Related papers: GEESE: Genotype-aware End-to-End Spatio-temporal E…

Learning user sequence behaviour embedding is very sophisticated and challenging due to the complicated feature interactions over time and high dimensions of user features. Recent emerging foundation models, e.g., BERT and its variants,…

Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on…

We present a new deep learning approach for real-time 3D human action recognition from skeletal data and apply it to develop a vision-based intelligent surveillance system. Given a skeleton sequence, we propose to encode skeleton poses and…

The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for trainable models that can produce natural-looking images with…

Discovering genes with similar functions across diverse biomedical contexts poses a significant challenge in gene representation learning due to data heterogeneity. In this study, we resolve this problem by introducing a novel model called…

Knowledge graph embedding (KGE), aiming to embed entities and relations into low-dimensional vectors, has attracted wide attention recently. However, the existing research is mainly based on the black-box neural models, which makes it…

We develop the sparse VAE for unsupervised representation learning on high-dimensional data. The sparse VAE learns a set of latent factors (representations) which summarize the associations in the observed data features. The underlying…

Graph autoencoders (GAEs) are powerful tools in representation learning for graph embedding. However, the performance of GAEs is very dependent on the quality of the graph structure, i.e., of the adjacency matrix. In other words, GAEs would…

The incredible feats of athleticism demonstrated by humans are made possible in part by a vast repertoire of general-purpose motor skills, acquired through years of practice and experience. These skills not only enable humans to perform…

Accurate and scalable quantification of animal pose and appearance is crucial for studying behavior. Current 3D pose estimation techniques, such as keypoint- and mesh-based techniques, often face challenges including limited…

Our way of grasping objects is challenging for efficient, intelligent and optimal grasp by COBOTs. To streamline the process, here we use deep learning techniques to help robots learn to generate and execute appropriate grasps quickly. We…

Understanding the intertwined contributions of amino acid sequence and spatial structure is essential to explain protein behaviour. Here, we introduce INFUSSE (Integrated Network Framework Unifying Structure and Sequence Embeddings), a deep…

We propose DeepGRU, a novel end-to-end deep network model informed by recent developments in deep learning for gesture and action recognition, that is streamlined and device-agnostic. DeepGRU, which uses only raw skeleton, pose or vector…

This work explores the biases in learning processes based on deep neural network architectures. We analyze how bias affects deep learning processes through a toy example using the MNIST database and a case study in gender detection from…

Graphs are ubiquitous in real-world scenarios and encompass a diverse range of tasks, from node-, edge-, and graph-level tasks to transfer learning. However, designing specific tasks for each type of graph data is often costly and lacks…

Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data…

Gait, the walking pattern of individuals, is one of the most important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as the gait features. These methods suffer from degraded…

This paper explores Masked Autoencoders (MAE) with Gaussian Splatting. While reconstructive self-supervised learning frameworks such as MAE learns good semantic abstractions, it is not trained for explicit spatial awareness. Our approach,…

Surrogate models based on machine learning methods have become an important part of modern engineering to replace costly computer simulations. The data used for creating a surrogate model are essential for the model accuracy and often…

We present a generative adversarial network to synthesize 3D pose sequences of co-speech upper-body gestures with appropriate affective expressions. Our network consists of two components: a generator to synthesize gestures from a joint…