Related papers: CLERF: Contrastive LEaRning for Full Range Head Po…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

Unsupervised sentence representation learning remains a critical challenge in modern natural language processing (NLP) research. Recently, contrastive learning techniques have achieved significant success in addressing this issue by…

We present a pioneering investigation into the application of deep learning techniques to analyze histopathological images for addressing the substantial challenge of automated prognostic prediction. Prognostic prediction poses a unique…

Appearance-based gaze estimation, aiming to predict accurate 3D gaze direction from a single facial image, has made promising progress in recent years. However, most methods suffer significant performance degradation in cross-domain…

Most recent head pose estimation (HPE) methods are dominated by the Euler angle representation. To avoid its inherent ambiguity problem of rotation labels, alternative quaternion-based and vector-based representations are introduced.…

Crucial to the success of training a depth-based 3D hand pose estimator (HPE) is the availability of comprehensive datasets covering diverse camera perspectives, shapes, and pose variations. However, collecting such annotated datasets is…

Contrastive learning has demonstrated great success in representation learning, especially for image classification tasks. However, there is still a shortage in studies targeting regression tasks, and more specifically applications on…

Self-supervised facial representation has recently attracted increasing attention due to its ability to perform face understanding without relying on large-scale annotated datasets heavily. However, analytically, current contrastive-based…

Deep learning has been impressively successful in the last decade in predicting human head poses from monocular images. However, for in-the-wild inputs the research community relies predominantly on a single training set, 300W-LP, of…

3D human pose and shape estimation (HPE) aims to reconstruct the 3D human body, face, and hands from a single image. Although powerful deep learning models have achieved accurate estimation in this task, they require enormous memory and…

Over the last two decades, deep learning has transformed the field of computer vision. Deep convolutional networks were successfully applied to learn different vision tasks such as image classification, image segmentation, object detection…

Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in…

The task of human pose estimation (HPE) deals with the ill-posed problem of estimating the 3D position of human joints directly from images and videos. In recent literature, most of the works tackle the problem mostly by using convolutional…

Modern neural recording techniques such as two-photon imaging or Neuropixel probes allow to acquire vast time-series datasets with responses of hundreds or thousands of neurons. Contrastive learning is a powerful self-supervised framework…

There is an urgent need to apply face alignment in a memory-efficient and real-time manner due to the recent explosion of face recognition applications. However, impact factors such as large pose variation and computational inefficiency,…

Deep candidate generation (DCG) that narrows down the collection of relevant items from billions to hundreds via representation learning has become prevalent in industrial recommender systems. Standard approaches approximate maximum…

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…

Many Click-Through Rate (CTR) prediction works focused on designing advanced architectures to model complex feature interactions but neglected the importance of feature representation learning, e.g., adopting a plain embedding layer for…

Human pose estimation (HPE) with convolutional neural networks (CNNs) for indoor monitoring is one of the major challenges in computer vision. In contrast to HPE in perspective views, an indoor monitoring system can consist of an…

We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network. In particular, we simultaneously learn a pose-joint regressor and a sliding-window body-part…