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.

IEEE SPS has built a streamlined mechanism for employers to add a job announcement by simply filling in a simple job opportunity submission Web form related to a particular TC field. To submit job announcements for a particular Technical Committee, the submission form can be found by visiting the page below and selecting a particular TC.

Graph neural networks (GNNs) have achieved impressive results in various graph learning tasks and they have found their way into many application domains. Despite their proliferation, our understanding of their robustness properties is still very limited. 

Novel computational signal and image analysis approaches based on feature-rich mathematical/computational frameworks continue to push the limits of the technological envelope, thus providing optimized and efficient solutions.

IEEE Signal Processing Society Past President Ahmed Tewfik, in his capacity as Chair of the Society’s Nominations and Appointments Committee, invites nominations for the IEEE Signal Processing Society Officer positions of President-Elect, Vice President-Conferences, and Vice President-Publications.

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 advances in multimodal processing have led to promising solutions for speech-processing tasks. One example is automatic speech recognition (ASR), which is a key component in current speech-based systems.

The IEEE Signal Processing Society (SPS) announces the 2023 Class of Distinguished Lecturers and Distinguished Industry Speakers for the term of 1 January 2023 to 31 December 2024.  The IEEE SPS Distinguished Lecturer (DL) Program provides a means for Chapters to have access to well-known educators and authors in the fields of signal processing to lecture at Chapter meetings.

While message-passing neural networks (MPNNs) are the most popular architectures for graph learning, their expressive power is inherently limited. In order to gain increased expressive power while retaining efficiency, several recent works apply MPNNs to subgraphs of the original graph. 

IEEE SPS has built a streamlined mechanism for employers to add a job announcement by simply filling in a simple job opportunity submission Web form related to a particular TC field. To submit job announcements for a particular Technical Committee, the submission form can be found by visiting the page below and selecting a particular TC.