Abstract Sparsely activated Mixture-of-Experts (MoE) is becoming a promising paradigm for
multi-task learning (MTL). Instead of compressing multiple tasks' knowledge into a single …

Abstract Model pre-training is a cornerstone of modern visual recognition systems. Although
fully supervised pre-training on datasets like ImageNet is still the de-facto standard, recent …

To investigate the well-observed racial disparities in computer vision systems that analyze
images of humans, researchers have turned to skin tone as a more objective annotation …

Learned embeddings for products are an important building block for web-scale e-
commerce recommendation systems. At Pinterest, we build a single set of product …

The infusion of generative artificial intelligence (AI), as exemplified by models such as
ChatGPT and Bard is proving to be a revolutionary catalyst within the building and …

The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has
led to multiple frameworks for studying manifolds. Many of those methods have shown …

Gait analysis is proven to be a reliable way to perform person identification without relying
on subject cooperation. Walking is a biometric that does not significantly change in short …

Large-scale datasets play a vital role in computer vision. But current datasets are annotated
blindly without differentiation to samples, making the data collection inefficient and …

Abstract Representation learning,\textit {ie} the generation of representations useful for
downstream applications, is a task of fundamental importance that underlies much of the …

The advent of text-image models, most notably CLIP, has significantly transformed the
landscape of information retrieval. These models enable the fusion of various modalities …