most citedOpen-World Pose Transfer via Sequential Test-Time Adaption

3 citations · 4 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV20241 cited

Dynamic Correlation Learning and Regularization for Multi-Label Confidence Calibration

Tianshui Chen, Weihang Wang, Tao Pu +4

Modern visual recognition models often display overconfidence due to their reliance on complex deep neural networks and one-hot target supervision, resulting in unreliable confiden…

cs.CV2024

Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition

Yuefang Gao, Yuhao Xie, Zeke Zexi Hu +2

Domain shift poses a significant challenge in Cross-Domain Facial Expression Recognition (CD-FER) due to the distribution variation across different domains. Current works mainly f…

cs.CV2023

Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search

Hefeng Wu, Weifeng Chen, Zhibin Liu +3

Given a descriptive text query, text-based person search (TBPS) aims to retrieve the best-matched target person from an image gallery. Such a cross-modal retrieval task is quite ch…

cs.CV2023

RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs

Zhouxia Wang, Jiawei Zhang, Tianshui Chen +2

Blind face restoration aims at recovering high-quality face images from those with unknown degradations. Current algorithms mainly introduce priors to complement high-quality detai…

cs.CV2023

Perception and Semantic Aware Regularization for Sequential Confidence Calibration

Zhenghua Peng, Yu Luo, Tianshui Chen +2

Deep sequence recognition (DSR) models receive increasing attention due to their superior application to various applications. Most DSR models use merely the target sequences as su…

cs.CV20233 cited

Open-World Pose Transfer via Sequential Test-Time Adaption

Junyang Chen, Xiaoyu Xian, Zhijing Yang +5

Pose transfer aims to transfer a given person into a specified posture, has recently attracted considerable attention. A typical pose transfer framework usually employs representat…