Task Programming: Learning Data Efficient Behavior Representations.

Specialized domain knowledge is often necessary to accurately annotate training sets for in-depth analysis, but can be burdensome and time-consuming to acquire from domain experts. This issue arises prominently in automated behavior analysis, in which agent movements or actions of interest are detected from video tracking data. To reduce annotation effort, we present TREBA: a method to learn annotation-sample efficient trajectory embedding for behavior analysis, based on multi-task self-supervised learning.

Non-functionalized carbon nanotube binding with hemoglobin.

Carbon nanotube has a high potential to be used as a biosensor and drug carrier. However, its binding behavior with proteins needs to be studied before the full potential of carbon nanotube in biological studies can be realized. Although many studies have been conducted to characterize the affinity of functionalized carbon nanotube to various types of proteins, our present study for the first time reported that hemoglobin can bind with non-functionalized carbon nanotube, and this binding can be identified by Raman spectrum.