Transductive Multi-View Zero-Shot Learning
Open accessThe DOI matches its Crossref record; 72 of the 74 references it cites were found in a registry or an index.
Abstract
Most existing zero-shot learning approaches exploit transfer learning via an intermediate semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A projection from a low-level feature space to the semantic representation space is learned from the auxiliary dataset and applied without adaptation to the target dataset. In this paper we identify two inherent limitations with these approaches. First, due to having disjoint and potentially unrelated classes, the projection functions learned from the auxiliary dataset/domain are biased when applied directly to the target dataset/domain. We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding, to solve it. The second limitation is the prototype sparsity problem which refers to the fact that for each target class, only a single prototype is available for zero-shot learning given a semantic representation. To overcome this problem, a novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space. It effectively exploits the complementary information offered by different semantic representations and takes advantage of the manifold structures of multiple representation spaces in a coherent manner. We demonstrate through extensive experiments that the proposed approach (1) rectifies the projection shift between the auxiliary and target domains, (2) exploits the complementarity of multiple semantic representations, (3) significantly outperforms existing methods for both zero-shot and N-shot recognition on three image and video benchmark datasets, and (4) enables novel cross-view annotation tasks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“What is interesting to see here is that Overfeat > Decaf since both are based on the same Convolutional Neural Network (CNN) model of [32].”
BackgroundCollective dynamics of ‘small-world’ networks
Watts, D. J., & Strogatz, S. H. (1998) · Nature · doi:10.1038/30918 · Cited by 43,060
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 1×
“However, this does not effectively exploit the multi-view complementarity, and suffers from labelled data (prototype) sparsity.”
Background(2008) · Journal of Machine Learning Research · Cited by 33,051
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239 · cited 1×
“The advantages of heterogeneous hypergraphs We argue that the pairwise similarity of heterogeneous hypergraph is a distributed representation [3].”
BackgroundRecognition-by-components: A theory of human image understanding.
Biederman, I. (1987) · Psychological Review · doi:10.1037/0033-295x.94.2.115 · Cited by 5,621 · cited 1×
“Humans can distinguish 30,000 basic object classes [3] and many more subordinate ones (e.g. breeds of dogs).”
BackgroundLearning Deep Architectures for AI
Bengio, Y. (2009) · now publishers, Inc. eBooks · doi:10.1561/9781601982957 · Cited by 4,941
Semi-Supervised Learning Literature Survey
Zhu, X. (2005) · Minds at UW (University of Wisconsin) · Cited by 4,505
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 1×
“In addition, the Decaf (D) [10] feature is also considered for AwA.”
Background
Research works printed but not linked: 5
- [39] E. Rosch. Classification of real-world objects: Origins and representations in cognition. Thinking: Readings in Cognitive Science , 1977. -
- [32] T. Mikolov, K. Chen, G. Corrado, and J. Dean. Efficient estimation of word representation in vector space. In Proceedings of Workshop at ICLR , 2013. -
- [33] M. Palatucci, G. Hinton, D. Pomerleau, and T. M. Mitchell. Zeroshot learning with semantic output codes. In NIPS , 2009. -
- [34] D. Parikh and K. Grauman. Relative attributes. In ICCV , 2011. -
- [21] Y. Huang, Q. Liu, and D. Metaxas. Video object segmentation by hypergraph cut. In CVPR , 2009. -
Cited by
Items 401–500 of 512
Learning exclusive discriminative semantic information for zero-shot learning
Mi, J., Zhang, Z., Tai, D., Zhou, L., & Jia, W. (2022) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-022-01661-0 · Cited by 2
“Meanwhile, most existing ZSL methods learn visual-semantic projection from visual features to semantic attributes, but rarely consider the reconstruction of image’s visual features, which inevitably brings the domain shift problem [9].”
Weighted Multi-view Zero-shot Learning Prototype Shift Model in Fault Diagnosis
Liu, Z., Yang, R., Chen, X., & Xue, Y. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055280 · Cited by 2
Transductive semantic knowledge graph propagation for zero-shot learning
Zhang, H., Que, H., Ren, J., & Wu, Z. (2023) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2023.07.009 · Cited by 2
Research on End Face Defect Detection of Small Sample Workpiece Based on Meta Learning
Yang, Y., Xia, D., Sun, H., Luo, D., & Luo, W. (2022) · International Symposium on Smart and Healthy Cities (ISHC) · doi:10.1109/ishc56805.2022.00017 · Cited by 2
“Therefore, within the meta-learning framework, it is possible to build few-shot classifiers through end-to-end training[2,3].”
BackgroundMulti-modal subspace learning with dropout regularization for cross-modal recognition and retrieval
Cao, G., Waris, M. A., Iosifidis, A., & Gabbouj, M. (2016) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2016.7821032 · Cited by 2
“Traditional methods such as CCA and PLS accept only pairwise information, and it has been shown to provide performance gain from more modalities [8].”
MethodA survey on Zero-shot learning
Song, F., & Chen, Y. (2016) · Cited by 2
A Simple yet Effective Model for Zero-Shot Learning
Cao, X. H., Zoran Obradovic, A., & Kim, K. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00089 · Cited by 2
“Evidence [14, 41, 42, 44] showed that the classification accuracy could be further improved by considering the structures in the feature space of the unseen examples.”
BackgroundDing, Z., Zhao, H., & Fu, Y. (2018) · Advanced information and knowledge processing · doi:10.1007/978-3-030-00734-8_6 · Cited by 2
Self-citationRGB-NIR image categorization with prior knowledge transfer
Peng, X., Li, Y., Wei, X. H., Luo, J., & Murphey, Y. L. (2018) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-018-0388-1 · Cited by 2
Fine-grained Human Action Recognition Based on Zero-Shot Learning
Zhao, Y., Shi, P. A., & You, J. (2019) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess47205.2019.9040818 · Cited by 2
“The zero-shot learning method based on word vectors [6, 7, 8, 9, 10] maps the original image pixels or image features to the word vector space and the label space to the word vector space.”
MethodMirza, B., Syed, T., Khan, B., & Malik, Y. (2021) · ACM Computing Surveys · doi:10.1145/3427476 · Cited by 4
“However, these suffer from domain shift problem, which occurs when unseen classes are dislocated due to training time bias from the seen classes [53].”
BackgroundA Generative Model for Zero-Shot Learning via Wasserstein Auto-encoder
Luo, X., Cai, Z., Wu, F., & Xiao-Yuan, J. (2020) · IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · doi:10.1109/iciba50161.2020.9276900 · Cited by 2
“978-1-7281-5224-0/20/$31.00 ©2020 IEEE lems [34] which is that the same attribute may perform different visual features in different classes.”
BackgroundInfluentialMulti-Knowledge Fusion Network for Generalized Zero-Shot Learning
Xiang, H., Xie, C., Zeng, T., & Yang, Y. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428278 · Cited by 2
“To solve this problem, many transductive ZSL approaches [2, 6] have been proposed.”
BackgroundMulti-View Visual Relationship Detection with Estimated Depth Map
Liu, X., Gan, M.-G., & He, Y. (2022) · Applied Sciences · doi:10.3390/app12094674 · Cited by 3
DSPformer: discovering semantic parts with token growth and clustering for zero-shot learning
Zhao, P., Wang, Q., & Yin, Y. (2024) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-024-00336-6 · Cited by 2
“However, such methods often suffer fromthedomainshiftproblem[25,26].”
Node Attribute Generation on GraphsPreprint
Chen, X., Chen, S., Zheng, H., Yao, J., Cui, K., Zhang, Y., & Tsang, I. W.-H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.09708 · Cited by 2
“In recent years, representation learning on graphs has attracted great research interest because of its great potential in numerous machine learning tasks, such as semi-supervised learning [19] and zero/few-shot learning [6, 31], as well as numerous real-world applications, such as recommendation systems [33] and acti…”
BackgroundRapid COVID-19 Risk Screening by Eye-region ManifestationsPreprint
Fu, Y., Zhao, L., Zheng, H., Sun, Q., Li, Y., Li, H., Xie, J., Xue, X., Li, F., Li, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.06664 · Cited by 2
Self-citationZero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A ReviewPreprint
Rezaei, M., & Shahidi, M. (2020) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/tbk3e · Cited by 5
Visuo-Haptic recognition of daily-life objects : a contribution to the data scarcity problem
Abderrahmane, Z. (2018) · theses.fr (ABES) · doi:10.70675/d1c86137z5775z4078zbc24z51938754daed · Cited by 2
Research on Transductive Zero-Shot Learning for Action Recognition
齐, 秋. (2022) · Computer Science and Application · doi:10.12677/csa.2022.123050 · Cited by 1
Image Security Attribute Inference Method Based on Class Attribute Portrait
Li, F., Du, X., Liu, A., & Zhang, L. (2023) · International Conference on Frontiers of Electronics, Information and Computation Technologies · doi:10.1109/icfeict59519.2023.00011 · Cited by 1
“The first is the domain shift problem [17].”
BackgroundVisual–Semantic Fuzzy Interaction Network for Zero-Shot Learning
Hui, X., Liu, Z., Liu, J., Zhang, Z., & Wang, L. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3524955 · Cited by 1
“Early embedding-based ZSL methods [2], [8], [9], [10], [11] attempt to build interactions between visual features and their semantic attribute vectors using a learned visual-to-semantic projection function.”
Class Semantic Attribute Perception Guided Zero-Shot Learning
Yue, Q., Cui, J., Liang, J., & Bai, L. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i21.34383 · Cited by 4
Domain-Aware Semantic Alignment Hashing for Large-Scale Zero-Shot Image Retrieval
Wang, Y., Dong, F., Chen, Z.-D., Luo, X., & Xu, X.-S. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3734871 · Cited by 1
“Due to the domain shift problem, the performance of ZSL is influenced by the target domain information contained in the training instances.”
Transduction to induction: Unsupervised representation learning based on rank information
Biotto, D. W., Valem, L. P., Pedronette, D. C. G., & Salvadeo, D. H. P. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131010 · Cited by 2
Enhancing destination marketing through artificial intelligence driven visual recognition
Savaşcı, E., Yıldırım, F. S., Sümer, S. I., & Sümer, E. (2025) · Information Technology & Tourism · doi:10.1007/s40558-025-00337-z · Cited by 1
“S = xs, ys, asn, n = 1 , . . . , N, xs ∈ XS, ys ∈ Y S, as ∈ A (1) Some variations of the ZSL method include inductive ZSL, generalized ZSL and transductive ZSL (Song et al. 2018 ; Wan et al. 2019 ; Fu et al. 2015 ; Zhang et al. 2020 ).”
A Survey of Zero-Shot Image Classification: Concepts, Developments, and Challenges
Xu, S. H., Wang, Y., Zhu, X., Guan, D., Zhang, Z., & Lin, F. (2025) · Tsinghua Science & Technology · doi:10.26599/tst.2025.9010131 · Cited by 1
Balancing Cross-Modal Attention for Generalized Zero-Shot Learning
Rao, Z., & Guo, J. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755055 · Cited by 2
ExPart3D : Exclusive part aggregation for zero-shot point cloud learning
Hao, Y., Wu, J., Ma, Z., Dang, L., Su, Y., & Wu, Q.-Y. (2026) · Expert systems with applications · doi:10.1016/j.eswa.2026.132370 · Cited by 1
Mutually Causal Semantic Distillation Network for Zero-Shot Learning
Chen, S., Chen, S., Xie, G.-S., & You, X. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02814-2 · Cited by 1
“In ZSL, there are clear projection domain shifts between seen and unseen classes (Fu et al, 2015; Chen et al, 2023b), e.g. , the attribute of "has tail" is different for horse (seen class) and pig (unseen class), which inevitably leads the attention model to learn the spurious associations between…”
Zero-Shot Learning with Fuzzy Attribute
Liu, C., Shang, Z., & Tang, Y. Y. (2017) · IEEE International Conference on Cybernetics (CYBCONF) · doi:10.1109/cybconf.2017.7985823 · Cited by 1
“many zero-shot learning methods had been proposed[4], [5], [6].”
BackgroundMethodZero-Shot Leaning with Manifold Embedding
Yu, Y., Ji, Z., & Pang, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-02698-1_12 · Cited by 1
Dong, H., Sun, Z., Fu, Y., Zhong, S., Zhang, Z., & Jiang, Y. (2019) · Frontiers of Computer Science · doi:10.1007/s11704-019-8249-3 · Cited by 1
Self-citationDeep Representation of Hierarchical Semantic Attributes for Zero-shot Learning
Zhang, Z., & Yang, G. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206924 · Cited by 1
“Domain shift [2]and hubness problem [3], [4] are the two crucial problems and need to be solved.”
BackgroundChai, C., Lou, Y., Zhang, S., & Hua, M. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413287 · Cited by 1
“During the training phase, zero-shot learning can be divided into inductive ZSL [8] [9] [10] [11] [12] [13] and transduced ZSL [14] [15] [16] [17] [18] [19].”
BackgroundZero-Shot Learning Based on Knowledge Sharing
Zeng, T., Xiang, H., Xie, C., Yang, Y., & Liu, Q. (2021) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd49262.2021.9437611 · Cited by 1
“[10] Yanwei Fu, Timothy M Hospedales, Tao Xiang, and Shaogang Gong.”
BackgroundDouble Discriminative Graph Regularized Semantic Auto-Encoder for Zero-shot Learning
Tai, D., & Zhang, Z. (2021) · International Conference on Artificial Intelligence and Information Systems (ICAIIS) · doi:10.1145/3469213.3470337 · Cited by 1
Novel Disease Detection Using Ensembles with Regularized Disagreement
Ţifrea, A., Stavarache, E., & Yang, F. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87735-4_13 · Cited by 2
Stack-VAE Network for Zero-Shot Learning
Xie, J., Wu, J., Liang, T., & Meng, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-92273-3_21 · Cited by 1
Attribute self-representation steered by exclusive lasso for zero-shot learning
Mi, J., Zhang, Z., Tai, D., & Zhou, L. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03497-1 · Cited by 1
“The domain shift problem in ZSL was first put forward by [6].”
BackgroundSemantic-Related Feature Generation for Generalized Zero-Shot Learning
Ma, P., Ran, W., & Lu, H. (2022) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme52920.2022.9859914 · Cited by 1
“Since the proposed model does not use the real image features of the unseen classes during train ing, this method is inductive rather than transductive [33].”
MethodExploring Attribute Space with Word Embedding for Zero-shot Learning
Zhang, Z., & Yang, G. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892132 · Cited by 1
“There is also a transductive setting [7], [29]–[33], which means that instances of unseen classes can be used in the training stage, but there is no corresponding label for each unseen instance.”
BackgroundMethodA Contrastive Method for Continual Generalized Zero-Shot Learning
Liang, C., Fan, W., Liu, X., & Peng, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36819-6_32 · Cited by 1
Class-Incremental Generalized Zero-Shot Learning
Sun, Z., Feng, R., & Fu, Y. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16316-7 · Cited by 1
Self-citationTransductive Reward Inference on Graph
Qu, B., Cao, X., Guo, Q., Chang, Y., Tsang, I. W.-H., & Zhang, C. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3398208 · Cited by 1
“Another classification of transduction methods involves graph-based methods [14], [16], [18], [47], [48].”
MethodConsistent representation joint adaptive adjustment for incremental zero-shot learning
Niu, C., Shang, J., Zhou, Z., & Yang, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128385 · Cited by 1
Mao, Q., Li, Z., Liu, Q., Wu, L., Zhang, H., & Chen, E. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3700444 · Cited by 3
“Over the past years, ZS approaches have achieved great success in both visual scenarios [23, 49, 73] and non-visual scenarios [11, 47, 94].”
Image Detection for Small Hardware Defect in Power Transmission Line Based on Zero-Shot Learning
Gao, B., He, J.-J., Rong, F., Li, X., & Chen, T. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-88294-4_55 · Cited by 1
Improving the generalization capability of face spoofing detection
Li, H. (2018) · doi:10.32657/10220/46392 · Cited by 1
Zero-Shot Learning with Sparse Attribute PropagationPreprint
Fei, N., Guan, J., Lu, Z., Xiang, T., & Wen, J.-R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.04427 · Cited by 1
“Due to the difficulty of collecting sufficient training images for large-scale object recognition [38, 16, 23, 41] where convolutional neural network (CNN) is often employed, zero-shot learning (ZSL) has become topical in computer vision [10, 11, 1, 35, 50, 20, 30, 22, 47].”
BackgroundMethodSelf-citationRepresentation Learning for Words and EntitiesPreprint
Rastogi, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05651 · Cited by 1
“2016b; He and Lawrence 2011) and few shot learning (Fu et al. 2015).”
BackgroundJoint attribute chain prediction for zero‐shot learning
Qiao, L., Tuo, H., Wang, J., Wang, C., & Jing, Z. (2018) · IET Computer Vision · doi:10.1049/iet-cvi.2017.0438
Co-consistent Regularization with Discriminative Feature for Zero-Shot Learning
Tian, Y., Zhang, W., Zhang, Q., Cheng, J. S., Hao, P., & Lü, G. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04167-0_4
Joint Embedding with Multi-Task Learning for Multi-Label Zero-Shot Action Recognition
An, R., Miao, Z., & Li, Q. (2018) · International Conference on Signal Processing · doi:10.1109/icsp.2018.8652415
An Inverse Mapping with Manifold Alignment for Zero-Shot Learning
Wu, X., Song, B., Wang, Z., & Yuan, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-37734-2_33
Qin, Z., & Li, Y. (2019) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip47243.2019.8966084
Addressing Target Shift in Zero-shot Learning using Grouped Adversarial Learning
Chemmengath, S., Paul, S., Bharadwaj, S., Samanta, S., & Sankaranarayanan, K. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00268 · Cited by 1
“On the other hand, the transductive ZSL represents a relaxed view [13, 40] that allows for unlabelled test set as unsupervised additional information.”
BackgroundTransductive Zero-Shot Learning using Cross-Modal CycleGANPreprint
Bordes, P., Zablocki, É., Piwowarski, B., & Gallinari, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.06850
“d unseen classes, e.g. attributes [5], or textual embeddings of class labels [3]. Evaluation is then carried out on the unseen classes. However, all these approaches suer from a domain shift problem [6]: since the sets of seen and unseen classes are disjoint and potentially unrelated, the learned projection functions…”
BackgroundSajjan, P. J., & Glavin, F. G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.09236
Vers un apprentissage sans exemple plus réaliste
Cacheux, Y. L. (2020) · theses.fr (ABES) · doi:10.70675/a628e266zf8bdz4c57zb7b3z91477cfbf198
Robust image features creation by learning how to merge visual and semantic attributes
de Resende, D. C. O. (2021) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.55.2021.tde-17032021-122717
Semantic-Guided High-Order Region Attention Embedding for Zero-Shot Learning
Zhang, R., Xu, X., & Zhu, Q. (2021) · International Conference on Advanced Computational Intelligence (ICACI) · doi:10.1109/icaci52617.2021.9435883
“Practically, the current approaches treat ZSL as a aligning problem between visual space and semantic space [2]–[5].”
BackgroundReport on Three Round COVID-19 Risk Blind Tests by Screening Eye-region ManifestationsPreprint
Fu, Y., Zhao, L., Zheng, H., Sun, Q., Yang, L., Li, H., Xie, J., Xue, X., Li, F., Li, Y., et al. (2021) · medRxiv · doi:10.1101/2021.06.23.21258626
Self-citationBi-shifting semantic auto-encoder for zero-shot learning
Wang, Y. (2021) · Electronic Research Archive · doi:10.3934/era.2022008
Transfer Visual Semantics into Knowledge Graph for Zero-Shot Recognition in Universal Datasets
Yu, B., Cheng, X., Wang, Y., & Xiang, H. (2021) · International Conference on Intelligent Systems and Knowledge Engineering (ISKE) · doi:10.1109/iske54062.2021.9755335
Auto‐encode the synthesis pseudo features for generalized zero‐shot learning
Wang, L., Shen, Z., Wang, G., Song, J., & Wu, Q. (2022) · The Journal of Engineering · doi:10.1049/tje2.12185
A Multi-robot Collaborative Exploration Technology Based on Instance Segmentation
Lin, J., Chen, Z., Wang, Y., Huang, K., & Chen, Y. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-6203-5_41
LVQ Treatment for Zero-Shot Learning
Ismailoglu, F. (2022) · TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES · doi:10.55730/1300-0632.3980
Chinese medical named entity recognition based on zero-shot learning
Zhou, M., & Gong, K. (2022) · International Conference on Machine Learning and Natural Language Processing (MLNLP) · doi:10.1145/3578741.3578780
Peer Review #4 of "Semantic-visual shared knowledge graph for zero-shot learning (v0.1)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1260v0.1/reviews/4
Peer Review #1 of "Semantic-visual shared knowledge graph for zero-shot learning (v0.1)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1260v0.1/reviews/1
Peer Review #3 of "Semantic-visual shared knowledge graph for zero-shot learning (v0.1)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1260v0.1/reviews/3
Peer Review #2 of "Semantic-visual shared knowledge graph for zero-shot learning (v0.1)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1260v0.1/reviews/2
Peer Review #3 of "Semantic-visual shared knowledge graph for zero-shot learning (v0.2)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1260v0.2/reviews/3
A Zero-Shot Learning Relationship Classification Method with Semantic Pivot RegularizationPreprint
Ye, Z., Tang, J., He, C., Yue, X., & Li, X. (2023) · Research Square · doi:10.21203/rs.3.rs-2925468/v1
Zero Shot Learning Recent Advances in RoboticsPreprint
Singh, S. (2023) · Preprints.org · doi:10.20944/preprints202306.1353.v1
Automatic Check-Out within Generalized Zero-Shot Learning Setting: Help Classifier Learn More EasilyPreprint
Han, Y., Chen, H., Han, Z., & Fu, Z. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4505118
Zero-Shot Neural Decoding with Semi-Supervised Multi-View Embedding
Akamatsu, Y., Maeda, K., Ogawa, T., & Haseyama, M. (2023) · Sensors · doi:10.3390/s23156903
“However, ZSL models mostly suffer from the projection domain shift problem [16].”
BackgroundNeyigapula, B. S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4606493
A Review of Zero-Shot Image Classification
Sun, H., Zhen, Z., Zhao, P., & Zhang, Y. (2024) · Smart innovation, systems and technologies · doi:10.1007/978-981-97-3980-6_36 · Cited by 1
Two Semantic Information Extension Enhancement Methods For Zero-Shot Learning
Huang, W., Ju, X., Zhou, Y., Xu, Y., & Yang, G. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8620-6_35
Autonomous novel class discovery for vision-based recognition in non-interactive environments
Zhang, X., Liu, F., Cheng, X., Yan, S., Liao, Z., & Ge, Z. (2024) · Cognitive Robotics · doi:10.1016/j.cogr.2024.10.002
Sinha, A. K., Mishra, D., & Moorthi, S. M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78183-4_21
Multi-view deep generative dual fusion network for zero-shot learning
Luo, X., & Yin, W. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20516-0
“This approach effectively overcomes the domain shift problem [12], where the same attribute can manifest as different visual features in different classes.”
Causal Intervention-based Counterfactual Generative Network for Generalized Zero-shot Learning
Zhang, Y., Huang, J., & Tian, Y. (2024) · International Conference on Signal Processing · doi:10.1109/icsp62129.2024.10846718
“However, such methods always suffer from the Yi Tian is the corresponding author. severe domain shift problem, i.e., unseen samples are incorrectly classified as seen classes [6].”
Disentangled representation learning for multi-label generalized zero-shot learning
Gull, M., Arif, O., Mumtaz, R., & Ahmad, M. (2025) · International Journal of General Systems · doi:10.1080/03081079.2025.2504682
“Single-label GZSL has garnered significant attention in recent years (Felix et al. 2018; Fu et al. 2015; Jayaraman and Grauman 2014; J. Li et al.2019; Romera-Paredes and Torr 2015; Xian et al. 2018; Xian, Schiele, and Akata2017; Xian et al.2019).”
Learning Discriminative Features with VAE-GAN for Zero-Shot Learning
Mi, J., Shi, S., Zhang, Z., & Liu, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9884-4_2
Exploiting Semantic-Visual Symmetry for Goal-Oriented Zero-Shot Recognition
Zheng, H., Zhou, Y. P., & Jiang, M. (2025) · Symmetry · doi:10.3390/sym17081291
Yang, G., Ju, X., Xu, Y., & Zhang, Y. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209938
“Transductive zero-shot learning was introduced to solve this problem, allowing the model to leverage unlabeled test data to mitigate the domain shift effect during training [8].”
Dual-Contrastive Attribute Embedding for Generalized Zero-Shot Learning
Li, Q., Long, Y., Zhang, Z., & Jiang, K. (2025) · Electronics · doi:10.3390/electronics14214341 · Cited by 1
“Furthermore, this approach has the potential to prevent models from recognizing attributes in unseen classes, which is the cause of the domain shift problem [16].”
Bias-Alleviated Zero-Shot Sports Action Recognition Enabled by Multi-Scale Semantic Alignment
Zheng, Q., Qin, W., Meng, F., & Liu, H. (2025) · Symmetry · doi:10.3390/sym17111959
“…multi-view hypergraph label propagation method that exploits complementary information from multiple semantic representations within a transductive embedding space and leverages the manifold structures across different representation spaces to enhance label propagation effectiveness [23].”
Deep ensemble learning method for zero-shot object detection
Dawood, F., Loo, C. K., Alhussein, M. A., Aurangzeb, K., & Azam, S. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114333
Zhang, H., Zhang, R., Jiang, H., Cheng, D., & Kou, Q. (2025) · Multimedia Systems · doi:10.1007/s00530-025-02055-2
“CDZSIR can be viewed as an extension of Zero-Shot Retrieval [29] and Domain Generalization [30].”
A Multi-Modal Knowledge-Driven Approach for Generalized Zero-shot Video Classification
Hong, M., Zhang, X., Li, G., & Qingming, H. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02584-3
Probabilistic regression-based multi-view clustering with anchor graphs
Liu, Y., Li, Q., Yang, G., Gao, Q., Duan, Y., & Deng, C. D. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.132679
Chauhan, P., Clark, J. R., Fileman, E. S., Widdicombe, C. E., Rühl, S., & Rowlands, S. (2026) · IEEE Access · doi:10.1109/access.2026.3652320
“…multi-instrument corpora emerge, advanced cross-modal alignment (e.g., Feature-wise Linear Modulation (FiLM) layer conditioning [65] or gated fusion on image–metadata pairs [66]) can be layered onto our baseline to further improve rare-taxon performance and out-of-domain generalization [67].”
Zero-Shot Recognition by Using Attention Mechanism
Mao, L., & Zhang, G. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-11957-5_7
Application of large language models: zero-shot learning
Pillai, A. S., Tanev, H., & Tedesco, R. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-33592-1.00009-7
Align-then-generate: An effective cross-modal generation paradigm for multi-label zero-shot learning
Ma, P., Ran, W., Gu, Y., Chen, H., He, Z., & Lu, H. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113229
Optical Image-Assisted Zero-Shot Learning for Unknown Target Recognition in SAR Images
Tong, X., Wang, Y., Song, Z., & Zhang, T. (2026) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2026.3657908
“1) Alignment-based ZSL algorithms [7], [8], [9] usually map the images and semantics of known targets and the images of unknown targets into the embedding space for alignment.”
Metadata
- Authors
- Fu, Y., Hospedales, T. M., Xiang, T., & Gong, S.
- Affiliations
- Walt Disney (United States) (US)
- Queen Mary University of London (GB)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2015-11-01
- Volume
- 37
- Issue
- 11
- Pages
- 2332-2345
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2141350700
- Cited by
- 514
- References
- 74
- Citations by year
- 2026: 17 · 2025: 32 · 2024: 32 · 2023: 52 · 2022: 60 · 2021: 75 · 2020: 62 · 2019: 57 · 2018: 64 · 2017: 41 · 2016: 21 · 2015: 1
- FWCI
- 41.51
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Queen Mary Research Online (Queen Mary University of London) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- zero-shot learning, transductive learning, multi-view embedding, semantic representation, transfer learning, manifold structure
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.