Related papers: Linear Disentangled Representation Learning for Fa…

In this paper, a novel video classification method is presented that aims to recognize different categories of third-person videos efficiently. Our motivation is to achieve a light model that could be trained with insufficient training…

We propose a real time deep learning framework for video-based facial expression capture. Our process uses a high-end facial capture pipeline based on FACEGOOD to capture facial expression. We train a convolutional neural network to produce…

Detecting manipulated images and videos is an important topic in digital media forensics. Most detection methods use binary classification to determine the probability of a query being manipulated. Another important topic is locating…

We present a learning algorithm for human activity recognition in videos. Our approach is designed for UAV videos, which are mainly acquired from obliquely placed dynamic cameras that contain a human actor along with background motion.…

The performance of machine learning and pattern recognition algorithms generally depends on data representation. That is why, much of the current effort in performing machine learning algorithms goes into the design of preprocessing…

A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world down-stream…

Algorithmic detection of facial palsy offers the potential to improve current practices, which usually involve labor-intensive and subjective assessment by clinicians. In this paper, we present a multimodal fusion-based deep learning model…

Race classification is a long-standing challenge in the field of face image analysis. The investigation of salient facial features is an important task to avoid processing all face parts. Face segmentation strongly benefits several face…

Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy-to-implement. While numerous hand-crafted and learning-based representations have…

Recognizing the expressions of partially occluded faces is a challenging computer vision problem. Previous expression recognition methods, either overlooked this issue or resolved it using extreme assumptions. Motivated by the fact that the…

Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited. In this work, we provide evidence that disentangled representations coupled with sparse…

We propose a novel method for real-time face alignment in videos based on a recurrent encoder-decoder network model. Our proposed model predicts 2D facial point heat maps regularized by both detection and regression loss, while uniquely…

Facial expression is the most natural means for human beings to communicate their emotions. Most facial expression analysis studies consider the case of acted expressions. Spontaneous facial expression recognition is significantly more…

In this paper, we propose a framework for disentangling the appearance and geometry representations in the face recognition task. To provide supervision for this aim, we generate geometrically identical faces by incorporating spatial…

This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce…

Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these misleading…

This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that…

Existing deep learning approaches for learning visual features tend to overlearn and extract more information than what is required for the task at hand. From a privacy preservation perspective, the input visual information is not protected…

Face images appeared in multimedia applications, e.g., social networks and digital entertainment, usually exhibit dramatic pose, illumination, and expression variations, resulting in considerable performance degradation for traditional face…

Neural networks employ spurious correlations in their predictions, resulting in decreased performance when these correlations do not hold. Recent works suggest fixing pretrained representations and training a classification head that does…