activity
20152023
most citedFeature Encoding with AutoEncoders for Weakly-supervised Anomaly Detection

175 citations · 473 across the 27 of their papers we have counts for

collaborators

42 papers

cs.CV20235 cited

Learning Conditional Attributes for Compositional Zero-Shot Learning

Qingsheng Wang, Lingqiao Liu, Chenchen Jing +4

Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations. One of the c…

cs.CV20222 cited

Generalizable Person Re-Identification via Viewpoint Alignment and Fusion

Bingliang Jiao, Lingqiao Liu, Liying Gao +5

In the current person Re-identification (ReID) methods, most domain generalization works focus on dealing with style differences between domains while largely ignoring unpredictabl…

cs.CV202244 cited

Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization

Hai-Ming Xu, Lingqiao Liu, Qiuchen Bian +1

Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-…

cs.CL2022

Progressive Class Semantic Matching for Semi-supervised Text Classification

Hai-Ming Xu, Lingqiao Liu, Ehsan Abbasnejad

Semi-supervised learning is a promising way to reduce the annotation cost for text-classification. Combining with pre-trained language models (PLMs), e.g., BERT, recent semi-superv…

cs.CV202214 cited

Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

Liang Chen, Yong Zhang, Yibing Song +2

Recent studies in deepfake detection have yielded promising results when the training and testing face forgeries are from the same dataset. However, the problem remains challenging…

cs.CV2022

Multi-Domain Joint Training for Person Re-Identification

Lu Yang, Lingqiao Liu, Yunlong Wang +2

Deep learning-based person Re-IDentification (ReID) often requires a large amount of training data to achieve good performance. Thus it appears that collecting more training data f…