: Grounded Question Answering in Images",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4995-5004",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117636"}

@inproceedings{bb121523,
        AUTHOR = "Zhang, P. and Goyal, Y. and Summers Stay, D. and Batra, D. and Parikh, D.",
        TITLE = "Yin and Yang: Balancing and Answering Binary Visual Questions",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "5014-5022",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117637"}

@inproceedings{bb121524,
        AUTHOR = "Park, D.H. and Darrell, T.J. and Rohrbach, A.",
        TITLE = "Robust Change Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4623-4632",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117638"}

@inproceedings{bb121525,
        AUTHOR = "Venugopalan, S. and Hendricks, L.A. and Rohrbach, M. and Mooney, R. and Darrell, T.J. and Saenko, K.",
        TITLE = "Captioning Images with Diverse Objects",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "1170-1178",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117639"}

@inproceedings{bb121526,
        AUTHOR = "Hendricks, L.A. and Venugopalan, S. and Rohrbach, M. and Mooney, R. and Saenko, K. and Darrell, T.J.",
        TITLE = "Deep Compositional Captioning: Describing Novel Object Categories
without Paired Training Data",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "1-10",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117640"}

@inproceedings{bb121527,
        AUTHOR = "Johnson, J. and Karpathy, A. and Fei Fei, L.",
        TITLE = "DenseCap:
Fully Convolutional Localization Networks for Dense Captioning",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4565-4574",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117641"}

@inproceedings{bb121528,
        AUTHOR = "Lin, X. and Parikh, D.",
        TITLE = "Leveraging Visual Question Answering for Image-Caption Ranking",
        BOOKTITLE = ECCV16,
        YEAR = "2016",
        PAGES = "II: 261-277",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117642"}

@inproceedings{bb121529,
        AUTHOR = "Lin, X. and Parikh, D.",
        TITLE = "Don't just listen, use your imagination:
Leveraging visual common sense for non-visual tasks",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2984-2993",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117643"}

@inproceedings{bb121530,
        AUTHOR = "Chen, T.L. and Zhang, Z.P. and You, Q.Z. and Fang, C. and Wang, Z.W. and Jin, H.L. and Luo, J.B.",
        TITLE = "'Factual' or 'Emotional':
Stylized Image Captioning with Adaptive Learning and Attention",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "X: 527-543",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117644"}

@inproceedings{bb121531,
        AUTHOR = "You, Q.Z. and Jin, H.L. and Wang, Z.W. and Fang, C. and Luo, J.B.",
        TITLE = "Image Captioning with Semantic Attention",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "4651-4659",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117645"}

@inproceedings{bb121532,
        AUTHOR = "Jia, X. and Gavves, E. and Fernando, B. and Tuytelaars, T.",
        TITLE = "Guiding the Long-Short Term Memory Model for Image Caption Generation",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "2407-2415",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117646"}

@inproceedings{bb121533,
        AUTHOR = "Chen, X.L. and Zitnick, C.L.",
        TITLE = "Mind's eye:
A recurrent visual representation for image caption generation",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2422-2431",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117647"}

@inproceedings{bb121534,
        AUTHOR = "Vedantam, R. and Zitnick, C.L. and Parikh, D.",
        TITLE = "CIDEr: Consensus-based image description evaluation",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "4566-4575",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117648"}

@inproceedings{bb121535,
        AUTHOR = "Fang, H. and Gupta, S. and Iandola, F. and Srivastava, R.K. and Deng, L. and Dollar, P. and Gao, J.F. and He, X.D. and Mitchell, M. and Platt, J.C. and Zitnick, C.L. and Zweig, G.",
        TITLE = "From captions to visual concepts and back",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "1473-1482",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117649"}

@inproceedings{bb121536,
        AUTHOR = "Ramnath, K. and Baker, S. and Vanderwende, L. and El Saban, M. and Sinha, S.N. and Kannan, A. and Hassan, N. and Galley, M. and Yang, Y. and Ramanan, D. and Bergamo, A. and Torresani, L.",
        TITLE = "AutoCaption: Automatic caption generation for personal photos",
        BOOKTITLE = WACV14,
        YEAR = "2014",
        PAGES = "1050-1057",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT117650"}

@article{bb121537,
        AUTHOR = "Gao, L.L. and Guo, Z. and Zhang, H.W. and Xu, X. and Shen, H.T.",
        TITLE = "Video Captioning With Attention-Based LSTM and Semantic Consistency",
        JOURNAL = MultMed,
        VOLUME = "19",
        YEAR = "2017",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2045-2055",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117651"}

@article{bb121538,
        AUTHOR = "Bin, Y. and Yang, Y. and Shen, F. and Xie, N. and Shen, H.T. and Li, X.",
        TITLE = "Describing Video With Attention-Based Bidirectional LSTM",
        JOURNAL = Cyber,
        VOLUME = "49",
        YEAR = "2019",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "2631-2641",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117652"}

@article{bb121539,
        AUTHOR = "Fu, K. and Jin, J.Q. and Cui, R.P. and Sha, F. and Zhang, C.S.",
        TITLE = "Aligning Where to See and What to Tell: Image Captioning with
Region-Based Attention and Scene-Specific Contexts",
        JOURNAL = PAMI,
        VOLUME = "39",
        YEAR = "2017",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "2321-2334",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117653"}

@article{bb121540,
        AUTHOR = "Xiao, C.M. and Yang, Q. and Xu, X.Q. and Zhang, J.W. and Zhou, F. and Zhang, C.S.",
        TITLE = "Where you edit is what you get: Text-guided image editing with
region-based attention",
        JOURNAL = PR,
        VOLUME = "139",
        YEAR = "2023",
        PAGES = "109458",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117654"}

@article{bb121541,
        AUTHOR = "Nian, F.D. and Li, T. and Wang, Y. and Wu, X.Y. and Ni, B.B. and Xu, C.S.",
        TITLE = "Learning explicit video attributes from mid-level representation for
video captioning",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "126-138",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117655"}

@article{bb121542,
        AUTHOR = "Ye, S. and Han, J. and Liu, N.",
        TITLE = "Attentive Linear Transformation for Image Captioning",
        JOURNAL = IP,
        VOLUME = "27",
        YEAR = "2018",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "5514-5524",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117656"}

@article{bb121543,
        AUTHOR = "Xian, Y. and Tian, Y.",
        TITLE = "Self-Guiding Multimodal LSTM: When We Do Not Have a Perfect Training
Dataset for Image Captioning",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "5241-5252",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117657"}

@article{bb121544,
        AUTHOR = "Peng, Y.Q. and Liu, X. and Wang, W.H. and Zhao, X.S. and Wei, M.",
        TITLE = "Image caption model of double LSTM with scene factors",
        JOURNAL = IVC,
        VOLUME = "86",
        YEAR = "2019",
        PAGES = "38-44",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117658"}

@article{bb121545,
        AUTHOR = "Wu, L. and Xu, M. and Wang, J. and Perry, S.",
        TITLE = "Recall What You See Continually Using GridLSTM in Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "808-818",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117659"}

@article{bb121546,
        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/match607lscap4.html#TT117660"}

@article{bb121547,
        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/match607lscap4.html#TT117661"}

@article{bb121548,
        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/match607lscap4.html#TT117662"}

@article{bb121549,
        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/match607lscap4.html#TT117663"}

@article{bb121550,
        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/match607lscap4.html#TT117664"}

@article{bb121551,
        AUTHOR = "Yuan, J. and Zhu, S. and Huang, S.Y. and Zhang, H.W. and Xiao, Y.Q. and Li, Z.Y. and Wang, M.",
        TITLE = "Discriminative Style Learning for Cross-Domain Image Captioning",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "1723-1736",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117665"}

@inproceedings{bb121552,
        AUTHOR = "Zhou, Y. and Zhang, Y. and Hu, Z.Z. and Wang, M.",
        TITLE = "Semi-Autoregressive Transformer for Image Captioning",
        BOOKTITLE = CLVL21,
        YEAR = "2021",
        PAGES = "3132-3136",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117666"}

@article{bb121553,
        AUTHOR = "Lv, G. and Sun, Y.N. and Nian, F. and Zhu, M.F. and Tang, W.L. and Hu, Z.Z.",
        TITLE = "COME: Clip-OCR and Master ObjEct for text image captioning",
        JOURNAL = IVC,
        VOLUME = "136",
        YEAR = "2023",
        PAGES = "104751",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117667"}

@inproceedings{bb121554,
        AUTHOR = "Niu, Z.X. and Zhou, M. and Wang, L. and Gao, X.B. and Hua, G.",
        TITLE = "Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1899-1907",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117668"}

@inproceedings{bb121555,
        AUTHOR = "Tan, Y.H. and Chan, C.S.",
        TITLE = "phi-LSTM: A Phrase-Based Hierarchical LSTM Model for Image Captioning",
        BOOKTITLE = ACCV16,
        YEAR = "2016",
        PAGES = "V: 101-117",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117669"}

@inproceedings{bb121556,
        AUTHOR = "Wang, M. and Song, L. and Yang, X.K. and Luo, C.F.",
        TITLE = "A parallel-fusion RNN-LSTM architecture for image caption generation",
        BOOKTITLE = ICIP16,
        YEAR = "2016",
        PAGES = "4448-4452",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607lscap4.html#TT117670"}

@article{bb121557,
        AUTHOR = "Verma, Y. and Jawahar, C.V.",
        TITLE = "A support vector approach for cross-modal search of images and texts",
        JOURNAL = CVIU,
        VOLUME = "154",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "48-63",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117671"}

@inproceedings{bb121558,
        AUTHOR = "Dutta, A. and Verma, Y. and Jawahar, C.V.",
        TITLE = "Recurrent Image Annotation with Explicit Inter-Label Dependencies",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXIX: 191-207",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117672"}

@article{bb121559,
        AUTHOR = "Xue, J.F. and Eguchi, K.",
        TITLE = "Video Data Modeling Using Sequential Correspondence Hierarchical
Dirichlet Processes",
        JOURNAL = IEICE,
        VOLUME = "E100-D",
        YEAR = "2017",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "33-41",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117673"}

@article{bb121560,
        AUTHOR = "Liu, A.A. and Xu, N. and Wong, Y.K. and Li, J. and Su, Y.T. and Kankanhalli, M.",
        TITLE = "Hierarchical & multimodal video captioning: Discovering and
transferring multimodal knowledge for vision to language",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "113-125",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117674"}

@article{bb121561,
        AUTHOR = "Guan, J.N. and Wang, E.",
        TITLE = "Repeated review based image captioning for image evidence review",
        JOURNAL = SP:IC,
        VOLUME = "63",
        YEAR = "2018",
        PAGES = "141-148",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117675"}

@article{bb121562,
        AUTHOR = "Hu, M. and Yang, Y. and Shen, F. and Zhang, L. and Shen, H.T. and Li, X.",
        TITLE = "Robust Web Image Annotation via Exploring Multi-Facet and Structural
Knowledge",
        JOURNAL = IP,
        VOLUME = "26",
        YEAR = "2017",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "4871-4884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117676"}

@article{bb121563,
        AUTHOR = "Gil Gonzalez, J. and Alvarez Meza, A. and Orozco Gutierrez, A.",
        TITLE = "Learning from multiple annotators using kernel alignment",
        JOURNAL = PRL,
        VOLUME = "116",
        YEAR = "2018",
        PAGES = "150-156",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117677"}

@article{bb121564,
        AUTHOR = "Zheng, H. and Wu, J.H. and Liang, R. and Li, Y. and Li, X.Z.",
        TITLE = "Multi-task learning for captioning images with novel words",
        JOURNAL = IET-CV,
        VOLUME = "13",
        YEAR = "2019",
        NUMBER = "3",
        MONTH = "April",
        PAGES = "294-301",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117678"}

@article{bb121565,
        AUTHOR = "Park, C.C. and Kim, B. and Kim, G.",
        TITLE = "Towards Personalized Image Captioning via Multimodal Memory Networks",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "999-1012",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117679"}

@inproceedings{bb121566,
        AUTHOR = "Park, C.C. and Kim, B. and Kim, G.",
        TITLE = "Attend to You: Personalized Image Captioning with Context Sequence
Memory Networks",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6432-6440",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117680"}

@article{bb121567,
        AUTHOR = "Yang, M. and Zhao, W. and Xu, W. and Feng, Y. and Zhao, Z. and Chen, X. and Lei, K.",
        TITLE = "Multitask Learning for Cross-Domain Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1047-1061",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117681"}

@article{bb121568,
        AUTHOR = "Yu, N. and Hu, X. and Song, B. and Yang, J. and Zhang, J.",
        TITLE = "Topic-Oriented Image Captioning Based on Order-Embedding",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "2743-2754",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117682"}

@article{bb121569,
        AUTHOR = "Li, X. and Xu, C. and Wang, X. and Lan, W. and Jia, Z. and Yang, G. and Xu, J.",
        TITLE = "COCO-CN for Cross-Lingual Image Tagging, Captioning, and Retrieval",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2347-2360",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117683"}

@article{bb121570,
        AUTHOR = "Tian, C. and Tian, M. and Jiang, M.M. and Liu, H. and Deng, D.H.",
        TITLE = "How much do cross-modal related semantics benefit image captioning by
weighting attributes and re-ranking sentences?",
        JOURNAL = PRL,
        VOLUME = "125",
        YEAR = "2019",
        PAGES = "639-645",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117684"}

@article{bb121571,
        AUTHOR = "Niu, Y. and Lu, Z. and Wen, J. and Xiang, T. and Chang, S.",
        TITLE = "Multi-Modal Multi-Scale Deep Learning for Large-Scale Image
Annotation",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1720-1731",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117685"}

@article{bb121572,
        AUTHOR = "Huang, Y. and Chen, J. and Ouyang, W. and Wan, W. and Xue, Y.",
        TITLE = "Image Captioning With End-to-End Attribute Detection and Subsequent
Attributes Prediction",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        PAGES = "4013-4026",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117686"}

@article{bb121573,
        AUTHOR = "Zhao, W. and Wu, X. and Luo, J.",
        TITLE = "Cross-Domain Image Captioning via Cross-Modal Retrieval and Model
Adaptation",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "1180-1192",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117687"}

@article{bb121574,
        AUTHOR = "Wang, H. and Du, Y.T. and Zhang, G.X. and Cai, Z.M. and Su, C.",
        TITLE = "Learning Fundamental Visual Concepts Based on Evolved Multi-Edge
Concept Graph",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "4400-4413",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117688"}

@article{bb121575,
        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/match607mmic3.html#TT117689"}

@article{bb121576,
        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/match607mmic3.html#TT117690"}

@inproceedings{bb121577,
        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/match607mmic3.html#TT117691"}

@article{bb121578,
        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/match607mmic3.html#TT117692"}

@article{bb121579,
        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/match607mmic3.html#TT117693"}

@article{bb121580,
        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/match607mmic3.html#TT117694"}

@article{bb121581,
        AUTHOR = "Ding, Z.W. and Lan, G.L. and Song, Y.Z. and Yang, Z.W.",
        TITLE = "SGIR: Star Graph-Based Interaction for Efficient and Robust
Multimodal Representation",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "4217-4229",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117695"}

@article{bb121582,
        AUTHOR = "Zhao, W.T. and Wu, X.X.",
        TITLE = "Boosting Entity-Aware Image Captioning With Multi-Modal Knowledge
Graph",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "2659-2670",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117696"}

@article{bb121583,
        AUTHOR = "Gao, J.L. and Li, J. and Jia, C.M. and Wang, S.S. and Ma, S.W. and Gao, W.",
        TITLE = "Cross Modal Compression With Variable Rate Prompt",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "3444-3456",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117697"}

@inproceedings{bb121584,
        AUTHOR = "Hu, J.C. and Cavicchioli, R. and Capotondi, A.",
        TITLE = "A Request for Clarity over the End of Sequence Token in the
Self-critical Sequence Training",
        BOOKTITLE = CIAP23,
        YEAR = "2023",
        PAGES = "I:39-50",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117698"}

@inproceedings{bb121585,
        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/match607mmic3.html#TT117699"}

@inproceedings{bb121586,
        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/match607mmic3.html#TT117700"}

@inproceedings{bb121587,
        AUTHOR = "Kuo, C.W. and Kira, Z.",
        TITLE = "Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual
Context for Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17948-17958",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117701"}

@inproceedings{bb121588,
        AUTHOR = "Zhou, M.Y. and Zhou, L.W. and Wang, S.H. and Cheng, Y. and Li, L.J. and Yu, Z. and Liu, J.J.",
        TITLE = "UC2: Universal Cross-lingual Cross-modal Vision-and-Language
Pre-training",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "4153-4163",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117702"}

@inproceedings{bb121589,
        AUTHOR = "Laina, I. and Rupprecht, C. and Navab, N.",
        TITLE = "Towards Unsupervised Image Captioning With Shared Multimodal
Embeddings",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "7413-7423",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117703"}

@inproceedings{bb121590,
        AUTHOR = "Akbari, H. and Karaman, S. and Bhargava, S. and Chen, B. and Vondrick, C. and Chang, S.F.",
        TITLE = "Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "12468-12478",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117704"}

@inproceedings{bb121591,
        AUTHOR = "Chen, T.H. and Liao, Y.H. and Chuang, C.Y. and Hsu, W.T. and Fu, J. and Sun, M.",
        TITLE = "Show, Adapt and Tell:
Adversarial Training of Cross-Domain Image Captioner",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "521-530",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117705"}

@inproceedings{bb121592,
        AUTHOR = "Pini, S. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "Towards Video Captioning with Naming:
A Novel Dataset and a Multi-modal Approach",
        BOOKTITLE = CIAP17,
        YEAR = "2017",
        PAGES = "II:384-395",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117706"}

@inproceedings{bb121593,
        AUTHOR = "Pan, J.Y. and Yang, H.J. and Faloutsos, C.",
        TITLE = "MMSS: Graph-based Multi-modal Story-oriented Video Summarization and
Retrieval",
        BOOKTITLE = CMU-CS-TR,
        YEAR = "2004",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117707"}

@inproceedings{bb121594,
        AUTHOR = "Pan, J.Y. and Yang, H.J. and Faloutsos, C. and Duygulu, P.",
        TITLE = "GCap: Graph-based Automatic Image Captioning",
        BOOKTITLE = MMDE04,
        YEAR = "2004",
        PAGES = "146",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117708"}

@inproceedings{bb121595,
        AUTHOR = "Pan, J.Y.",
        TITLE = "Advanced Tools for Video and Multimedia Mining",
        BOOKTITLE = CMU-CS,
        YEAR = "2006",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117709"}

@inproceedings{bb121596,
        AUTHOR = "Pan, J.Y.",
        TITLE = "Advanced Tools for Video and Multimedia Mining",
        BOOKTITLE = Ph.D.,
        YEAR = "2006",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607mmic3.html#TT117709"}

@article{bb121597,
        AUTHOR = "Yu, J. and Li, J. and Yu, Z. and Huang, Q.",
        TITLE = "Multimodal Transformer With Multi-View Visual Representation for
Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "30",
        YEAR = "2020",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "4467-4480",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT117710"}

@article{bb121598,
        AUTHOR = "Zhang, Y. and Shi, X.Y. and Mi, S. and Yang, X.",
        TITLE = "Image captioning with transformer and knowledge graph",
        JOURNAL = PRL,
        VOLUME = "143",
        YEAR = "2021",
        PAGES = "43-49",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT117711"}

@article{bb121599,
        AUTHOR = "Yan, C.G. and Hao, Y.M. and Li, L. and Yin, J. and Liu, A. and Mao, Z. and Chen, Z.Y. and Gao, X.Y.",
        TITLE = "Task-Adaptive Attention for Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "43-51",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT117712"}

Last update:Mar 25, 2024 at 16:07:51