SPS Blog Article

This blog describes 4 computer vision algorithms for better human analysis, that understand human hand, gesture, pose, and action from various input modalities.

We all experienced the discomfort of communicating with our friends at a cocktail party or in a pub with loud background music. When difficult acoustic scenarios like these occur, we tend to rely on several visual cues, such as lips and mouth movement of the speaker, in order to understand the speech of interest.

Audio pattern recognition is an important research topic in the machine learning area, and includes several tasks such as audio tagging, acoustic scene classification, music classification, speech emotion classification and sound event detection. In this blog, we introduce pretrained audio neural networks (PANNs) trained on the large-scale AudioSet dataset. These PANNs are transferred to other audio related tasks. We investigate the performance and computational complexity of PANNs modeled by a variety of convolutional neural networks. We propose an architecture called Wavegram-Logmel-CNN using both log-mel spectrogram and waveform as input feature.

Recent years, face recognition has made a remarkable breakthrough due to the emergence of deep learning. However, compared with frontal face recognition, many deep face recognition models still suffer serious performance degradation when handling profile faces. To address this issue, we propose a novel Frontal-Centers Guided Loss (FCGFace) to obtain highly discriminative features for face recognition. Most existing discriminative feature learning approaches project features from the same class into a separated latent subspace.

This blog explores modern deep learning applications as well as traditional machine learning techniques for automated X-ray security imaging.

A framework of robust transmission design for reconfigurable intelligent surfaces (RIS) aided systems has been proposed to address the imperfect cascaded channel state information issue.

Recent years have seen great strides being made in R&D of speech and language technologies. As these technologies continue to permeate our daily lives, they need to support diverse users and usage contexts, especially those with inputs that deviate from the mainstream.

In this blog, we investigate the model-driven deep learning for multiple input-multiple output (MIMO) detection. In particular, the MIMO detector is specially designed by unfolding an iterative algorithm and adding some trainable parameters.

A brief introduction to state estimation in multi-object system that arises from applications where the number of objects and their states are unknown and vary randomly with time. State space model (SSM) is a fundamental concept in system theory that permeated through many fields of study.

We design a data-driven wavelet transform, called the empirical wavelet transform, which permits to extract very accurate time-frequency information from signals, or features from images.