Search Results for author:
Found 9 papers, 6 papers with code
Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
Auto-regressive partial differential equation (PDE) foundation models have shown great potential in handling time-dependent data.
STSA: Spatial-Temporal Semantic Alignment for Visual Dubbing
Despite this, we observe that the semantic ambiguity between spatial and temporal domains significantly degrades the synthesis stability for the dynamic faces.
Reinforcement Unlearning
Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners.
Phase Matching for Out-of-Distribution Generalization
Beyond vanilla analysis and experiments, we further clarify the relationships between the Fourier components and DG problems by introducing a Fourier-based Structural Causal Model (SCM).
Occlusion-Robust Face Alignment Using a Viewpoint-Invariant Hierarchical Network Architecture
The occlusion problem heavily degrades the localization performance of face alignment.
Ranked #3 on
Face Alignment
on COFW-68
Reasoning Structural Relation for Occlusion-Robust Facial Landmark Localization
Moreover, the SRN augments the training data by synthesizing occluded faces.
Unsupervised Learning of Multi-level Structures for Anomaly Detection
This paper first introduces a novel method to generate anomalous data by breaking up global structures while preserving local structures of normal data at multiple levels.
Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks
We argue that exploring the weaknesses of the detector so as to remedy them is a promising method of robust facial landmark detection.
Ranked #5 on
Face Alignment
on COFW-68
Towards Omni-Supervised Face Alignment for Large Scale Unlabeled Videos
In this paper, we propose a spatial-temporal relational reasoning networks (STRRN) approach to investigate the problem of omni-supervised face alignment in videos.
