@article{bb221000,
AUTHOR = "Gong, Y. and Cosma, G.",
TITLE = "Improving visual-semantic embeddings by learning
semantically-enhanced hard negatives for cross-modal information
retrieval",
JOURNAL = PR,
VOLUME = "137",
YEAR = "2023",
PAGES = "109272",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216000"}
@article{bb221001,
AUTHOR = "Li, W.H. and Wang, Y. and Su, Y.T. and Li, X.Y. and Liu, A.A. and Zhang, Y.D.",
TITLE = "Multi-Scale Fine-Grained Alignments for Image and Sentence Matching",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "543-556",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216001"}
@article{bb221002,
AUTHOR = "Ou, W.H. and Deng, J.X. and Zhang, L. and Gou, J.P. and Zhou, Q.",
TITLE = "Cross-Modal Generation and Pair Correlation Alignment Hashing",
JOURNAL = ITS,
VOLUME = "24",
YEAR = "2023",
NUMBER = "3",
MONTH = "March",
PAGES = "3018-3026",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216002"}
@article{bb221003,
AUTHOR = "Wang, D. and Zhang, C.P. and Wang, Q. and Tian, Y.M. and He, L. and Zhao, L.",
TITLE = "Hierarchical Semantic Structure Preserving Hashing for Cross-Modal
Retrieval",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "1217-1229",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216003"}
@article{bb221004,
AUTHOR = "Hu, P. and Huang, Z.Y. and Peng, D.Z. and Wang, X. and Peng, X.",
TITLE = "Cross-Modal Retrieval With Partially Mismatched Pairs",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "8",
MONTH = "August",
PAGES = "9595-9610",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216004"}
@article{bb221005,
AUTHOR = "Liu, Y.X. and Wu, J.L. and Qu, L. and Gan, T. and Yin, J.H. and Nie, L.Q.",
TITLE = "Self-Supervised Correlation Learning for Cross-Modal Retrieval",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "2851-2863",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216005"}
@article{bb221006,
AUTHOR = "Wang, B.H. and Zhang, H.X. and Zhu, L. and Nie, L.Q. and Liu, L.",
TITLE = "Multi-level adversarial attention cross-modal hashing",
JOURNAL = SP:IC,
VOLUME = "117",
YEAR = "2023",
PAGES = "117017",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216006"}
@article{bb221007,
AUTHOR = "Sun, C. and Zhang, H.X. and Liu, L. and Liu, D.M. and Wang, L.",
TITLE = "Multi-Label Adversarial Fine-Grained Cross-Modal Retrieval",
JOURNAL = SP:IC,
VOLUME = "117",
YEAR = "2023",
PAGES = "117018",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216007"}
@article{bb221008,
AUTHOR = "Huo, Y.D. and Qin, Q. and Dai, J.Y. and Wang, L. and Zhang, W.F. and Huang, L. and Wang, C.",
TITLE = "Deep Semantic-Aware Proxy Hashing for Multi-Label Cross-Modal
Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "1",
MONTH = "January",
PAGES = "576-589",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216008"}
@article{bb221009,
AUTHOR = "Song, D. and Ling, Y.T. and Li, T. and Wang, T. and Li, X.",
TITLE = "Hierarchical deep semantic alignment for cross-domain 3D model
retrieval",
JOURNAL = JVCIR,
VOLUME = "95",
YEAR = "2023",
PAGES = "103895",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216009"}
@article{bb221010,
AUTHOR = "Li, T.B. and Liu, A.A. and Song, D. and Li, W.H. and Li, X.Y. and Su, Y.T.",
TITLE = "Focus on Hard Samples: Hierarchical Unbiased Constraints for
Cross-Domain 3D Model Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "11",
MONTH = "November",
PAGES = "7036-7049",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216010"}
@article{bb221011,
AUTHOR = "Dong, X. and Zhan, X.L. and Wei, Y.C. and Wei, X.Y. and Wang, Y. and Lu, M.L. and Cao, X.C. and Liang, X.D.",
TITLE = "Entity-Graph Enhanced Cross-Modal Pretraining for Instance-Level
Product Retrieval",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "11",
MONTH = "November",
PAGES = "13117-13133",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216011"}
@inproceedings{bb221012,
AUTHOR = "Zhan, X.L. and Wu, Y.X. and Dong, X. and Wei, Y.C. and Lu, M.L. and Zhang, Y.C. and Xu, H. and Liang, X.D.",
TITLE = "Product1M: Towards Weakly Supervised Instance-Level Product Retrieval
via Cross-Modal Pretraining",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "11762-11771",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216012"}
@article{bb221013,
AUTHOR = "Zhang, X. and Li, W.P. and Wang, X. and Wang, L. and Zheng, F.Z. and Wang, L. and Zhang, H.",
TITLE = "A Fusion Encoder with Multi-Task Guidance for Cross-Modal Text-Image
Retrieval in Remote Sensing",
JOURNAL = RS,
VOLUME = "15",
YEAR = "2023",
NUMBER = "18",
PAGES = "4637",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216013"}
@article{bb221014,
AUTHOR = "Tu, R.C. and Jiang, J. and Lin, Q.H. and Cai, C.F. and Tian, S.X. and Wang, H.F. and Liu, W.",
TITLE = "Unsupervised Cross-Modal Hashing With Modality-Interaction",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "9",
MONTH = "September",
PAGES = "5296-5308",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216014"}
@article{bb221015,
AUTHOR = "Liu, X. and Yi, J.H. and Cheung, Y.M. and Xu, X. and Cui, Z.",
TITLE = "OMGH: Online Manifold-Guided Hashing for Flexible Cross-Modal
Retrieval",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "3811-3824",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216015"}
@article{bb221016,
AUTHOR = "Peng, S.J. and Yi, J.H. and Liu, X. and Cheung, Y.M. and Cui, Z. and Li, T.H.",
TITLE = "OLCH: Online Label Consistent Hashing for streaming cross-modal
retrieval",
JOURNAL = PR,
VOLUME = "150",
YEAR = "2024",
PAGES = "110335",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216016"}
@article{bb221017,
AUTHOR = "Tan, W.T. and Zhu, L. and Li, J.J. and Zhang, H.X. and Han, J.W.",
TITLE = "Teacher-Student Learning: Efficient Hierarchical Message Aggregation
Hashing for Cross-Modal Retrieval",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "4520-4532",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216017"}
@article{bb221018,
AUTHOR = "Song, L.Y. and Shang, X. and Yang, C. and Sun, M.X.",
TITLE = "Attribute-Guided Multiple Instance Hashing Network for Cross-Modal
Zero-Shot Hashing",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "5305-5318",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216018"}
@article{bb221019,
AUTHOR = "Li, L. and Shu, Z.Q. and Yu, Z.T. and Wu, X.J.",
TITLE = "Robust online hashing with label semantic enhancement for cross-modal
retrieval",
JOURNAL = PR,
VOLUME = "145",
YEAR = "2024",
PAGES = "109972",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216019"}
@article{bb221020,
AUTHOR = "Ye, Z. and Yao, L. and Zhang, Y. and Gustin, S.",
TITLE = "Self-supervised cross-modal visual retrieval from brain activities",
JOURNAL = PR,
VOLUME = "145",
YEAR = "2024",
PAGES = "109915",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216020"}
@article{bb221021,
AUTHOR = "Chen, Z.J. and Zhang, Y. and Mi, S.",
TITLE = "Assisting Multimodal Named Entity Recognition by cross-modal
auxiliary tasks",
JOURNAL = PRL,
VOLUME = "175",
YEAR = "2023",
PAGES = "52-58",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216021"}
@article{bb221022,
AUTHOR = "Liu, X.Q. and Zeng, H.Q. and Shi, Y.F. and Zhu, J.Q. and Hsia, C.H. and Ma, K.K.",
TITLE = "Deep Cross-Modal Hashing Based on Semantic Consistent Ranking",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "9530-9542",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216022"}
@article{bb221023,
AUTHOR = "Luo, K.Y. and Zhang, C. and Li, H.X. and Jia, X. and Chen, C.L.",
TITLE = "Adaptive Marginalized Semantic Hashing for Unpaired Cross-Modal
Retrieval",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "9082-9095",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216023"}
@article{bb221024,
AUTHOR = "Li, Z.X. and Zhao, W.Z. and Du, X.Y. and Zhou, G.Y. and Zhang, S.",
TITLE = "Cross-Modal Retrieval and Semantic Refinement for Remote Sensing
Image Captioning",
JOURNAL = RS,
VOLUME = "16",
YEAR = "2024",
NUMBER = "1",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216024"}
@article{bb221025,
AUTHOR = "Xu, R.Q. and Mayer, W. and Chu, H.L. and Zhang, Y. and Zhang, H.Y. and Wang, Y.L. and Liu, Y. and Feng, Z.",
TITLE = "Automatic semantic modeling of structured data sources with
cross-modal retrieval",
JOURNAL = PRL,
VOLUME = "177",
YEAR = "2024",
PAGES = "7-14",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216025"}
@article{bb221026,
AUTHOR = "Okamura, D. and Harakawa, R. and Iwahashi, M.",
TITLE = "LCNME: Label Correction Using Network Prediction Based on
Memorization Effects for Cross-Modal Retrieval With Noisy Labels",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "1",
MONTH = "January",
PAGES = "590-602",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216026"}
@article{bb221027,
AUTHOR = "Yang, F. and Han, M. and Ma, F.M. and Liu, Y.F. and Ding, X.J. and Tong, D.Y.",
TITLE = "Disperse Asymmetric Subspace Relation Hashing for Cross-Modal
Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "1",
MONTH = "January",
PAGES = "603-617",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216027"}
@article{bb221028,
AUTHOR = "Zhang, G.J. and Li, S.K. and Wei, S.K. and Ge, S.M. and Cai, N. and Zhao, Y.",
TITLE = "Multimodal Composition Example Mining for Composed Query Image
Retrieval",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "1149-1161",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216028"}
@article{bb221029,
AUTHOR = "Sun, Y. and Ren, Z.W. and Hu, P. and Peng, D.Z. and Wang, X.",
TITLE = "Hierarchical Consensus Hashing for Cross-Modal Retrieval",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "824-836",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216029"}
@article{bb221030,
AUTHOR = "Zhang, L. and Chen, L. and Zhou, C. and Li, X. and Yang, F. and Yi, Z.",
TITLE = "Weighted Graph-Structured Semantics Constraint Network for
Cross-Modal Retrieval",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "1551-1564",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216030"}
@article{bb221031,
AUTHOR = "Wang, Y.B. and Wang, S.H. and Luo, H. and Dong, J.F. and Wang, F. and Han, M. and Wang, X. and Wang, M.",
TITLE = "Dual-View Curricular Optimal Transport for Cross-Lingual Cross-Modal
Retrieval",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "1522-1533",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216031"}
@article{bb221032,
AUTHOR = "Meng, M. and Sun, J.X. and Liu, J. and Yu, J. and Wu, J.",
TITLE = "Semantic Disentanglement Adversarial Hashing for Cross-Modal
Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "3",
MONTH = "March",
PAGES = "1914-1926",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216032"}
@article{bb221033,
AUTHOR = "Zhang, H. and Li, Y.D. and Li, X.L.",
TITLE = "Constrained Bipartite Graph Learning for Imbalanced Multi-Modal
Retrieval",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "4502-4514",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216033"}
@article{bb221034,
AUTHOR = "Wang, Z. and Xu, X. and Wei, J. and Xie, N. and Yang, Y. and Shen, H.T.",
TITLE = "Semantics Disentangling for Cross-Modal Retrieval",
JOURNAL = IP,
VOLUME = "33",
YEAR = "2024",
PAGES = "2226-2237",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216034"}
@inproceedings{bb221035,
AUTHOR = "Honig, R. and Ackermann, J. and Chi, M.Y.",
TITLE = "Bi-Encoder Cascades for Efficient Image Search",
BOOKTITLE = REDLCV23,
YEAR = "2023",
PAGES = "1350-1355",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216035"}
@inproceedings{bb221036,
AUTHOR = "Cao, Y.C. and Tang, Q. and Yang, F. and Su, X. and You, S. and Lu, X.B. and Xu, C.",
TITLE = "Re-mine, Learn and Reason: Exploring the Cross-modal Semantic
Correlations for Language-guided HOI detection",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "23435-23446",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216036"}
@inproceedings{bb221037,
AUTHOR = "Trinci, T. and Bianconcini, T. and Sarti, L. and Taccari, L. and Sambo, F.",
TITLE = "Cross-model temporal cooperation via saliency maps for efficient
frame classification",
BOOKTITLE = REDLCV23,
YEAR = "2023",
PAGES = "1156-1160",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216037"}
@inproceedings{bb221038,
AUTHOR = "Long, T. and van Noord, N.",
TITLE = "Cross-modal Scalable Hyperbolic Hierarchical Clustering",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "16609-16618",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216038"}
@inproceedings{bb221039,
AUTHOR = "Li, H. and Li, X.Y. and Hu, P. and Lei, Y. and Li, C.X. and Zhou, Y.",
TITLE = "Boosting Multi-modal Model Performance with Adaptive Gradient
Modulation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22157-22167",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216039"}
@inproceedings{bb221040,
AUTHOR = "Li, W. and Pun, C.M.",
TITLE = "Asymmetric Scalable Cross-Modal Hashing",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "316-320",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216040"}
@inproceedings{bb221041,
AUTHOR = "Zhao, L.J. and Wang, Y. and Kato, J.",
TITLE = "Using Classifier Discrepancy for Cross-Domain Image Retrieval",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "3314-3318",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216041"}
@inproceedings{bb221042,
AUTHOR = "Era, Y. and Togo, R. and Maeda, K. and Ogawa, T. and Haseyama, M.",
TITLE = "Video-Music Retrieval with Fine-Grained Cross-Modal Alignment",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "2005-2009",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216042"}
@inproceedings{bb221043,
AUTHOR = "Yu, Y. and Chung, J. and Yun, H. and Hessel, J. and Park, J.S. and Lu, X. and Zellers, R. and Ammanabrolu, P. and Le Bras, R. and Kim, G. and Choi, Y.",
TITLE = "Fusing Pre-Trained Language Models with Multimodal Prompts through
Reinforcement Learning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10845-10856",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216043"}
@inproceedings{bb221044,
AUTHOR = "Huang, S. and Gong, B. and Pan, Y.L. and Jiang, J.W. and Lv, Y.L. and Li, Y.Y. and Wang, D.L.",
TITLE = "VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6565-6574",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216044"}
@inproceedings{bb221045,
AUTHOR = "Chen, M.X. and Xing, L. and Wang, Y. and Zhang, X.",
TITLE = "Enhanced Multimodal Representation Learning with Cross-modal KD",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11766-11775",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216045"}
@inproceedings{bb221046,
AUTHOR = "Yang, S. and Xu, Z. and Wang, K. and You, Y. and Yao, H.X. and Liu, T.L. and Xu, M.",
TITLE = "BiCro: Noisy Correspondence Rectification for Multi-modality Data via
Bi-directional Cross-modal Similarity Consistency",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "19883-19892",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216046"}
@inproceedings{bb221047,
AUTHOR = "Kim, D. and Kim, N. and Kwak, S.",
TITLE = "Improving Cross-Modal Retrieval with Set of Diverse Embeddings",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "23422-23431",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216047"}
@inproceedings{bb221048,
AUTHOR = "Kim, J.M. and Koepke, A.S. and Schmid, C. and Akata, Z.",
TITLE = "Exposing and Mitigating Spurious Correlations for Cross-Modal
Retrieval",
BOOKTITLE = MULA23,
YEAR = "2023",
PAGES = "2585-2595",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216048"}
@inproceedings{bb221049,
AUTHOR = "Tran, V. and Balasubramanian, N. and Hoai, M.",
TITLE = "From Within to Between: Knowledge Distillation for Cross Modality
Retrieval",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "IV:605-622",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216049"}
@inproceedings{bb221050,
AUTHOR = "Zhao, Y. and Zhu, Y.Z. and Liao, S. and Ye, Q. and Zhang, H.F.",
TITLE = "Class Concentration with Twin Variational Autoencoders for Unsupervised
Cross-modal Hashing",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "VI:235-251",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216050"}
@inproceedings{bb221051,
AUTHOR = "Fragomeni, A. and Wray, M. and Damen, D.",
TITLE = "Contra: (con)text (tra)nsformer for Cross-modal Video Retrieval",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "IV:451-468",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216051"}
@inproceedings{bb221052,
AUTHOR = "Zheng, Y.C. and Zhang, X.W.",
TITLE = "Heterogeneous Interactive Learning Network for Unsupervised Cross-modal
Retrieval",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "IV:692-707",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216052"}
@inproceedings{bb221053,
AUTHOR = "Zhao, Y. and Yu, J.G. and Liao, S. and Zhang, Z. and Zhang, H.F.",
TITLE = "From Sparse to Dense: Semantic Graph Evolutionary Hashing for
Unsupervised Cross-Modal Retrieval",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "IV:521-536",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216053"}
@inproceedings{bb221054,
AUTHOR = "Arnold, R. and Sauter, L. and Schuldt, H.",
TITLE = "Free-Form Multi-Modal Multimedia Retrieval (4MR)",
BOOKTITLE = MMMod23,
YEAR = "2023",
PAGES = "I: 678-683",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216054"}
@inproceedings{bb221055,
AUTHOR = "Xuan, H. and Chen, X.S.",
TITLE = "Dissecting Deep Metric Learning Losses for Image-Text Retrieval",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "2163-2172",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216055"}
@inproceedings{bb221056,
AUTHOR = "Ge, X. and Chen, F. and Xu, S. and Tao, F. and Jose, J.M.",
TITLE = "Cross-modal Semantic Enhanced Interaction for Image-Sentence
Retrieval",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "1022-1031",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216056"}
@inproceedings{bb221057,
AUTHOR = "Jawade, B. and Mohan, D.D. and Ali, N.M. and Setlur, S. and Govindaraju, V.",
TITLE = "NAPReg: Nouns As Proxies Regularization for Semantically Aware
Cross-Modal Embeddings",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "1135-1144",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216057"}
@inproceedings{bb221058,
AUTHOR = "Nakatsuka, T. and Hamasaki, M. and Goto, M.",
TITLE = "Content-Based Music-Image Retrieval Using Self- and Cross-Modal
Feature Embedding Memory",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "2173-2183",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216058"}
@inproceedings{bb221059,
AUTHOR = "Chen, Y.X. and Yuan, J.B. and Zhao, L. and Chen, T.L. and Luo, R. and Davis, L. and Metaxas, D.N.",
TITLE = "More Than Just Attention: Improving Cross-Modal Attentions with
Contrastive Constraints for Image-Text Matching",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "4421-4429",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216059"}
@inproceedings{bb221060,
AUTHOR = "Agarwal, A. and Karanam, S. and Srinivasan, B.V. and Banerjee, B.",
TITLE = "Contrastive Learning of Semantic Concepts for Open-set Cross-domain
Retrieval",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "4104-4113",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216060"}
@inproceedings{bb221061,
AUTHOR = "Yang, Y. and Shen, H. and Yang, M.",
TITLE = "Relation-Guided Network for Image-Text Retrieval",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "1856-1860",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216061"}
@inproceedings{bb221062,
AUTHOR = "Sumbul, G. and Muller, M. and Demir, B.",
TITLE = "A Novel Self-Supervised Cross-Modal Image Retrieval Method in Remote
Sensing",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2426-2430",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216062"}
@inproceedings{bb221063,
AUTHOR = "Wang, H. and Zhang, J.P. and Chen, Y.H. and Ma, C.B. and Avery, J. and Hull, L. and Carneiro, G.",
TITLE = "Uncertainty-Aware Multi-modal Learning via Cross-Modal Random Network
Prediction",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVII:200-217",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216063"}
@inproceedings{bb221064,
AUTHOR = "de Almeida, L.B. and Valem, L.P. and Pedronette, D.C.G.",
TITLE = "Graph Convolutional Networks and Manifold Ranking for Multimodal
Video Retrieval",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2811-2815",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216064"}
@inproceedings{bb221065,
AUTHOR = "Liang, T. and Lin, G.S. and Wan, M.Y. and Li, T.R. and Ma, G.J. and Lv, F.M.",
TITLE = "Expanding Large Pre-trained Unimodal Models with Multimodal
Information Injection for Image-Text Multimodal Classification",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15471-15480",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216065"}
@inproceedings{bb221066,
AUTHOR = "Yang, J.H. and Chen, X.Y. and Jiang, M. and Chen, S. and Wang, L. and Zhao, Q.",
TITLE = "VisualHow: Multimodal Problem Solving",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15606-15616",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216066"}
@inproceedings{bb221067,
AUTHOR = "Girdhar, R. and Singh, M. and Ravi, N. and van der Maaten, L. and Joulin, A. and Misra, I.",
TITLE = "Omnivore: A Single Model for Many Visual Modalities",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16081-16091",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216067"}
@inproceedings{bb221068,
AUTHOR = "Ma, M.M. and Ren, J. and Zhao, L. and Testuggine, D. and Peng, X.",
TITLE = "Are Multimodal Transformers Robust to Missing Modality?",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "18156-18165",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216068"}
@inproceedings{bb221069,
AUTHOR = "Han, Z.B. and Yang, F. and Huang, J.Z. and Zhang, C.Q. and Yao, J.H.",
TITLE = "Multimodal Dynamics: Dynamical Fusion for Trustworthy Multimodal
Classification",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "20675-20685",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216069"}
@inproceedings{bb221070,
AUTHOR = "Gupta, V. and Mittal, T. and Mathur, P. and Mishra, V. and Maheshwari, M. and Bera, A. and Mukherjee, D. and Manocha, D.",
TITLE = "3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social
Media Short Videos",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "21032-21043",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216070"}
@inproceedings{bb221071,
AUTHOR = "Bogolin, S.V. and Croitoru, I. and Jin, H.L. and Liu, Y. and Albanie, S.",
TITLE = "Cross Modal Retrieval with Querybank Normalisation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "5184-5195",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216071"}
@inproceedings{bb221072,
AUTHOR = "Yang, E. and Yao, D.R. and Liu, T.L. and Deng, C.",
TITLE = "Mutual Quantization for Cross-Modal Search with Noisy Labels",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "7541-7550",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216072"}
@inproceedings{bb221073,
AUTHOR = "Neculai, A. and Chen, Y.B. and Akata, Z.",
TITLE = "Probabilistic Compositional Embeddings for Multimodal Image Retrieval",
BOOKTITLE = MULA22,
YEAR = "2022",
PAGES = "4546-4556",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216073"}
@inproceedings{bb221074,
AUTHOR = "Couairon, G. and Douze, M. and Cord, M. and Schwenk, H.",
TITLE = "Embedding Arithmetic of Multimodal Queries for Image Retrieval",
BOOKTITLE = ODRUM22,
YEAR = "2022",
PAGES = "4946-4954",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216074"}
@inproceedings{bb221075,
AUTHOR = "Sun, C.C. and Latapie, H. and Liu, G. and Yan, Y.",
TITLE = "Deep Normalized Cross-Modal Hashing with Bi-Direction Relation
Reasoning",
BOOKTITLE = ODRUM22,
YEAR = "2022",
PAGES = "4937-4945",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216075"}
@inproceedings{bb221076,
AUTHOR = "Li, Y.H. and Yu, J. and Cai, Z. and Pan, Y.",
TITLE = "Cross-modal Target Retrieval for Tracking by Natural Language",
BOOKTITLE = ODRUM22,
YEAR = "2022",
PAGES = "4927-4936",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216076"}
@inproceedings{bb221077,
AUTHOR = "Thomas, C. and Kovashka, A.",
TITLE = "Emphasizing Complementary Samples for Non-literal Cross-modal
Retrieval",
BOOKTITLE = MULA22,
YEAR = "2022",
PAGES = "4631-4640",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216077"}
@inproceedings{bb221078,
AUTHOR = "Xu, B. and Xiong, Y.H. and Zhang, R. and Feng, Y. and Wu, H.F.",
TITLE = "Natural Language-Based Vehicle Retrieval with Explicit Cross-Modal
Representation Learning",
BOOKTITLE = AICity22,
YEAR = "2022",
PAGES = "3141-3148",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216078"}
@inproceedings{bb221079,
AUTHOR = "Shvetsova, N. and Chen, B. and Rouditchenko, A. and Thomas, S. and Kingsbury, B. and Feris, R.S. and Harwath, D. and Glass, J. and Kuehne, H.",
TITLE = "Everything at Once - Multi-modal Fusion Transformer for Video
Retrieval",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "19988-19997",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216079"}
@inproceedings{bb221080,
AUTHOR = "Andonian, A. and Chen, S.X. and Hamid, R.",
TITLE = "Robust Cross-Modal Representation Learning with Progressive
Self-Distillation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16409-16420",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216080"}
@inproceedings{bb221081,
AUTHOR = "Lu, H.Y. and Fei, N. and Huo, Y.Q. and Gao, Y.Z. and Lu, Z.W. and Wen, J.R.",
TITLE = "COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for
Cross-Modal Retrieval",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15671-15680",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216081"}
@inproceedings{bb221082,
AUTHOR = "Abdelnabi, S. and Hasan, R. and Fritz, M.",
TITLE = "Open-Domain, Content-based, Multi-modal Fact-checking of
Out-of-Context Images via Online Resources",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "14920-14929",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216082"}
@inproceedings{bb221083,
AUTHOR = "Wang, Y. and Zhang, T. and Zhang, X. and Cui, Z. and Huang, Y. and Shen, P.C. and Li, S.X. and Yang, J.",
TITLE = "Wasserstein Coupled Graph Learning for Cross-Modal Retrieval",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1793-1802",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216083"}
@inproceedings{bb221084,
AUTHOR = "Cai, G. and Zhang, J. and Jiang, X.Y. and Gong, Y.F. and He, L. and Yu, F. and Peng, P. and Guo, X.W. and Huang, F.Y. and Sun, X.",
TITLE = "Ask amp;Confirm: Active Detail Enriching for Cross-Modal Retrieval
with Partial Query",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1815-1824",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216084"}
@inproceedings{bb221085,
AUTHOR = "Wen, K.Y. and Xia, J. and Huang, Y.Y. and Li, L.Y. and Xu, J.Y. and Shao, J.",
TITLE = "COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-training for
Vision-Language Representation",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "2188-2197",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216085"}
@inproceedings{bb221086,
AUTHOR = "Patrick, M. and Huang, P.Y. and Misra, I. and Metze, F. and Vedaldi, A. and Asano, Y.M. and Henriques, J.",
TITLE = "Space-Time Crop & Attend:
Improving Cross-modal Video Representation Learning",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "10540-10552",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216086"}
@inproceedings{bb221087,
AUTHOR = "Lin, M.X. and Yang, J. and Wang, H. and Lai, Y.K. and Jia, R. and Zhao, B.Q. and Gao, L.",
TITLE = "Single Image 3D Shape Retrieval via Cross-Modal Instance and Category
Contrastive Learning",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "11385-11395",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216087"}
@inproceedings{bb221088,
AUTHOR = "Changpinyo, S. and Pont Tuset, J. and Ferrari, V. and Soricut, R.",
TITLE = "Telling the What while Pointing to the Where:
Multimodal Queries for Image Retrieval",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "12116-12126",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216088"}
@inproceedings{bb221089,
AUTHOR = "Gabeur, V. and Nagrani, A. and Sun, C. and Alahari, K. and Schmid, C.",
TITLE = "Masking Modalities for Cross-modal Video Retrieval",
BOOKTITLE = WACV22,
YEAR = "2022",
PAGES = "2111-2120",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216089"}
@inproceedings{bb221090,
AUTHOR = "Galanopoulos, D. and Mezaris, V.",
TITLE = "Hard-Negatives or Non-Negatives? A Hard-Negative Selection Strategy
for Cross-Modal Retrieval Using the Improved Marginal Ranking Loss",
BOOKTITLE = ViRaL21,
YEAR = "2021",
PAGES = "2312-2316",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216090"}
@inproceedings{bb221091,
AUTHOR = "Jing, L.L. and Vahdani, E. and Tan, J.X. and Tian, Y.L.",
TITLE = "Cross-Modal Center Loss for 3D Cross-Modal Retrieval",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "3141-3150",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216091"}
@inproceedings{bb221092,
AUTHOR = "Feng, Y.L. and Zhu, H.Y. and Peng, D.Z. and Peng, X. and Hu, P.",
TITLE = "RONO: Robust Discriminative Learning with Noisy Labels for 2D-3D
Cross-Modal Retrieval",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11610-11619",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216092"}
@inproceedings{bb221093,
AUTHOR = "Hu, P. and Peng, X. and Zhu, H.Y. and Zhen, L. and Lin, J.",
TITLE = "Learning Cross-Modal Retrieval with Noisy Labels",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "5399-5409",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216093"}
@inproceedings{bb221094,
AUTHOR = "Almazan, J. and Ko, B. and Gu, G. and Larlus, D. and Kalantidis, Y.",
TITLE = "Granularity-Aware Adaptation for Image Retrieval Over Multiple Tasks",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XIV:389-406",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216094"}
@inproceedings{bb221095,
AUTHOR = "Chun, S. and Oh, S.J. and Sampaio de Rezende, R. and Kalantidis, Y. and Larlus, D.",
TITLE = "Probabilistic Embeddings for Cross-Modal Retrieval",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "8411-8420",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216095"}
@inproceedings{bb221096,
AUTHOR = "Croitoru, I. and Bogolin, S.V. and Leordeanu, M. and Jin, H.L. and Zisserman, A. and Albanie, S. and Liu, Y.",
TITLE = "TeachText:
CrossModal Generalized Distillation for Text-Video Retrieval",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "11563-11573",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216096"}
@inproceedings{bb221097,
AUTHOR = "Liu, Y. and Chen, Q.C. and Albanie, S.",
TITLE = "Adaptive Cross-Modal Prototypes for Cross-Domain Visual-Language
Retrieval",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "14949-14959",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216097"}
@inproceedings{bb221098,
AUTHOR = "Salvador, A. and Gundogdu, E. and Bazzani, L. and Donoser, M.",
TITLE = "Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers
and Self-supervised Learning",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "15470-15479",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216098"}
@inproceedings{bb221099,
AUTHOR = "Dzabraev, M. and Kalashnikov, M. and Komkov, S. and Petiushko, A.",
TITLE = "MDMMT: Multidomain Multimodal Transformer for Video Retrieval",
BOOKTITLE = HVU21,
YEAR = "2021",
PAGES = "3349-3358",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat830cm1.html#TT216099"}
Last update:Apr 10, 2024 at 09:54:40