@inproceedings{bb136900,
        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#TT132890"}

@inproceedings{bb136901,
        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#TT132891"}

@inproceedings{bb136902,
        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#TT132892"}

@inproceedings{bb136903,
        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#TT132893"}

@inproceedings{bb136904,
        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#TT132894"}

@inproceedings{bb136905,
        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#TT132894"}

@article{bb136906,
        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#TT132895"}

@article{bb136907,
        AUTHOR = "Zhang, Z. and Li, J. and Liang, Y.Q. and Yan, J. and Xiao, Y. and Su, X. and Yuan, Q.Q.",
        TITLE = "ECRformer: An efficient cloud removal Transformer with
semantic-decoupled learning for multimodal satellite imagery",
        JOURNAL = PandRS,
        VOLUME = "237",
        YEAR = "2026",
        PAGES = "323-338",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132896"}

@article{bb136908,
        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#TT132897"}

@article{bb136909,
        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#TT132898"}

@article{bb136910,
        AUTHOR = "Ren, Z.H. and Gou, S.P. and Guo, Z. and Mao, S.S. and Li, R.M.",
        TITLE = "A Mask-Guided Transformer Network with Topic Token for Remote Sensing
Image Captioning",
        JOURNAL = RS,
        VOLUME = "14",
        YEAR = "2022",
        NUMBER = "12",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132899"}

@article{bb136911,
        AUTHOR = "Ji, J.Y. and Ma, Y.W. and Sun, X.S. and Zhou, Y. and Wu, Y.J. and Ji, R.R.",
        TITLE = "Knowing What to Learn: A Metric-Oriented Focal Mechanism for Image
Captioning",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "4321-4335",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132900"}

@article{bb136912,
        AUTHOR = "Li, X. and Zhang, W.K. and Sun, X. and Gao, X.",
        TITLE = "Semantic-meshed and content-guided transformer for image captioning",
        JOURNAL = IET-CV,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "5",
        PAGES = "431-444",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132901"}

@article{bb136913,
        AUTHOR = "Xian, T.T. and Li, Z.X. and Tang, Z.J. and Ma, H.F.",
        TITLE = "Adaptive Path Selection for Dynamic Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "5762-5775",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132902"}

@article{bb136914,
        AUTHOR = "Cao, S. and An, G. and Zheng, Z.X. and Wang, Z.Y.",
        TITLE = "Vision-Enhanced and Consensus-Aware Transformer for Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "7005-7018",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132903"}

@article{bb136915,
        AUTHOR = "Jiang, W.T. and Zhou, W. and Hu, H.F.",
        TITLE = "Double-Stream Position Learning Transformer Network for Image
Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "7706-7718",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132904"}

@article{bb136916,
        AUTHOR = "Li, J.C. and Zhou, W. and Wang, K. and Hu, H.F.",
        TITLE = "Triple-Stream Commonsense Circulation Transformer Network for Image
Captioning",
        JOURNAL = CVIU,
        VOLUME = "249",
        YEAR = "2024",
        PAGES = "104165",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132905"}

@article{bb136917,
        AUTHOR = "Hu, J.T. and Yang, Y. and Yao, L. and An, Y.Z. and Pan, L.Y.",
        TITLE = "Position-guided transformer for image captioning",
        JOURNAL = IVC,
        VOLUME = "128",
        YEAR = "2022",
        PAGES = "104575",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132906"}

@article{bb136918,
        AUTHOR = "Wang, Z.G. and Shi, S. and Zhai, Z.R. and Wu, Y. and Yang, R.",
        TITLE = "ArCo: Attention-reinforced transformer with contrastive learning for
image captioning",
        JOURNAL = IVC,
        VOLUME = "128",
        YEAR = "2022",
        PAGES = "104570",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132907"}

@article{bb136919,
        AUTHOR = "Li, Z.X. and Wei, J.H. and Huang, F.C. and Ma, H.F.",
        TITLE = "Modeling graph-structured contexts for image captioning",
        JOURNAL = IVC,
        VOLUME = "129",
        YEAR = "2023",
        PAGES = "104591",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132908"}

@article{bb136920,
        AUTHOR = "Zhang, J. and Xie, Y.S. and Ding, W.C. and Wang, Z.",
        TITLE = "Cross on Cross Attention: Deep Fusion Transformer for Image
Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "33",
        YEAR = "2023",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "4257-4268",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132909"}

@article{bb136921,
        AUTHOR = "Lim, J.H. and Chan, C.S.",
        TITLE = "Mask-guided network for image captioning",
        JOURNAL = PRL,
        VOLUME = "173",
        YEAR = "2023",
        PAGES = "79-86",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132910"}

@article{bb136922,
        AUTHOR = "Li, Z.X. and Su, Q. and Chen, T.Y.",
        TITLE = "External knowledge-assisted Transformer for image captioning",
        JOURNAL = IVC,
        VOLUME = "140",
        YEAR = "2023",
        PAGES = "104864",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132911"}

@article{bb136923,
        AUTHOR = "Chen, J.Q.",
        TITLE = "Transform, contrast and tell:
Coherent entity-aware multi-image captioning",
        JOURNAL = CVIU,
        VOLUME = "238",
        YEAR = "2024",
        PAGES = "103878",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132912"}

@article{bb136924,
        AUTHOR = "Yang, X.B. and Tian, X. and Wu, J.S. and Yang, X.C. and Ma, S. and Qi, X. and Hou, Z.Q.",
        TITLE = "LLAFN-Generator: Learnable linear-attention with fast-normalization
for large-scale image captioning",
        JOURNAL = CVIU,
        VOLUME = "248",
        YEAR = "2024",
        PAGES = "104088",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132913"}

@article{bb136925,
        AUTHOR = "Yi, Y.H. and Liang, Y.K. and Kong, D.Z. and Tang, Z.W. and Peng, J.B.",
        TITLE = "Tag-inferring and tag-guided Transformer for image captioning",
        JOURNAL = IET-CV,
        VOLUME = "18",
        YEAR = "2024",
        NUMBER = "6",
        PAGES = "801-812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132914"}

@article{bb136926,
        AUTHOR = "Caffagni, D. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "Augmenting and mixing Transformers with synthetic data for image
captioning",
        JOURNAL = IVC,
        VOLUME = "162",
        YEAR = "2025",
        PAGES = "105661",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132915"}

@inproceedings{bb136927,
        AUTHOR = "Caffagni, D. and Barraco, M. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "Synthcap: Augmenting Transformers with Synthetic Data for Image
Captioning",
        BOOKTITLE = CIAP23,
        YEAR = "2023",
        PAGES = "I:112-123",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132916"}

@inproceedings{bb136928,
        AUTHOR = "Song, J.Y. and Pan, R.J. and Zhou, J. and Yang, H.",
        TITLE = "M-rat: a Multi-grained Retrieval Augmentation Transformer for Image
Captioning",
        BOOKTITLE = ACCV24,
        YEAR = "2024",
        PAGES = "III: 185-203",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132917"}

@inproceedings{bb136929,
        AUTHOR = "Lou, L.S. and Lu, K. and Xue, J.",
        TITLE = "Improved Transformer with Parallel Encoders for Image Captioning",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "4072-4075",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132918"}

@inproceedings{bb136930,
        AUTHOR = "Wang, Y.H. and Shang, L.",
        TITLE = "Generating Spatial-aware Captions for TextCaps",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "379-385",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132919"}

@inproceedings{bb136931,
        AUTHOR = "Feng, Y. and Maeda, K. and Ogawa, T. and Haseyama, M.",
        TITLE = "Human-Centric Image Retrieval with Gaze-Based Image Captioning",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "3828-3832",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132920"}

@inproceedings{bb136932,
        AUTHOR = "Yang, X. and Wang, Y. and Chen, H. and Li, J.",
        TITLE = "CSTNET: Enhancing Global-To-Local Interactions for Image Captioning",
        BOOKTITLE = ICIP22,
        YEAR = "2022",
        PAGES = "1861-1865",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132921"}

@inproceedings{bb136933,
        AUTHOR = "Nguyen, V.Q. and Suganuma, M. and Okatani, T.",
        TITLE = "GRIT: Faster and Better Image Captioning Transformer Using Dual Visual
Features",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "XXXVI:167-184",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132922"}

@inproceedings{bb136934,
        AUTHOR = "Vo, D.M. and Chen, H. and Sugimoto, A. and Nakayama, H.",
        TITLE = "NOC-REK: Novel Object Captioning with Retrieved Vocabulary from
External Knowledge",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17979-17987",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132923"}

@inproceedings{bb136935,
        AUTHOR = "Yuan, Z.H. and Yan, X. and Liao, Y.H. and Guo, Y. and Li, G.B. and Cui, S.G. and Li, Z.",
        TITLE = "X-Trans2Cap:
Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "8553-8563",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132924"}

@inproceedings{bb136936,
        AUTHOR = "Liu, B. and Wang, D. and Yang, X. and Zhou, Y. and Yao, R. and Shao, Z.W. and Zhao, J.Q.",
        TITLE = "Show, Deconfound and Tell: Image Captioning with Causal Inference",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "18020-18029",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132925"}

@inproceedings{bb136937,
        AUTHOR = "Fang, Z.Y. and Wang, J.F. and Hu, X.W. and Liang, L. and Gan, Z. and Wang, L.J. and Yang, Y.Z. and Liu, Z.C.",
        TITLE = "Injecting Semantic Concepts into End-to-End Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17988-17998",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132926"}

@inproceedings{bb136938,
        AUTHOR = "Li, Y. and Pan, Y.W. and Yao, T. and Mei, T.",
        TITLE = "Comprehending and Ordering Semantics for Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17969-17978",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132927"}

@inproceedings{bb136939,
        AUTHOR = "Fei, Z.C. and Yan, X. and Wang, S.H. and Tian, Q.",
        TITLE = "DeeCap: Dynamic Early Exiting for Efficient Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "12206-12216",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132928"}

@inproceedings{bb136940,
        AUTHOR = "Wu, M.R. and Zhang, X.Y. and Sun, X.S. and Zhou, Y. and Chen, C. and Gu, J.X. and Sun, X. and Ji, R.R.",
        TITLE = "DIFNet: Boosting Visual Information Flow for Image Captioning",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "17999-18008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132929"}

@inproceedings{bb136941,
        AUTHOR = "Rio Torto, I. and Cardoso, J.S. and Teixeira, L.F.",
        TITLE = "From Captions to Explanations: A Multimodal Transformer-based
Architecture for Natural Language Explanation Generation",
        BOOKTITLE = IbPRIA22,
        YEAR = "2022",
        PAGES = "54-65",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132930"}

@inproceedings{bb136942,
        AUTHOR = "Chen, H.S. and Wang, Y. and Yang, X. and Li, J.",
        TITLE = "Captioning Transformer With Scene Graph Guiding",
        BOOKTITLE = ICIP21,
        YEAR = "2021",
        PAGES = "2538-2542",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132931"}

@inproceedings{bb136943,
        AUTHOR = "Zhang, X.Y. and Sun, X.S. and Luo, Y.P. and Ji, J.Y. and Zhou, Y. and Wu, Y.J. and Huang, F.Y. and Ji, R.R.",
        TITLE = "RSTNet:
Captioning with Adaptive Attention on Visual and Non-Visual Words",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "15460-15469",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132932"}

@inproceedings{bb136944,
        AUTHOR = "He, S. and Liao, W.T. and Tavakoli, H.R. and Yang, M. and Rosenhahn, B. and Pugeault, N.",
        TITLE = "Image Captioning Through Image Transformer",
        BOOKTITLE = ACCV20,
        YEAR = "2020",
        PAGES = "IV:153-169",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132933"}

@inproceedings{bb136945,
        AUTHOR = "Cornia, M. and Stefanini, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "Meshed-Memory Transformer for Image Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10575-10584",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132934"}

@inproceedings{bb136946,
        AUTHOR = "Tran, A. and Mathews, A. and Xie, L.",
        TITLE = "Transform and Tell: Entity-Aware News Image Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "13032-13042",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132935"}

@inproceedings{bb136947,
        AUTHOR = "Li, G. and Zhu, L. and Liu, P. and Yang, Y.",
        TITLE = "Entangled Transformer for Image Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "8927-8936",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607tic2.html#TT132936"}

@article{bb136948,
        AUTHOR = "Sharma, D. and Chattopadhyay, C.",
        TITLE = "High-level feature aggregation for fine-grained architectural floor
plan retrieval",
        JOURNAL = IET-CV,
        VOLUME = "12",
        YEAR = "2018",
        NUMBER = "5",
        MONTH = "August",
        PAGES = "702-709",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132937"}

@inproceedings{bb136949,
        AUTHOR = "Sharma, D. and Chattopadhyay, C. and Harit, G.",
        TITLE = "A unified framework for semantic matching of architectural floorplans",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "2422-2427",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132938"}

@article{bb136950,
        AUTHOR = "Ham, B. and Cho, M.S. and Schmid, C. and Ponce, J.",
        TITLE = "Proposal Flow: Semantic Correspondences from Object Proposals",
        JOURNAL = PAMI,
        VOLUME = "40",
        YEAR = "2018",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1711-1725",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132939"}

@inproceedings{bb136951,
        AUTHOR = "Ham, B. and Cho, M.S. and Schmid, C. and Ponce, J.",
        TITLE = "Proposal Flow",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "3475-3484",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132940"}

@article{bb136952,
        AUTHOR = "Xiao, T.H. and Liu, S.F. and de Mello, S. and Yu, Z.D. and Kautz, J. and Yang, M.H.",
        TITLE = "Learning Contrastive Representation for Semantic Correspondence",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1293-1309",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132941"}

@article{bb136953,
        AUTHOR = "Yang, M.H. and Kautz, J. and Yu, Z.D. and de Mello, S. and Liu, S.F. and Xiao, T.H.",
        TITLE = "Learning Contrastive Representation for Semantic Correspondence",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "1607-1607",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132941"}

@inproceedings{bb136954,
        AUTHOR = "Yuan, W.T. and Eckart, B. and Kim, K. and Jampani, V. and Fox, D. and Kautz, J.",
        TITLE = "DeepGMR: Learning Latent Gaussian Mixture Models for Registration",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "V:733-750",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132942"}

@inproceedings{bb136955,
        AUTHOR = "Eckart, B. and Kim, K. and Kautz, J.",
        TITLE = "HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XV: 730-746",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132943"}

@article{bb136956,
        AUTHOR = "He, J.F. and Zhang, T.Z. and Zheng, Y.H. and Xu, M.L. and Zhang, Y.D. and Wu, F.",
        TITLE = "Consistency Graph Modeling for Semantic Correspondence",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "4932-4946",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132944"}

@article{bb136957,
        AUTHOR = "Jeon, S. and Kim, S. and Min, D.B. and Sohn, K.H.",
        TITLE = "Pyramidal Semantic Correspondence Networks",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "9102-9118",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132945"}

@article{bb136958,
        AUTHOR = "Cao, C.Q. and Zhang, Y.N.",
        TITLE = "Learning to Compare Relation:
Semantic Alignment for Few-Shot Learning",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "1462-1474",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132946"}

@article{bb136959,
        AUTHOR = "Cheng, J. and Hao, F.S. and Liu, L. and Tao, D.C.",
        TITLE = "Imposing Semantic Consistency of Local Descriptors for Few-Shot
Learning",
        JOURNAL = IP,
        VOLUME = "31",
        YEAR = "2022",
        PAGES = "1587-1600",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132947"}

@article{bb136960,
        AUTHOR = "Hao, F.S. and He, F.X. and Cheng, J. and Tao, D.C.",
        TITLE = "Global-Local Interplay in Semantic Alignment for Few-Shot Learning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "4351-4363",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132948"}

@inproceedings{bb136961,
        AUTHOR = "Hao, F.S. and He, F.X. and Cheng, J. and Wang, L. and Cao, J. and Tao, D.C.",
        TITLE = "Collect and Select:
Semantic Alignment Metric Learning for Few-Shot Learning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "8459-8468",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132949"}

@article{bb136962,
        AUTHOR = "Liu, H. and Wang, T. and Li, Y.D. and Lang, C.Y. and Jin, Y. and Ling, H.B.",
        TITLE = "Joint Graph Learning and Matching for Semantic Feature Correspondence",
        JOURNAL = PR,
        VOLUME = "134",
        YEAR = "2023",
        PAGES = "109059",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132950"}

@article{bb136963,
        AUTHOR = "Sachdeva, R. and Cordeiro, F.R. and Belagiannis, V. and Reid, I.D. and Carneiro, G.",
        TITLE = "ScanMix: Learning from Severe Label Noise via Semantic Clustering and
Semi-Supervised Learning",
        JOURNAL = PR,
        VOLUME = "134",
        YEAR = "2023",
        PAGES = "109121",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132951"}

@article{bb136964,
        AUTHOR = "Xu, X. and Xu, X. and Shen, F.M. and Li, Y.J.",
        TITLE = "Semantic-Aligned Attention With Refining Feature Embedding for
Few-Shot Image Classification",
        JOURNAL = ITS,
        VOLUME = "23",
        YEAR = "2022",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "25458-25468",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132952"}

@article{bb136965,
        AUTHOR = "Yang, Z.Q. and Zhang, Y.Q. and Du, Y.X. and Tong, C.",
        TITLE = "Semantic-aligned reinforced attention model for zero-shot learning",
        JOURNAL = IVC,
        VOLUME = "128",
        YEAR = "2022",
        PAGES = "104586",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132953"}

@article{bb136966,
        AUTHOR = "Wang, J. and Zhang, Z.Q. and Shi, Z.H. and Cai, J.Y. and Ji, S.W. and Wu, F.",
        TITLE = "Duality-Induced Regularizer for Semantic Matching Knowledge Graph
Embeddings",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "1652-1667",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132954"}

@article{bb136967,
        AUTHOR = "Liu, W.X. and Zhong, X. and Jia, X.M. and Jiang, K. and Lin, C.W.",
        TITLE = "Actor-Aware Alignment Network for Action Recognition",
        JOURNAL = SPLetters,
        VOLUME = "29",
        YEAR = "2022",
        PAGES = "2597-2601",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132955"}

@article{bb136968,
        AUTHOR = "Wang, Z. and Fu, Z.H. and Guo, Y.L. and Li, Z. and Yu, Q.F.",
        TITLE = "Local-to-Global Cost Aggregation for Semantic Correspondence",
        JOURNAL = CirSysVideo,
        VOLUME = "33",
        YEAR = "2023",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "1209-1222",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132956"}

@article{bb136969,
        AUTHOR = "Xu, W.J. and Wang, J.N. and Wei, Z.W. and Peng, M. and Wu, Y.R.",
        TITLE = "Deep Semantic-Visual Alignment for zero-shot remote sensing image
scene classification",
        JOURNAL = PandRS,
        VOLUME = "198",
        YEAR = "2023",
        PAGES = "140-152",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132957"}

@article{bb136970,
        AUTHOR = "Yang, J.Q. and Shen, Q. and Xie, C.",
        TITLE = "Generation-based contrastive model with semantic alignment for
generalized zero-shot learning",
        JOURNAL = IVC,
        VOLUME = "137",
        YEAR = "2023",
        PAGES = "104758",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132958"}

@article{bb136971,
        AUTHOR = "Duan, Z.H. and Ma, Z. and Zhu, F.Q.",
        TITLE = "Unified Architecture Adaptation for Compressed Domain Semantic
Inference",
        JOURNAL = CirSysVideo,
        VOLUME = "33",
        YEAR = "2023",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "4108-4121",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132959"}

@article{bb136972,
        AUTHOR = "Xu, H.Y. and Liao, J. and Liu, H.P. and Sun, Y.X.",
        TITLE = "Learning Semantic Alignment Using Global Features and Multi-Scale
Confidence",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "897-910",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132960"}

@article{bb136973,
        AUTHOR = "Liu, J. and Xie, J.L. and Zhou, F.Y. and He, S.F.",
        TITLE = "Triadic temporal-semantic alignment for weakly-supervised video
moment retrieval",
        JOURNAL = PR,
        VOLUME = "156",
        YEAR = "2024",
        PAGES = "110819",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132961"}

@article{bb136974,
        AUTHOR = "Zhang, T. and Fang, H. and Zhang, H. and Gao, J.L. and Lu, X. and Nie, X. and Yin, Y.L.",
        TITLE = "Learning Feature Semantic Matching for Spatio-Temporal Video
Grounding",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "9268-9279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132962"}

@article{bb136975,
        AUTHOR = "Wu, R.J. and Guo, W. and Liu, Y. and Sun, C.H.",
        TITLE = "High-Precision Heterogeneous Satellite Image Manipulation
Localization: Feature Point Rules and Semantic Similarity Measurement",
        JOURNAL = RS,
        VOLUME = "16",
        YEAR = "2024",
        NUMBER = "19",
        PAGES = "3719",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132963"}

@article{bb136976,
        AUTHOR = "Giang, K.T. and Song, S. and Jo, S.",
        TITLE = "TopicFM+: Boosting Accuracy and Efficiency of Topic-Assisted Feature
Matching",
        JOURNAL = IP,
        VOLUME = "33",
        YEAR = "2024",
        PAGES = "6016-6028",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132964"}

@article{bb136977,
        AUTHOR = "Liao, G. and Zhou, K. and Bao, Z.Y. and Liu, K.L. and Li, Q.",
        TITLE = "OV-NeRF: Open-Vocabulary Neural Radiance Fields With Vision and
Language Foundation Models for 3D Semantic Understanding",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "12923-12936",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132965"}

@article{bb136978,
        AUTHOR = "Shi, W. and Zhu, R.H. and Li, S.",
        TITLE = "Unsupervised Class-Imbalanced Domain Adaptation With Pairwise
Adversarial Training and Semantic Alignment",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "12411-12424",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132966"}

@article{bb136979,
        AUTHOR = "Zhang, H. and Xu, L.M. and Lai, S.Q. and Shao, W.Q. and Zheng, N.N. and Luo, P. and Qiao, Y. and Zhang, K.P.",
        TITLE = "Open-Vocabulary Animal Keypoint Detection with Semantic-Feature
Matching",
        JOURNAL = IJCV,
        VOLUME = "132",
        YEAR = "2024",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "5741-5758",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132967"}

@article{bb136980,
        AUTHOR = "Xu, L.M. and Li, H.Q. and Zheng, B. and Li, W.S. and Lv, J.C.",
        TITLE = "Deep Lifelong Cross-Modal Hashing",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "13478-13493",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132968"}

@article{bb136981,
        AUTHOR = "Dong, M.P. and Li, F. and Li, Z.B. and Liu, X.",
        TITLE = "PRSN: Prototype resynthesis network with cross-image semantic
alignment for few-shot image classification",
        JOURNAL = PR,
        VOLUME = "159",
        YEAR = "2025",
        PAGES = "111122",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132969"}

@article{bb136982,
        AUTHOR = "Gonzalez, L.H.R. and Florez, S.L. and Gonzalez Briones, A. and de la Prieta, F.",
        TITLE = "Semantic scene understanding through advanced object context analysis
in image",
        JOURNAL = CVIU,
        VOLUME = "252",
        YEAR = "2025",
        PAGES = "104299",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132970"}

@article{bb136983,
        AUTHOR = "Shi, Y. and Li, R.X. and Gan, L. and Zhan, D.C. and Ye, H.J.",
        TITLE = "Generalized Conditional Similarity Learning via Semantic Matching",
        JOURNAL = PAMI,
        VOLUME = "47",
        YEAR = "2025",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "3847-3862",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132971"}

@article{bb136984,
        AUTHOR = "Dong, S.H. and Xie, W.Y. and Yang, D. and Li, Y.S. and Zhang, J.Q. and Tian, J.Y. and Lei, J.",
        TITLE = "SeaDATE: Remedy Dual-Attention Transformer With Semantic Alignment
via Contrast Learning for Multimodal Object Detection",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "4713-4726",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132972"}

@article{bb136985,
        AUTHOR = "Tan, Y.B. and Wang, H. and Cai, R.F. and Gao, L.L. and Yu, Z.H. and Li, X.",
        TITLE = "Spatial Proximity Relations-Driven Semantic Representation for
Geospatial Entity Categories",
        JOURNAL = IJGI,
        VOLUME = "14",
        YEAR = "2025",
        NUMBER = "6",
        PAGES = "233",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132973"}

@article{bb136986,
        AUTHOR = "Wei, Z. and Hou, Z.Y. and Zhou, X.Z.",
        TITLE = "Eliminating Non-Overlapping Semantic Misalignment for Cross-Modal
Medical Retrieval",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "3510-3514",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132974"}

@article{bb136987,
        AUTHOR = "Wang, Z.H. and Du, S.L. and Yan, Y.P. and Xiao, G. and Lu, X.B.",
        TITLE = "Tex2Sem: Learning From Textures to Semantics for Robust Semantic
Correspondence",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "10875-10890",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132975"}

@article{bb136988,
        AUTHOR = "Tan, X.L. and Chen, G.Z. and Zhang, X.D. and Wang, T. and Wang, J.Q. and Wang, K. and Miao, T.X.",
        TITLE = "TripleS: Mitigating multi-task learning conflicts for semantic change
detection in high-resolution remote sensing imagery",
        JOURNAL = PandRS,
        VOLUME = "230",
        YEAR = "2025",
        PAGES = "374-401",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132976"}

@article{bb136989,
        AUTHOR = "Jiang, Q. and Lu, X.Y. and Liang, D. and Du, S.L.",
        TITLE = "SemMatcher: Semantic-aware feature matching with neighborhood
consensus",
        JOURNAL = JVCIR,
        VOLUME = "113",
        YEAR = "2025",
        PAGES = "104611",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132977"}

@article{bb136990,
        AUTHOR = "Jin, H.L. and Li, H.Y.",
        TITLE = "KPLNet: Keypoint prototype learning for zero image semantic
correspondence",
        JOURNAL = PR,
        VOLUME = "172",
        YEAR = "2026",
        PAGES = "112702",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132978"}

@article{bb136991,
        AUTHOR = "Jin, H.L. and Li, H.Y.",
        TITLE = "Dual Consistency Matching for Semi-Supervised Semantic Correspondence",
        JOURNAL = IJCV,
        VOLUME = "134",
        YEAR = "2026",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "13",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132979"}

@article{bb136992,
        AUTHOR = "Liu, W. and Tian, N. and Shao, Y. and Zhao, W.",
        TITLE = "Object-level semantic alignment for enhancing fidelity in
text-to-image generation with diffusion models",
        JOURNAL = IVC,
        VOLUME = "167",
        YEAR = "2026",
        PAGES = "105923",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132980"}

@article{bb136993,
        AUTHOR = "Zhang, K. and Li, X.H. and Lu, J.Y. and Han, K.",
        TITLE = "Semantic Correspondence: Unified Benchmarking and a Strong Baseline",
        JOURNAL = PAMI,
        VOLUME = "48",
        YEAR = "2026",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "3911-3930",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132981"}

@article{bb136994,
        AUTHOR = "Bi, Q. and Yi, J.J. and Zhan, H. and Ji, W. and Xia, G.S.",
        TITLE = "Revisiting Fine-Grained Image Analysis by Semantic-Part Alignment",
        JOURNAL = IP,
        VOLUME = "35",
        YEAR = "2026",
        PAGES = "670-684",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132982"}

@article{bb136995,
        AUTHOR = "Fang, X. and Li, Z.Z. and Ma, J.Y.",
        TITLE = "SigMa: Semantic Similarity-Guided Semi-Dense Feature Matching",
        JOURNAL = IP,
        VOLUME = "35",
        YEAR = "2026",
        PAGES = "872-887",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132983"}

@article{bb136996,
        AUTHOR = "Yuan, H. and Zhang, B. and Wang, Y. and Qiang, Q.Y.",
        TITLE = "From Structural Degradation to Semantic Misalignment: A Unified
Frequency-Aware Compensation Framework for Remote Sensing Object
Detection",
        JOURNAL = RS,
        VOLUME = "18",
        YEAR = "2026",
        NUMBER = "5",
        PAGES = "777",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132984"}

@article{bb136997,
        AUTHOR = "Zhang, Y.Z. and Lian, W.Q. and Tu, Z.W. and Xue, L. and Wang, T. and Tao, R.",
        TITLE = "Structure-Aware Dual Semantic Augmentation Alignment for Unsupervised
Person Re-Identification",
        JOURNAL = SPLetters,
        VOLUME = "33",
        YEAR = "2026",
        PAGES = "1351-1355",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132985"}

@article{bb136998,
        AUTHOR = "Peng, L. and Ye, Y.X. and Liu, C. and Che, H. and Wang, F. and Yu, Z.W. and Wu, S. and Wong, H.S.",
        TITLE = "SMART: Semantic Matching Contrastive Learning for Partially
View-Aligned Clustering",
        JOURNAL = CirSysVideo,
        VOLUME = "36",
        YEAR = "2026",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "4357-4370",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132986"}

@article{bb136999,
        AUTHOR = "Zhang, H. and Du, R. and Wang, B.S. and Nie, F.P. and Li, X.L.",
        TITLE = "Flexible multi-view feature selection with semi-supervised label
semantic alignment",
        JOURNAL = PR,
        VOLUME = "178",
        YEAR = "2026",
        PAGES = "113386",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT132987"}

Last update:Jun 4, 2026 at 16:38:45