相关论文: 3D Face Modeling via Weakly-supervised Disentangle…

Unsupervised representation learning, particularly sequential disentanglement, aims to separate static and dynamic factors of variation in data without relying on labels. This remains a challenging problem, as existing approaches based on…

Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However,…

We aim to separate the generative factors of data into two latent vectors in a variational autoencoder. One vector captures class factors relevant to target classification tasks, while the other vector captures style factors relevant to the…

Recent facial image synthesis methods have been mainly based on conditional generative models. Sketch-based conditions can effectively describe the geometry of faces, including the contours of facial components, hair structures, as well as…

Facial Expression Recognition (FER) is an important task in computer vision and has wide applications in human-computer interaction, intelligent security, emotion analysis, and other fields. However, the limited size of FER datasets limits…

3D weakly supervised semantic segmentation (3D WSSS) aims to achieve semantic segmentation by leveraging sparse or low-cost annotated data, significantly reducing reliance on dense point-wise annotations. Previous works mainly employ class…

Face and person recognition have recently achieved remarkable success under challenging scenarios, such as off-pose and cross-spectrum matching. However, long-range recognition systems are often hindered by atmospheric turbulence, leading…

Disentangled representation learning is one of the major goals of deep learning, and is a key step for achieving explainable and generalizable models. A well-defined theoretical guarantee still lacks for the VAE-based unsupervised methods,…

Facial expressions recognition (FER) of 3D face scans has received a significant amount of attention in recent years. Most of the facial expression recognition methods have been proposed using mainly 2D images. These methods suffer from…

We introduce a method to disentangle controllable and uncontrollable factors of variation by interacting with the world. Disentanglement leads to good representations and is important when applying deep neural networks (DNNs) in fields…

A crucial problem in learning disentangled image representations is controlling the degree of disentanglement during image editing, while preserving the identity of objects. In this work, we propose a simple yet effective model with the…

Current state-of-the-art self-supervised approaches, are effective when trained on individual domains but show limited generalization on unseen domains. We observe that these models poorly generalize even when trained on a mixture of…

A disentangled representation of a data set should be capable of recovering the underlying factors that generated it. One question that arises is whether using Euclidean space for latent variable models can produce a disentangled…

Domain Generalization (DG) seeks to develop a versatile model capable of performing effectively on unseen target domains. Notably, recent advances in pre-trained Visual Foundation Models (VFMs), such as CLIP, have demonstrated considerable…

Sensory data are often comprised of independent content and transformation factors. For example, face images may have shapes as content and poses as transformation. To infer separately these factors from given data, various…

With the development of high-throughput technologies, genomics datasets rapidly grow in size, including functional genomics data. This has allowed the training of large Deep Learning (DL) models to predict epigenetic readouts, such as…

Self-supervised learning (SSL) and diffusion models have advanced representation learning and image synthesis, but in 3D medical imaging they are still largely used separately for analysis and synthesis, respectively. Unifying them is…

In response to the rapid growth of Internet of Things (IoT) devices and rising security risks, Radio Frequency Fingerprint (RFF) has become key for device identification and authentication. However, various changing factors - beyond the RFF…

Although face swapping has attracted much attention in recent years, it remains a challenging problem. Existing methods leverage a large number of data samples to explore the intrinsic properties of face swapping without considering the…

In this paper, we present a novel strategy to design disentangled 3D face shape representation. Specifically, a given 3D face shape is decomposed into identity part and expression part, which are both encoded and decoded in a nonlinear way.…