1

Modeling Financial Uncertainty with Multivariate Temporal Entropy-based Curriculums

In the financial realm, profit generation greatly relies on the complicated task of stock prediction. Lately, neural methods have shown success in exploiting stock affecting signals from textual data across news and tweets to forecast stock …

Track, Check, Repeat: An EM Approach to Unsupervised Tracking

We propose an unsupervised method for detecting and tracking moving objects in 3D, in unlabelled RGB-D videos. The method begins with classic handcrafted techniques for segmenting objects using motion cues: we estimate optical flow and camera motion, …

Multimodal Multi-Task Financial Risk Forecasting

Stock price movement and volatility prediction aim to predict stocks' future trends to help investors make sound investment decisions and model financial risk. Companies' earnings calls are a rich, underexplored source of multimodal information for …