We present a framework that automatically and quickly learns a large number of signs from sign language-interpreted TV broadcasts by exploiting supervisory information available in the subtitles. Our contributions are: (i) we show that, somewhat counter-intuitively, mouth patterns are highly informative for distinguishing words in a language for the Deaf, and their co-occurrence with signing ca...

Object detection in large-scale real-world scenes requires efficient multi-class detection approaches. Random forests have been shown to handle large training datasets and many classes for object detection efficiently. The most prominent example is the commercial application of random forests for gaming [37]. In this paper, we describe the general framework of random forests for multi-class obj...

Confounded information is an objective fact when using multi-instance learning (MIL) to classify bags of instances, which may be inherited by MIL embedding methods and lead questionable bag label prediction. To respond this problem, we propose the with deconfounded instance-level prediction algorithm. Unlike traditional embedding-based strategies, design a optimization goal maximize distinction...

In instance-based learning, a training set is given to a classifier for classifying new instances. In practice, not all information in the training set is useful for classifiers. Therefore, it is convenient to discard irrelevant instances from the training set. This process is known as instance reduction, which is an important task for classifiers since through this process the time for classif...

When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy an instance often depends on not only itself but also its context in corresponding bag. From viewpoint causal inference, such bag contextual prior works as a confounder and may result model robustness interpretability issues. Focusing this problem, we propose novel interventional (IMIL...