M. Hayat

Latest

Restormer: Efficient Transformer for High-Resolution Image Restoration
Semantic-Aware Domain Generalized Segmentation
Towards Robust and Reproducible Active Learning Using Neural Networks
Learning Enriched Features for Fast Image Restoration and Enhancement
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Intriguing Properties of Vision Transformers
On Generating Transferable Targeted Perturbations
Orthogonal Projection Loss
Transformers in Vision: A Survey
Synthesizing the Unseen for Zero-shot Object Detection
Learning Enriched Features for Real Image Restoration and Enhancement
A Self-supervised Approach for Adversarial Robustness
CycleISP: Real Image Restoration via Improved Data Synthesis
iTAML: An Incremental Task-Agnostic Meta-learning Approach
Deeply Supervised Discriminative Learning for Adversarial Defense
Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection
Gaussian affinity for max-margin class imbalanced learning
Random path selection for continual learning
Adversarial defense by restricting the hidden space of deep neural networks
Regularization of deep neural networks with spectral dropout
Image super-resolution as a defense against adversarial attacks
Striking the right balance with uncertainty
Unsupervised primitive discovery for improved 3D generative modeling
Adversarial training of variational auto-encoders for high fidelity image generation
A multimodal system to characterise melancholia: cascaded bag of words approach
Heart rate estimation from facial videos for depression analysis
Investigating word affect features and fusion of probabilistic predictions incorporating uncertainty in AVEC 2017
Scene categorization with spectral features
Cost-sensitive learning of deep feature representations from imbalanced data
Empowering simple binary classifiers for image set based face recognition
Joint Registration and Representation Learning for Unconstrained Face Identification
A video-based facial behaviour analysis approach to melancholia
A spatial layout and scale invariant feature representation for indoor scene classification
A discriminative representation of convolutional features for indoor scene recognition
A two-phase weighted collaborative representation for 3D partial face recognition with single sample
An RGB--D based image set classification for robust face recognition from Kinect data
Contractive rectifier networks for nonlinear maximum margin classification
Reverse training: An efficient approach for image set classification
Deep reconstruction models for image set classification
An automatic framework for textured 3D video-based facial expression recognition
Learning Non-Linear Reconstruction Models for Image Set Classification
An efficient 3D face recognition approach using local geometrical signatures
Clustering of video-patches on grassmannian manifold for facial expression recognition from 3d videos
Novel low level local features for 3D expression invariant face recognition
Fully automatic face recognition from 3D videos
Evaluation of spatiotemporal detectors and descriptors for facial expression recognition