Search Results for author:
Found 11 papers, 2 papers with code
CATFace: Cross-Attribute-Guided Transformer with Self-Attention Distillation for Low-Quality Face Recognition
In this paper, we propose a novel multi-branch neural network that leverages SB attribute information to boost the performance of FR.
Multi-Context Dual Hyper-Prior Neural Image Compression
In addition, we introduce a novel entropy model that incorporates two different hyperpriors to model cross-channel and spatial dependencies of the latent representation.
Towards Generalizable Morph Attack Detection with Consistency Regularization
The proposed consistency regularization aligns the abstraction in the hidden layers of our model across the morph attack images which are generated from diverse domains in the wild.
CCFace: Classification Consistency for Low-Resolution Face Recognition
However, these methods have shown a significant decline in performance when applied to real-world low-resolution benchmarks like TinyFace or SCFace.
AAFACE: Attribute-aware Attentional Network for Face Recognition
In this paper, we present a new multi-branch neural network that simultaneously performs soft biometric (SB) prediction as an auxiliary modality and face recognition (FR) as the main task.
MedViT: A Robust Vision Transformer for Generalized Medical Image Classification
Convolutional Neural Networks (CNNs) have advanced existing medical systems for automatic disease diagnosis.
Robust Transformer with Locality Inductive Bias and Feature Normalization
In this paper, we explore the robustness of vision transformers against adversarial perturbations and try to enhance their robustness/accuracy trade-off in white box attack settings.
Robust Ensemble Morph Detection with Domain Generalization
In this paper, we intend to learn a morph detection model with high generalization to a wide range of morphing attacks and high robustness against different adversarial attacks.
Multi-Expert Human Action Recognition with Hierarchical Super-Class Learning
In this paper, we propose a two-phase multi-expert classification method for human action recognition to cope with long-tailed distribution by means of super-class learning and without any extra information.
Online Visual Tracking with One-Shot Context-Aware Domain Adaptation
In this paper, we propose a domain adaptation approach to strengthen the contributions of the semantic background context.
Visual Object Tracking based on Adaptive Siamese and Motion Estimation Network
Visual object tracking is one of the interesting and important areas in computer vision that achieves remarkable improvements in recent years.
