339 citations · 849 across the 27 of their papers we have counts for
27 papers
Order-preserving Consistency Regularization for Domain Adaptation and Generalization
Mengmeng Jing, Xiantong Zhen, Jingjing Li +1
Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this…
Zero-Shot Learning by Harnessing Adversarial Samples
Zhi Chen, Pengfei Zhang, Jingjing Li +2
Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizing the knowledge, i.e., visual and semantic relationships, obtained from seen classes, where image augmentati…
Variational Model Perturbation for Source-Free Domain Adaptation
Mengmeng Jing, Xiantong Zhen, Jingjing Li +1
We aim for source-free domain adaptation, where the task is to deploy a model pre-trained on source domains to target domains. The challenges stem from the distribution shift from…
Federated Zero-Shot Learning for Visual Recognition
Zhi Chen, Yadan Luo, Sen Wang +2
Zero-shot learning is a learning regime that recognizes unseen classes by generalizing the visual-semantic relationship learned from the seen classes. To obtain an effective ZSL mo…
Spectrum Gaussian Processes Based On Tunable Basis Functions
Wenqi Fang, Guanlin Wu, Jingjing Li +3
Spectral approximation and variational inducing learning for the Gaussian process are two popular methods to reduce computational complexity. However, in previous research, those m…
Exploiting Cross-Session Information for Session-based Recommendation with Graph Neural Networks
Ruihong Qiu, Zi Huang, Jingjing Li +1
Different from the traditional recommender system, the session-based recommender system introduces the concept of the session, i.e., a sequence of interactions between a user and m…
Mitigating Generation Shifts for Generalized Zero-Shot Learning
Zhi Chen, Yadan Luo, Sen Wang +3
Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not obser…
Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
Zhekai Du, Jingjing Li, Hongzu Su +2
Unsupervised Domain Adaptation (UDA) aims to generalize the knowledge learned from a well-labeled source domain to an unlabeled target domain. Recently, adversarial domain adaptati…
Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
Zhi Chen, Zi Huang, Jingjing Li +1
Compared to conventional zero-shot learning (ZSL) where recognising unseen classes is the primary or only aim, the goal of generalized zero-shot learning (GZSL) is to recognise bot…
Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation
Taotao Jing, Bingrong Xu, Jingjing Li +1
Domain adaptation (DA) becomes an up-and-coming technique to address the insufficient or no annotation issue by exploiting external source knowledge. Existing DA algorithms mainly…
Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches
Zhi Chen, Sen Wang, Jingjing Li +1
Zero-shot learning (ZSL) is commonly used to address the very pervasive problem of predicting unseen classes in fine-grained image classification and other tasks. One family of sol…
Accurate RGB-D Salient Object Detection via Collaborative Learning
Wei Ji, Jingjing Li, Miao Zhang +2
Benefiting from the spatial cues embedded in depth images, recent progress on RGB-D saliency detection shows impressive ability on some challenge scenarios. However, there are stil…
Dual-level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval
Lei Zhu, Hui Cui, Zhiyong Cheng +2
Social network stores and disseminates a tremendous amount of user shared images. Deep hashing is an efficient indexing technique to support large-scale social image retrieval, due…
Task-adaptive Asymmetric Deep Cross-modal Hashing
Fengling Li, Tong Wang, Lei Zhu +2
Supervised cross-modal hashing aims to embed the semantic correlations of heterogeneous modality data into the binary hash codes with discriminative semantic labels. Because of its…
Multi-Feature Discrete Collaborative Filtering for Fast Cold-start Recommendation
Yang Xu, Lei Zhu, Zhiyong Cheng +2
Hashing is an effective technique to address the large-scale recommendation problem, due to its high computation and storage efficiency on calculating the user preferences on items…
Rethinking the Item Order in Session-based Recommendation with Graph Neural Networks
Ruihong Qiu, Jingjing Li, Zi Huang +1
Predicting a user's preference in a short anonymous interaction session instead of long-term history is a challenging problem in the real-life session-based recommendation, e.g., e…
CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language
Zhi Chen, Jingjing Li, Yadan Luo +2
Existing methods using generative adversarial approaches for Zero-Shot Learning (ZSL) aim to generate realistic visual features from class semantics by a single generative network,…
Cycle-consistent Conditional Adversarial Transfer Networks
Jingjing Li, Erpeng Chen, Zhengming Ding +3
Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions. Recen…
Alleviating Feature Confusion for Generative Zero-shot Learning
Jingjing Li, Mengmeng Jing, Ke Lu +3
Lately, generative adversarial networks (GANs) have been successfully applied to zero-shot learning (ZSL) and achieved state-of-the-art performance. By synthesizing virtual unseen…
Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation
Yadan Luo, Zi Huang, Zheng Zhang +3
Visual paragraph generation aims to automatically describe a given image from different perspectives and organize sentences in a coherent way. In this paper, we address three criti…
Agile Domain Adaptation
Jingjing Li, Mengmeng Jing, Yue Xie +2
Domain adaptation investigates the problem of leveraging knowledge from a well-labeled source domain to an unlabeled target domain, where the two domains are drawn from different d…
A Fusion Adversarial Underwater Image Enhancement Network with a Public Test Dataset
Hanyu Li, Jingjing Li, Wei Wang
Underwater image enhancement algorithms have attracted much attention in underwater vision task. However, these algorithms are mainly evaluated on different data sets and different…
From Zero-Shot Learning to Cold-Start Recommendation
Jingjing Li, Mengmeng Jing, Ke Lu +3
Zero-shot learning (ZSL) and cold-start recommendation (CSR) are two challenging problems in computer vision and recommender system, respectively. In general, they are independentl…
Coupled VAE: Improved Accuracy and Robustness of a Variational Autoencoder
Shichen Cao, Jingjing Li, Kenric P. Nelson +1
We present a coupled Variational Auto-Encoder (VAE) method that improves the accuracy and robustness of the probabilistic inferences on represented data. The new method models the…