@inproceedings{bb189400,
        AUTHOR = "Liu, Y.F. and Wan, B. and Ma, L. and He, X.M.",
        TITLE = "Relation-aware Instance Refinement for Weakly Supervised Visual
Grounding",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "5608-5617",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184677"}

@inproceedings{bb189401,
        AUTHOR = "Liu, H.L. and Lin, A. and Han, X.G. and Yang, L. and Yu, Y.Z. and Cui, S.G.",
        TITLE = "Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in
RGBD Images",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "6028-6037",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184678"}

@inproceedings{bb189402,
        AUTHOR = "Lin, X.R. and Li, G. and Yu, Y.Z.",
        TITLE = "Scene-Intuitive Agent for Remote Embodied Visual Grounding",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "7032-7041",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184679"}

@inproceedings{bb189403,
        AUTHOR = "Liu, D.Z. and Qu, X.Y. and Dong, J.F. and Zhou, P. and Cheng, Y. and Wei, W. and Xu, Z. and Xie, Y.",
        TITLE = "Context-aware Biaffine Localizing Network for Temporal Sentence
Grounding",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "11230-11239",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184680"}

@inproceedings{bb189404,
        AUTHOR = "Meng, Z. and Yu, L.C. and Zhang, N. and Berg, T. and Damavandi, B. and Singh, V. and Bearman, A.",
        TITLE = "Connecting What to Say With Where to Look by Modeling Human Attention
Traces",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "12674-12683",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184681"}

@inproceedings{bb189405,
        AUTHOR = "Sun, M.J. and Xiao, J. and Lim, E.G.",
        TITLE = "Iterative Shrinking for Referring Expression Grounding Using Deep
Reinforcement Learning",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "14055-14064",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184682"}

@inproceedings{bb189406,
        AUTHOR = "Wang, L. and Huang, J. and Li, Y. and Xu, K. and Yang, Z.Y. and Yu, D.",
        TITLE = "Improving Weakly Supervised Visual Grounding by Contrastive Knowledge
Distillation",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "14085-14095",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184683"}

@inproceedings{bb189407,
        AUTHOR = "Feng, G. and Hu, Z.W. and Zhang, L. and Lu, H.C.",
        TITLE = "Encoder Fusion Network with Co-Attention Embedding for Referring
Image Segmentation",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "15501-15510",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184684"}

@inproceedings{bb189408,
        AUTHOR = "Huang, B.B. and Lian, D.Z. and Luo, W.X. and Gao, S.H.",
        TITLE = "Look Before You Leap:
Learning Landmark Features for One-Stage Visual Grounding",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "16883-16892",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184685"}

@inproceedings{bb189409,
        AUTHOR = "Zhou, H. and Zhang, C.Y. and Luo, Y. and Chen, Y.J. and Hu, C.P.",
        TITLE = "Embracing Uncertainty: Decoupling and De-bias for Robust Temporal
Grounding",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "8441-8450",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184686"}

@inproceedings{bb189410,
        AUTHOR = "Khan, A.U. and Kuehne, H. and Duarte, K. and Gan, C. and Lobo, N. and Shah, M.",
        TITLE = "Found a Reason for me? Weakly-supervised Grounded Visual Question
Answering using Capsules",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "8461-8470",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184687"}

@inproceedings{bb189411,
        AUTHOR = "Zhang, S.Y. and Jiang, T. and Wang, T. and Kuang, K. and Zhao, Z. and Zhu, J. and Yu, J. and Yang, H.X. and Wu, F.",
        TITLE = "DeVLBert: Out-of-distribution Visio-Linguistic Pretraining with
Causality",
        BOOKTITLE = CiV21,
        YEAR = "2021",
        PAGES = "1744-1747",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184688"}

@inproceedings{bb189412,
        AUTHOR = "Nguyen, A.T. and Richards, L.E. and Kebe, G.Y. and Raff, E. and Darvish, K. and Ferraro, F. and Matuszek, C.",
        TITLE = "Practical Cross-modal Manifold Alignment for Robotic Grounded
Language Learning",
        BOOKTITLE = MULA21,
        YEAR = "2021",
        PAGES = "1613-1622",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184689"}

@inproceedings{bb189413,
        AUTHOR = "Shrestha, A. and Pugdeethosapol, K. and Fang, H. and Qiu, Q.",
        TITLE = "MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language
Queries at Phrase Level",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "8275-8282",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184690"}

@inproceedings{bb189414,
        AUTHOR = "Zhang, Z. and Zhao, Z. and Zhao, Y. and Wang, Q. and Liu, H. and Gao, L.",
        TITLE = "Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form
Sentences",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10665-10674",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184691"}

@inproceedings{bb189415,
        AUTHOR = "Sadhu, A. and Chen, K. and Nevatia, R.",
        TITLE = "Video Object Grounding Using Semantic Roles in Language Description",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10414-10424",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184692"}

@inproceedings{bb189416,
        AUTHOR = "Ma, C.Y. and Kalantidis, Y. and AlRegib, G. and Vajda, P. and Rohrbach, M. and Kira, Z.",
        TITLE = "Learning to Generate Grounded Visual Captions Without Localization
Supervision",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVIII:353-370",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184693"}

@inproceedings{bb189417,
        AUTHOR = "Gouthaman, K.V. and Mittal, A.",
        TITLE = "Reducing Language Biases in Visual Question Answering with
Visually-grounded Question Encoder",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIII:18-34",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184694"}

@inproceedings{bb189418,
        AUTHOR = "Zeng, R.H. and Xu, H.M. and Huang, W.B. and Chen, P.H. and Tan, M.K. and Gan, C.",
        TITLE = "Dense Regression Network for Video Grounding",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10284-10293",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184695"}

@inproceedings{bb189419,
        AUTHOR = "Gupta, T. and Vahdat, A. and Chechik, G. and Yang, X.D. and Kautz, J. and Hoiem, D.",
        TITLE = "Contrastive Learning for Weakly Supervised Phrase Grounding",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "III:752-768",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184696"}

@inproceedings{bb189420,
        AUTHOR = "Tan, H.L. and Leong, M.C. and Xu, Q. and Li, L. and Fang, F. and Cheng, Y. and Gauthier, N. and Sun, Y. and Lim, J.H.",
        TITLE = "Task-Oriented Multi-Modal Question Answering For Collaborative
Applications",
        BOOKTITLE = ICIP20,
        YEAR = "2020",
        PAGES = "1426-1430",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184697"}

@inproceedings{bb189421,
        AUTHOR = "Yang, S. and Li, G.B. and Yu, Y.Z.",
        TITLE = "Propagating Over Phrase Relations for One-stage Visual Grounding",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIX:589-605",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184698"}

@inproceedings{bb189422,
        AUTHOR = "Xiao, J.B. and Shang, X. and Yang, X. and Tang, S. and Chua, T.S.",
        TITLE = "Visual Relation Grounding in Videos",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "VI:447-464",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184699"}

@inproceedings{bb189423,
        AUTHOR = "Mun, J. and Cho, M. and Han, B.",
        TITLE = "Local-Global Video-Text Interactions for Temporal Grounding",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10807-10816",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184700"}

@inproceedings{bb189424,
        AUTHOR = "Wu, C. and Lin, Z. and Cohen, S. and Bui, T. and Maji, S.",
        TITLE = "PhraseCut: Language-Based Image Segmentation in the Wild",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10213-10222",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184701"}

@inproceedings{bb189425,
        AUTHOR = "Selvaraju, R.R. and Tendulkar, P. and Parikh, D. and Horvitz, E. and Tulio Ribeiro, M. and Nushi, B. and Kamar, E.",
        TITLE = "SQuINTing at VQA Models: Introspecting VQA Models With Sub-Questions",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10000-10008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184702"}

@inproceedings{bb189426,
        AUTHOR = "Chen, L. and Zhai, M.Y. and He, J.W. and Mori, G.",
        TITLE = "Object Grounding via Iterative Context Reasoning",
        BOOKTITLE = MDALC19,
        YEAR = "2019",
        PAGES = "1407-1415",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184703"}

@inproceedings{bb189427,
        AUTHOR = "Sinha, A. and Akilesh, B. and Sarkar, M. and Krishnamurthy, B.",
        TITLE = "Attention Based Natural Language Grounding by Navigating Virtual
Environment",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "236-244",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184704"}

@inproceedings{bb189428,
        AUTHOR = "Selvaraju, R.R. and Lee, S. and Shen, Y. and Jin, H. and Ghosh, S. and Heck, L. and Batra, D. and Parikh, D.",
        TITLE = "Taking a HINT: Leveraging Explanations to Make Vision and Language
Models More Grounded",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "2591-2600",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184705"}

@inproceedings{bb189429,
        AUTHOR = "Zhang, Y. and Niebles, J.C. and Soto, A.",
        TITLE = "Interpretable Visual Question Answering by Visual Grounding From
Attention Supervision Mining",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "349-357",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184706"}

@inproceedings{bb189430,
        AUTHOR = "Shi, J. and Xu, J. and Gong, B.Q. and Xu, C.L.",
        TITLE = "Not All Frames Are Equal: Weakly-Supervised Video Grounding With
Contextual Similarity and Visual Clustering Losses",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "10436-10444",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184707"}

@inproceedings{bb189431,
        AUTHOR = "Datta, S. and Sikka, K. and Roy, A. and Ahuja, K. and Parikh, D. and Divakaran, A.",
        TITLE = "Align2Ground: Weakly Supervised Phrase Grounding Guided by
Image-Caption Alignment",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "2601-2610",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184708"}

@inproceedings{bb189432,
        AUTHOR = "Fang, Z.Y. and Kong, S. and Fowlkes, C.C. and Yang, Y.Z.",
        TITLE = "Modularized Textual Grounding for Counterfactual Resilience",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6371-6381",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184709"}

@inproceedings{bb189433,
        AUTHOR = "Liu, X.J. and Li, L. and Wang, S.H. and Zha, Z.J. and Meng, D.C. and Huang, Q.M.",
        TITLE = "Adaptive Reconstruction Network for Weakly Supervised Referring
Expression Grounding",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "2611-2620",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184710"}

@inproceedings{bb189434,
        AUTHOR = "Zhuang, B. and Wu, Q. and Shen, C. and Reid, I.D. and van den Hengel, A.J.",
        TITLE = "Parallel Attention: A Unified Framework for Visual Object Discovery
Through Dialogs and Queries",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "4252-4261",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184711"}

@inproceedings{bb189435,
        AUTHOR = "Yang, Z.Y. and Chen, T.L. and Wang, L. and Luo, J.B.",
        TITLE = "Improving One-Stage Visual Grounding by Recursive Sub-query
Construction",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIV:387-404",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184712"}

@inproceedings{bb189436,
        AUTHOR = "Zhang, H.W. and Niu, Y.L. and Chang, S.F.",
        TITLE = "Grounding Referring Expressions in Images by Variational Context",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "4158-4166",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184713"}

@inproceedings{bb189437,
        AUTHOR = "Yu, L.C. and Lin, Z. and Shen, X.H. and Yang, J.M. and Lu, X. and Bansal, M. and Berg, T.L.",
        TITLE = "MAttNet: Modular Attention Network for Referring Expression
Comprehension",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "1307-1315",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184714"}

@inproceedings{bb189438,
        AUTHOR = "Liu, D.Q. and Zhang, H.W. and Zha, Z.J. and Wu, F.",
        TITLE = "Learning to Assemble Neural Module Tree Networks for Visual Grounding",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4672-4681",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184715"}

@inproceedings{bb189439,
        AUTHOR = "Sadhu, A. and Chen, K. and Nevatia, R.",
        TITLE = "Zero-Shot Grounding of Objects From Natural Language Queries",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4693-4702",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184716"}

@inproceedings{bb189440,
        AUTHOR = "Yang, Z.Y. and Gong, B.Q. and Wang, L.W. and Huang, W.B. and Yu, D. and Luo, J.B.",
        TITLE = "A Fast and Accurate One-Stage Approach to Visual Grounding",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4682-4692",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184717"}

@inproceedings{bb189441,
        AUTHOR = "Rohrbach, A. and Rohrbach, M. and Tang, S. and Oh, S.J. and Schiele, B.",
        TITLE = "Generating Descriptions with Grounded and Co-referenced People",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "4196-4206",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184718"}

@inproceedings{bb189442,
        AUTHOR = "Zhu, Y. and Kiros, R. and Zemel, R. and Salakhutdinov, R. and Urtasun, R. and Torralba, A.B. and Fidler, S.",
        TITLE = "Aligning Books and Movies: Towards Story-Like Visual Explanations by
Watching Movies and Reading Books",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "19-27",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vgr2.html#TT184719"}

@article{bb189443,
        AUTHOR = "Su, H.H. and Chen, T.W. and Kao, C.C. and Hsu, W.H. and Chien, S.Y.",
        TITLE = "Preference-Aware View Recommendation System for Scenic Photos Based on
Bag-of-Aesthetics-Preserving Features",
        JOURNAL = MultMed,
        VOLUME = "14",
        YEAR = "2012",
        NUMBER = "3",
        PAGES = "833-843",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184720"}

@article{bb189444,
        AUTHOR = "Chen, L. and Xu, D. and Tsang, I.W. and Luo, J.",
        TITLE = "Tag-Based Image Retrieval Improved by Augmented Features and
Group-Based Refinement",
        JOURNAL = MultMed,
        VOLUME = "14",
        YEAR = "2012",
        NUMBER = "4",
        PAGES = "1057-1067",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184721"}

@article{bb189445,
        AUTHOR = "Chen, L. and Xu, D. and Tsang, I.W. and Li, X.",
        TITLE = "Spectral Embedded Hashing for Scalable Image Retrieval",
        JOURNAL = Cyber,
        VOLUME = "44",
        YEAR = "2014",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1180-1190",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184722"}

@article{bb189446,
        AUTHOR = "Jiao, B. and Yang, L. and Xu, J. and Tian, Q. and Wu, F.",
        TITLE = "Visually Summarizing Web Pages Through Internal and External Images",
        JOURNAL = MultMed,
        VOLUME = "14",
        YEAR = "2012",
        NUMBER = "6",
        PAGES = "1673-1683",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184723"}

@article{bb189447,
        AUTHOR = "Sawant, N. and Wang, J.Z. and Li, J.",
        TITLE = "Enhancing Training Collections for Image Annotation:
An Instance-Weighted Mixture Modeling Approach",
        JOURNAL = IP,
        VOLUME = "22",
        YEAR = "2013",
        NUMBER = "9",
        PAGES = "3562-3577",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184724"}

@article{bb189448,
        AUTHOR = "Zhou, N. and Fan, J.P.",
        TITLE = "Automatic image-text alignment for large-scale web image indexing and
retrieval",
        JOURNAL = PR,
        VOLUME = "48",
        YEAR = "2015",
        NUMBER = "1",
        PAGES = "205-219",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184725"}

@article{bb189449,
        AUTHOR = "Tian, J. and Huang, Y. and Guo, Z. and Qi, X. and Chen, Z. and Huang, T.",
        TITLE = "A Multi-Modal Topic Model for Image Annotation Using Text Analysis",
        JOURNAL = SPLetters,
        VOLUME = "22",
        YEAR = "2015",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "886-890",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184726"}

@article{bb189450,
        AUTHOR = "Rodriguez Vaamonde, S. and Torresani, L. and Fitzgibbon, A.W.",
        TITLE = "What Can Pictures Tell Us About Web Pages? Improving Document Search
Using Images",
        JOURNAL = PAMI,
        VOLUME = "37",
        YEAR = "2015",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "1274-1285",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184727"}

@article{bb189451,
        AUTHOR = "Tirkaz, C. and Eisenstein, J. and Sezgin, T.M. and Yanikoglu, B.A.",
        TITLE = "Identifying visual attributes for object recognition from text and
taxonomy",
        JOURNAL = CVIU,
        VOLUME = "137",
        YEAR = "2015",
        NUMBER = "1",
        PAGES = "12-23",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184728"}

@article{bb189452,
        AUTHOR = "Lu, Y.J. and Yang, L. and Yang, K. and Rui, Y.",
        TITLE = "Mining Latent Attributes From Click-Through Logs for Image
Recognition",
        JOURNAL = MultMed,
        VOLUME = "17",
        YEAR = "2015",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1213-1224",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184729"}

@article{bb189453,
        AUTHOR = "Fu, J. and Wang, J. and Rui, Y. and Wang, X. and Mei, T. and Lu, H.",
        TITLE = "Image Tag Refinement With View-Dependent Concept Representations",
        JOURNAL = CirSysVideo,
        VOLUME = "25",
        YEAR = "2015",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1409-1422",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184730"}

@article{bb189454,
        AUTHOR = "Belongie, S. and Perona, P.",
        TITLE = "Visipedia circa 2015",
        JOURNAL = PRL,
        VOLUME = "72",
        YEAR = "2016",
        NUMBER = "1",
        PAGES = "15-24",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184731"}

@article{bb189455,
        AUTHOR = "Niu, L. and Li, W. and Xu, D.",
        TITLE = "Exploiting Privileged Information from Web Data for Action and Event
Recognition",
        JOURNAL = IJCV,
        VOLUME = "118",
        YEAR = "2016",
        NUMBER = "2",
        MONTH = "June",
        PAGES = "130-150",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184732"}

@inproceedings{bb189456,
        AUTHOR = "Li, W. and Niu, L. and Xu, D.",
        TITLE = "Exploiting Privileged Information from Web Data for Image
Categorization",
        BOOKTITLE = ECCV14,
        YEAR = "2014",
        PAGES = "V: 437-452",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184733"}

@article{bb189457,
        AUTHOR = "Sejal, D. and Rashmi, V. and Venugopal, K.R. and Iyengar, S.S. and Patnaik, L.M.",
        TITLE = "Image recommendation based on keyword relevance using absorbing Markov
chain and image features",
        JOURNAL = MultInfoRetr,
        VOLUME = "5",
        YEAR = "2016",
        NUMBER = "3",
        MONTH = "September",
        PAGES = "185-199",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184734"}

@article{bb189458,
        AUTHOR = "Yan, Y. and Nie, F.P. and Li, W. and Gao, C.Q. and Yang, Y. and Xu, D.",
        TITLE = "Image Classification by Cross-Media Active Learning With Privileged
Information",
        JOURNAL = MultMed,
        VOLUME = "18",
        YEAR = "2016",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "2494-2502",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184735"}

@article{bb189459,
        AUTHOR = "Qian, X. and Li, C. and Lan, K. and Hou, X. and Li, Z. and Han, J.",
        TITLE = "POI Summarization by Aesthetics Evaluation From Crowd Source Social
Media",
        JOURNAL = IP,
        VOLUME = "27",
        YEAR = "2018",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "1178-1189",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184736"}

@article{bb189460,
        AUTHOR = "Li, Z.C. and Tang, J.H. and Mei, T.",
        TITLE = "Deep Collaborative Embedding for Social Image Understanding",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "9",
        MONTH = "Sep",
        PAGES = "2070-2083",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184737"}

@article{bb189461,
        AUTHOR = "Zhang, Z.Z. and Chen, P.J. and Shi, X.S. and Yang, L.",
        TITLE = "Text-Guided Neural Network Training for Image Recognition in Natural
Scenes and Medicine",
        JOURNAL = PAMI,
        VOLUME = "43",
        YEAR = "2021",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1733-1745",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184738"}

@article{bb189462,
        AUTHOR = "Zheng, C.M. and Wu, Z.W. and Wang, T. and Cai, Y. and Li, Q.",
        TITLE = "Object-Aware Multimodal Named Entity Recognition in Social Media
Posts With Adversarial Learning",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "2520-2532",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184739"}

@article{bb189463,
        AUTHOR = "Park, J.Y. and Ryu, D.J. and Nam, K.W. and Jang, I. and Jang, M. and Lee, Y.",
        TITLE = "DeepDBSCAN: Deep Density-Based Clustering for Geo-Tagged Photos",
        JOURNAL = IJGI,
        VOLUME = "10",
        YEAR = "2021",
        NUMBER = "8",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184740"}

@article{bb189464,
        AUTHOR = "Zheng, C. and Zhu, L. and Cheng, Z.Y. and Li, J.J. and Liu, A.A.",
        TITLE = "Adaptive Partial Multi-View Hashing for Efficient Social Image
Retrieval",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "4079-4092",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184741"}

@inproceedings{bb189465,
        AUTHOR = "Liu, Z.J. and Stent, S. and Li, J. and Gideon, J. and Han, S.",
        TITLE = "LocTex: Learning Data-Efficient Visual Representations from Localized
Textual Supervision",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "2147-2156",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184742"}

@inproceedings{bb189466,
        AUTHOR = "Desai, K. and Johnson, J.",
        TITLE = "VirTex: Learning Visual Representations from Textual Annotations",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "11157-11168",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184743"}

@inproceedings{bb189467,
        AUTHOR = "Kenigsfield, G.S. and El Yaniv, R.",
        TITLE = "TranstextNet: Transducing Text for Recognizing Unseen Visual
Relationships",
        BOOKTITLE = WACV21,
        YEAR = "2021",
        PAGES = "1954-1963",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184744"}

@inproceedings{bb189468,
        AUTHOR = "Mithun, N.C. and Pasricha, R. and Papalexakis, E. and Roy Chowdhury, A.K.",
        TITLE = "Webly Supervised Image-Text Embedding with Noisy Tag Refinement",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "7454-7461",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184745"}

@inproceedings{bb189469,
        AUTHOR = "Tesan, T. and Coscia, P. and Ballan, L.",
        TITLE = "A CNN-RNN Framework for Image Annotation from Visual Cues and Social
Network Metadata",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "231-238",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184746"}

@inproceedings{bb189470,
        AUTHOR = "Yang, J.K. and Feng, L.T. and Chen, W.R. and Yan, X.P. and Zheng, H. and Luo, P. and Zhang, W.",
        TITLE = "Webly Supervised Image Classification with Self-Contained Confidence",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "VIII:779-795",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184747"}

@inproceedings{bb189471,
        AUTHOR = "Long, C.J. and Collins, R. and Swears, E. and Hoogs, A.",
        TITLE = "Deep Neural Networks in Fully Connected CRF for Image Labeling with
Social Network Metadata",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "1607-1615",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184748"}

@inproceedings{bb189472,
        AUTHOR = "Tu, Y. and Niu, L. and Chen, J.J. and Cheng, D.W. and Zhang, L.Q.",
        TITLE = "Learning From Web Data With Self-Organizing Memory Module",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "12843-12852",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184749"}

@inproceedings{bb189473,
        AUTHOR = "Niu, L. and Tang, Q.T. and Veeraraghavan, A. and Sabharwal, A.",
        TITLE = "Learning from Noisy Web Data with Category-Level Supervision",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7689-7698",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184750"}

@inproceedings{bb189474,
        AUTHOR = "Guo, S. and Huang, W.L. and Zhang, H.Z. and Zhuang, C.F. and Dong, D. and Scott, M.R. and Huang, D.L.",
        TITLE = "CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "X: 139-154",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184751"}

@inproceedings{bb189475,
        AUTHOR = "Chang, X.O. and Xiang, T. and Hospedales, T.M.",
        TITLE = "L_1 Graph Based Sparse Model for Label De-noising",
        BOOKTITLE = BMVC16,
        YEAR = "2016",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184752"}

@inproceedings{bb189476,
        AUTHOR = "Vadicamo, L. and Carrara, F. and Cimino, A. and Cresci, S. and Dell'Orletta, F. and Falchi, F. and Tesconi, M.",
        TITLE = "Cross-Media Learning for Image Sentiment Analysis in the Wild",
        BOOKTITLE = WSM17,
        YEAR = "2017",
        PAGES = "308-317",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184753"}

@inproceedings{bb189477,
        AUTHOR = "Fernandez, D. and Varas, D. and Espadaler, J. and Masuda, I. and Ferreira, J. and Woodward, A. and Rodriguez, D. and Giro i Nieto, X. and Riveiro, J.C. and Bou, E.",
        TITLE = "ViTS: Video Tagging System from Massive Web Multimedia Collections",
        BOOKTITLE = WSM17,
        YEAR = "2017",
        PAGES = "337-346",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184754"}

@inproceedings{bb189478,
        AUTHOR = "Goyal, R. and Kahou, S.E. and Michalski, V. and Materzynska, J. and Westphal, S. and Kim, H. and Haenel, V. and Fruend, I. and Yianilos, P. and Mueller Freitag, M. and Hoppe, F. and Thurau, C. and Bax, I. and Memisevic, R.",
        TITLE = "The 'Something Something' Video Database for Learning and Evaluating
Visual Common Sense",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "5843-5851",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184755"}

@inproceedings{bb189479,
        AUTHOR = "Gomez, L. and Patel, Y. and Rusinol, M. and Karatzas, D. and Jawahar, C.V.",
        TITLE = "Self-Supervised Learning of Visual Features through Embedding Images
into Text Topic Spaces",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "2017-2026",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184756"}

@inproceedings{bb189480,
        AUTHOR = "Eskevich, M. and Larson, M. and Aly, R. and Sabetghadam, S. and Jones, G.J.F. and Ordelman, R. and Huet, B.",
        TITLE = "Multimodal Video-to-Video Linking:
Turning to the Crowd for Insight and Evaluation",
        BOOKTITLE = MMMod17,
        YEAR = "2017",
        PAGES = "II: 280-292",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184757"}

@inproceedings{bb189481,
        AUTHOR = "Bois, R. and Vukotic, V. and Simon, A.R. and Sicre, R. and Raymond, C. and Sebillot, P. and Gravier, G.",
        TITLE = "Exploiting Multimodality in Video Hyperlinking to Improve Target
Diversity",
        BOOKTITLE = MMMod17,
        YEAR = "2017",
        PAGES = "II: 185-197",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184758"}

@inproceedings{bb189482,
        AUTHOR = "Izadinia, H. and Sadeghi, F. and Divvala, S.K. and Hajishirzi, H. and Choi, Y. and Farhadi, A.",
        TITLE = "Segment-Phrase Table for Semantic Segmentation, Visual Entailment and
Paraphrasing",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "10-18",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184759"}

@inproceedings{bb189483,
        AUTHOR = "Hou, Y.Q.",
        TITLE = "Image Annotation Incorporating Low-Rankness, Tag and Visual Correlation
and Inhomogeneous Errors",
        BOOKTITLE = ISVC15,
        YEAR = "2015",
        PAGES = "I: 71-81",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184760"}

@inproceedings{bb189484,
        AUTHOR = "Yao, Y.Z. and Zhang, J. and Hua, X.S. and Shen, F.M. and Tang, Z.M.",
        TITLE = "Extracting Visual Knowledge from the Internet:
Making Sense of Image Data",
        BOOKTITLE = MMMod16,
        YEAR = "2016",
        PAGES = "I: 862-873",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184761"}

@inproceedings{bb189485,
        AUTHOR = "Jas, M. and Parikh, D.",
        TITLE = "Image specificity",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2727-2736",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184762"}

@inproceedings{bb189486,
        AUTHOR = "Johns, E. and Aodha, O.M. and Brostow, G.J.",
        TITLE = "Becoming the expert: Interactive multi-class machine teaching",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2616-2624",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184763"}

@inproceedings{bb189487,
        AUTHOR = "Russakovsky, O. and Li, L.J. and Fei Fei, L.",
        TITLE = "Best of both worlds:
Human-machine collaboration for object annotation",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "2121-2131",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184764"}

@inproceedings{bb189488,
        AUTHOR = "Abdulhak, S.A. and Riviera, W. and Zeni, N. and Cristani, M. and Ferrario, R. and Cristani, M.",
        TITLE = "Semantic-Analysis Object Recognition:
Automatic Training Set Generation Using Textual Tags",
        BOOKTITLE = CVONT14,
        YEAR = "2014",
        PAGES = "309-322",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184765"}

@inproceedings{bb189489,
        AUTHOR = "He, Y.H. and Wang, J. and Xiang, S.M. and Pan, C.H.",
        TITLE = "Image annotation via learning the image-label interrelations",
        BOOKTITLE = ICIP14,
        YEAR = "2014",
        PAGES = "3102-3106",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184766"}

@inproceedings{bb189490,
        AUTHOR = "Jhuo, I.H. and Weng, L.",
        TITLE = "Image auto-annotation by exploiting web information",
        BOOKTITLE = ICIP14,
        YEAR = "2014",
        PAGES = "3052-3056",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184767"}

@inproceedings{bb189491,
        AUTHOR = "Safadi, B. and Sahuguet, M. and Huet, B.",
        TITLE = "Linking text and visual concepts semantically for cross modal
multimedia search",
        BOOKTITLE = ICIP14,
        YEAR = "2014",
        PAGES = "3077-3081",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184768"}

@inproceedings{bb189492,
        AUTHOR = "Xue, J. and Du, Y. and Shui, H.",
        TITLE = "Semantic Correlation Mining between Images and Texts with Global
Semantics and Local Mapping",
        BOOKTITLE = MMMod15,
        YEAR = "2015",
        PAGES = "II: 427-435",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184769"}

@inproceedings{bb189493,
        AUTHOR = "Verma, Y. and Jawahar, C.V.",
        TITLE = "Im2Text and Text2Im:
Associating Images and Texts for Cross-Modal Retrieval",
        BOOKTITLE = BMVC14,
        YEAR = "2014",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184770"}

@inproceedings{bb189494,
        AUTHOR = "Feng, Z. and Feng, S.H. and Jin, R. and Jain, A.K.",
        TITLE = "Image Tag Completion by Noisy Matrix Recovery",
        BOOKTITLE = ECCV14,
        YEAR = "2014",
        PAGES = "VII: 424-438",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184771"}

@inproceedings{bb189495,
        AUTHOR = "Radu, A.L. and Ionescu, B. and Menendez, M. and Stottinger, J. and Giunchiglia, F. and de Angeli, A.",
        TITLE = "A Hybrid Machine-Crowd Approach to Photo Retrieval Result
Diversification",
        BOOKTITLE = MMMod14,
        YEAR = "2014",
        PAGES = "I: 25-36",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184772"}

@inproceedings{bb189496,
        AUTHOR = "Wang, C.X. and Song, Z. and Feng, S.H. and Lang, C.Y. and Yan, S.C.",
        TITLE = "A novel image tag saliency ranking algorithm based on sparse
representation",
        BOOKTITLE = VCIP13,
        YEAR = "2013",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184773"}

@inproceedings{bb189497,
        AUTHOR = "Mishra, A. and Alahari, K. and Jawahar, C.V.",
        TITLE = "Image Retrieval Using Textual Cues",
        BOOKTITLE = ICCV13,
        YEAR = "2013",
        PAGES = "3040-3047",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184774"}

@inproceedings{bb189498,
        AUTHOR = "Padilla, S. and Halley, F. and Robb, D.A.",
        TITLE = "Intuitive Large Image Database Browsing Using Perceptual Similarity
Enriched by Crowds",
        BOOKTITLE = CAIP13,
        YEAR = "2013",
        PAGES = "II:169-176",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184775"}

@inproceedings{bb189499,
        AUTHOR = "Lin, J. and Duan, L.Y. and Yuan, J.S. and Li, Q.Y. and Luo, S.W.",
        TITLE = "Learning sparse tag patterns for social image classification",
        BOOKTITLE = ICIP12,
        YEAR = "2012",
        PAGES = "2881-2884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT184776"}

Last update: