19 citations · 32 across the 7 of their papers we have counts for
7 papers
A Grammatical Compositional Model for Video Action Detection
Zhijun Zhang, Xu Zou, Jiahuan Zhou +2
Analysis of human actions in videos demands understanding complex human dynamics, as well as the interaction between actors and context. However, these interaction relationships us…
ALUM: Adversarial Data Uncertainty Modeling from Latent Model Uncertainty Compensation
Wei Wei, Jiahuan Zhou, Hongze Li +1
It is critical that the models pay attention not only to accuracy but also to the certainty of prediction. Uncertain predictions of deep models caused by noisy data raise significa…
Beyond Empirical Risk Minimization: Local Structure Preserving Regularization for Improving Adversarial Robustness
Wei Wei, Jiahuan Zhou, Ying Wu
It is broadly known that deep neural networks are susceptible to being fooled by adversarial examples with perturbations imperceptible by humans. Various defenses have been propose…
Dual Clustering Co-teaching with Consistent Sample Mining for Unsupervised Person Re-Identification
Zeqi Chen, Zhichao Cui, Chi Zhang +2
In unsupervised person Re-ID, peer-teaching strategy leveraging two networks to facilitate training has been proven to be an effective method to deal with the pseudo label noise. H…
Unsupervised Embedding Learning from Uncertainty Momentum Modeling
Jiahuan Zhou, Yansong Tang, Bing Su +1
Existing popular unsupervised embedding learning methods focus on enhancing the instance-level local discrimination of the given unlabeled images by exploring various negative data…
Exposing Deep-faked Videos by Anomalous Co-motion Pattern Detection
Gengxing Wang, Jiahuan Zhou, Ying Wu
Recent deep learning based video synthesis approaches, in particular with applications that can forge identities such as "DeepFake", have raised great security concerns. Therefore,…
Uncertainty-aware Score Distribution Learning for Action Quality Assessment
Yansong Tang, Zanlin Ni, Jiahuan Zhou +4
Assessing action quality from videos has attracted growing attention in recent years. Most existing approaches usually tackle this problem based on regression algorithms, which ign…