@inproceedings{bb135400,
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#TT131393"}
@inproceedings{bb135401,
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#TT131394"}
@inproceedings{bb135402,
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#TT131395"}
@inproceedings{bb135403,
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#TT131395"}
@article{bb135404,
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#TT131396"}
@article{bb135405,
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#TT131397"}
@article{bb135406,
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#TT131398"}
@article{bb135407,
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#TT131399"}
@article{bb135408,
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#TT131400"}
@article{bb135409,
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#TT131401"}
@article{bb135410,
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#TT131402"}
@article{bb135411,
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#TT131403"}
@article{bb135412,
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#TT131404"}
@article{bb135413,
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#TT131405"}
@article{bb135414,
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#TT131406"}
@article{bb135415,
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#TT131407"}
@article{bb135416,
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#TT131408"}
@article{bb135417,
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#TT131409"}
@article{bb135418,
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#TT131410"}
@article{bb135419,
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#TT131411"}
@article{bb135420,
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#TT131412"}
@article{bb135421,
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#TT131413"}
@article{bb135422,
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#TT131414"}
@article{bb135423,
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#TT131415"}
@inproceedings{bb135424,
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#TT131416"}
@inproceedings{bb135425,
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#TT131417"}
@inproceedings{bb135426,
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#TT131418"}
@inproceedings{bb135427,
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#TT131419"}
@inproceedings{bb135428,
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#TT131420"}
@inproceedings{bb135429,
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#TT131421"}
@inproceedings{bb135430,
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#TT131422"}
@inproceedings{bb135431,
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#TT131423"}
@inproceedings{bb135432,
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#TT131424"}
@inproceedings{bb135433,
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#TT131425"}
@inproceedings{bb135434,
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#TT131426"}
@inproceedings{bb135435,
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#TT131427"}
@inproceedings{bb135436,
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#TT131428"}
@inproceedings{bb135437,
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#TT131429"}
@inproceedings{bb135438,
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#TT131430"}
@inproceedings{bb135439,
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#TT131431"}
@inproceedings{bb135440,
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#TT131432"}
@inproceedings{bb135441,
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#TT131433"}
@inproceedings{bb135442,
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#TT131434"}
@inproceedings{bb135443,
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#TT131435"}
@inproceedings{bb135444,
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#TT131436"}
@article{bb135445,
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#TT131437"}
@inproceedings{bb135446,
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#TT131438"}
@article{bb135447,
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#TT131439"}
@inproceedings{bb135448,
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#TT131440"}
@article{bb135449,
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#TT131441"}
@article{bb135450,
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#TT131441"}
@inproceedings{bb135451,
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#TT131442"}
@inproceedings{bb135452,
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#TT131443"}
@article{bb135453,
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#TT131444"}
@article{bb135454,
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#TT131445"}
@article{bb135455,
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#TT131446"}
@article{bb135456,
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#TT131447"}
@article{bb135457,
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#TT131448"}
@inproceedings{bb135458,
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#TT131449"}
@article{bb135459,
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#TT131450"}
@article{bb135460,
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#TT131451"}
@article{bb135461,
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#TT131452"}
@article{bb135462,
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#TT131453"}
@article{bb135463,
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#TT131454"}
@article{bb135464,
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#TT131455"}
@article{bb135465,
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#TT131456"}
@article{bb135466,
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#TT131457"}
@article{bb135467,
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#TT131458"}
@article{bb135468,
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#TT131459"}
@article{bb135469,
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#TT131460"}
@article{bb135470,
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#TT131461"}
@article{bb135471,
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#TT131462"}
@article{bb135472,
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#TT131463"}
@article{bb135473,
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#TT131464"}
@article{bb135474,
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#TT131465"}
@article{bb135475,
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#TT131466"}
@article{bb135476,
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#TT131467"}
@article{bb135477,
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#TT131468"}
@article{bb135478,
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#TT131469"}
@article{bb135479,
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#TT131470"}
@article{bb135480,
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#TT131471"}
@article{bb135481,
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#TT131472"}
@article{bb135482,
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#TT131473"}
@article{bb135483,
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#TT131474"}
@article{bb135484,
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#TT131475"}
@article{bb135485,
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#TT131476"}
@article{bb135486,
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#TT131477"}
@article{bb135487,
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#TT131478"}
@article{bb135488,
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#TT131479"}
@inproceedings{bb135489,
AUTHOR = "Shaik, F.A. and Acharjee, S. and Oussalah, M.",
TITLE = "Towards Trustworthy Disaster Severity Scoring: Combining Semantic
Alignment and Chain-of-Thought LLMs",
BOOKTITLE = IPTA25,
YEAR = "2025",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131480"}
@inproceedings{bb135490,
AUTHOR = "Wang, Z.Q. and Wang, J. and Wen, G.H.",
TITLE = "HSBS: Comprehensive Boosting Of Facial Expression Recognition Via
Hierarchical Semantic And Batch-Wise Similarity",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "755-760",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131481"}
@inproceedings{bb135491,
AUTHOR = "Hazman, M. and McKeever, S. and Griffith, J.",
TITLE = "Beyond Meme Templates:
Limitations of Visual Similarity Measures in Meme Matching",
BOOKTITLE = IPTA25,
YEAR = "2025",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131482"}
@inproceedings{bb135492,
AUTHOR = "Chanchlani, V. and Himmatsinghka, V. and Himmatsinghka, A. and Sandhan, J. and Sandhan, T.",
TITLE = "Tagsim: Topic-Informed Attention Guided Similarity Metric for Image
Caption Comparison",
BOOKTITLE = ICIP25,
YEAR = "2025",
PAGES = "2008-2013",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131483"}
@inproceedings{bb135493,
AUTHOR = "Ranario, E. and Lundqvist, L. and Yun, H. and Bailey, B.N. and Earles, J.M.",
TITLE = "AGILE: A Diffusion-Based Attention-Guided Image and Label Translation
for Efficient Cross-Domain Plant Trait Identification",
BOOKTITLE = AgriVision25,
YEAR = "2025",
PAGES = "5392-5401",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131484"}
@inproceedings{bb135494,
AUTHOR = "Wang, S.L. and Lin, W. and Huang, H. and Wang, H.T. and Cai, S. and Han, W.K. and Jin, T. and Chen, J.Y. and Sun, J.C. and Zhu, J. and Zhao, Z.",
TITLE = "Towards Transformer-Based Aligned Generation with Self-Coherence
Guidance",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18455-18464",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131485"}
@inproceedings{bb135495,
AUTHOR = "Jose, C. and Moutakanni, T. and Kang, D. and Baldassarre, F. and Darcet, T. and Xu, H. and Li, D. and Szafraniec, M. and Ramamonjisoa, M. and Oquab, M. and Simeoni, O. and Vo, H.V. and Labatut, P. and Bojanowski, P.",
TITLE = "DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level
Vision-Language Alignment",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24905-24916",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131486"}
@inproceedings{bb135496,
AUTHOR = "Tang, Y.T. and Guo, Y.X. and Li, D. and Peng, C.",
TITLE = "SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D
Reconstruction",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "26810-26821",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131487"}
@inproceedings{bb135497,
AUTHOR = "Ding, Z.H. and Chen, G.L. and Zhang, Q. and Wu, H. and Qin, J.",
TITLE = "CSC-PA: Cross-image Semantic Correlation via Prototype Attentions for
Single-network Semi-supervised Breast Tumor Segmentation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "15632-15641",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131488"}
@inproceedings{bb135498,
AUTHOR = "Huang, J. and Liu, T. and Wu, Y.H. and Qu, X. and Liu, L.Q. and Hu, X.L.",
TITLE = "MTADiffusion: Mask Text Alignment Diffusion Model for Object
Inpainting",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18325-18334",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131489"}
@inproceedings{bb135499,
AUTHOR = "Qian, Q. and Chen, H.S. and Tomizuka, M. and Keutzer, K. and Wang, Q.Q. and Xu, C.F.",
TITLE = "Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic
Correspondence",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "11579-11589",
BIBSOURCE = "http://www.visionbib.com/bibliography/match607seco3.html#TT131490"}
Last update:Feb 17, 2026 at 20:06:16