How do young children direct their attention to other people in the natural world? While many studies have examined the perception of faces and of goal-directed actions, relatively little work has focused on what children will look at in unconstrained viewing environments. To address this question we showed videos of objects, faces, children playing with toys, and complex social scenes to a lar...

Recent research has demonstrated that involuntary attention improves target identification accuracy for letters using non-predictive peripheral cues, helping to resolve some of the controversy over performance enhancement from involuntary attention. While various cueing studies have demonstrated that their reported cueing effects were not due to response bias to the cue, very few investigations...

Recently, attention-based encoder-decoder (AED) models have shown state-of-the-art performance in automatic speech recognition (ASR). As the original AED with global attentions are not capable of online inference, various attention schemes been developed to reduce ASR latency for better user experience. However, a common limitation conventional softmax-based approaches is that they introduce an...

Drum–Buffer–Rope is a theory of constraints production planning methodology that operates by developing a schedule for the system’s first bottleneck. The first bottleneck is the bottleneck with the highest utilization. In the theory of constraints, any job that is not processed at the first bottleneck is referred to as a free good. Free goods do not use capacity at the first bottleneck, so very...

We propose a recurrent neural network (RNN) based model for image multi-label classification. Our model uniquely integrates and learning of visual attention and Long Short Term Memory (LSTM) layers, which jointly learns the labels of interest and their co-occurrences, while the associated image regions are visually attended. Different from existing approaches utilize either model in their netwo...