• Corpus ID: 211677891

Attention-aware fusion RGB-D face recognition

  title={Attention-aware fusion RGB-D face recognition},
  author={Hardik Uppal and Alireza Sepas-Moghaddam and Michael A. Greenspan and S. A. Etemad},
A novel attention aware method is proposed to fuse two image modalities, RGB and depth, for enhanced RGB-D facial recognition. The proposed method uses two attention layers, the first focused on the fused feature maps generated by convolution layers, and the second focused on the spatial features of those maps. The training database is preprocessed and augmented through a set of geometric transformations, and the learning process is further aided using transfer learning from a pure 2D RGB image… 
High-Accuracy RGB-D Face Recognition via Segmentation-Aware Face Depth Estimation and Mask-Guided Attention Network
The proposed mask-guided RGB-D face recognition model can fully exploit the depth map and segmentation mask information and is more robust against pose variation than previous methods, and outperforms state-of-the-art methods on several public 3D face datasets.


RGB-D Face Recognition via Deep Complementary and Common Feature Learning
This work proposes a novel approach for RGB-D face recognition that is able to learn complementary features from multiple modalities and common features between different modalities, and introduces a joint loss taking activation from both modality-specific feature learning networks, and enforcing the features to be learned in a complementary way.
RGB-D face recognition via learning-based reconstruction
A learning based reconstruction and mapping algorithm to generate a feature rich representation from the RGB images used for face identification and shows significant improvements compared to when the original depth map is used for identification.
Accurate and robust face recognition from RGB-D images with a deep learning approach
This paper proposes a face recognition system based on deep learning, which can be used to verify and identify a subject from the colour and depth face images captured with a consumer-level RGB-D camera.
Face Verification from Depth using Privileged Information
The proposed approach efficiently verifies if two face images belong to the same person while handling a great variety of head poses and occlusions, despite the lack of deep-oriented depth-based datasets.
RGB-D Face Recognition With Texture and Attribute Features
The experimental results indicate that the proposed algorithm achieves high face recognition accuracy on RGB-D images obtained using Kinect compared with existing 2D and 3D approaches.
Robust RGB-D Face Recognition Using Attribute-Aware Loss
A new CNN-based face recognition approach that incorporates such attributes into the training process using an attribute-aware loss function that regularizes the feature mapping using attribute proximity, which greatly improve the accuracy and robustness of face recognition.
Convolutional-Recursive Deep Learning for 3D Object Classification
This work introduces a model based on a combination of convolutional and recursive neural networks (CNN and RNN) for learning features and classifying RGB-D images, which obtains state of the art performance on a standardRGB-D object dataset while being more accurate and faster during training and testing than comparable architectures such as two-layer CNNs.
On RGB-D face recognition using Kinect
The experimental results indicate that the RGB-D information obtained by Kinect can be used to achieve improved face recognition performance compared to existing 2D and 3D approaches.
Facial Emotion Recognition Using Light Field Images with Deep Attention-Based Bidirectional LSTM
A new deep network is proposed that first extracts spatial features using a VGG16 convolutional neural network, then a Bidirectional Long Short-Term Memory (Bi-LSTM) recurrent neural network is used to learn spatio-angular features from viewpoint feature sequences, exploring both forward and backward angular relationships.
Face recognition based on Kinect
A new algorithm that utilizes low-quality red, green, blue and depth (RGB-D) data from the Kinect sensor for face recognition under challenging conditions and a Finer Feature Fusion technique is developed that removes redundant information and retains only the meaningful features for possible maximum class separability.