Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining. Existing algorithms generally formulate the task as selection from a set of bounding box proposals obtained from deep net based systems. In this work, we demonstrate that we can cast the problem of textual grounding into a unified framework that permits efficient search over all...

Discriminative training applied to hidden Markov model (HMM) design can yield significant benefits in recognition accuracy and model compactness. However, compared to Maximum Likelihood based methods, discriminative training typically requires much more computation, as all competing candidates must be considered, not just the correct one. The choice of the algorithm used to optimize the discrim...

Abstract The recent advances of wearable sensors are remarkable but there still limitations that they need to be refabricated tune the sensor for target signal. However, biological sensory systems have inherent potential adjust their sensitivity according external environment, allowing a broad and enhanced detection. Here, we developed Tunable, Ultrasensitive, Nature-inspired, Epidermal Sensor ...

Single crystal Lithium Fluoride (LiF) has been base-lined as one of the optical materials for the Near Infra-Red Camera (NIRCam) on the James Webb Space Telescope (JWST). Optically, this material is outstanding for use in the near IR. Unfortunately, it has poor mechanical properties that make it very difficult for use in any appreciable size on cryogenic space based instruments. In addition to ...

Methods for automated detection of DNA restriction fragments resolved on agarose fingerprinting gels are described. We present a mathematical model for the location and shape of the restriction fragments as a function of fragment size, with model parameters determined empirically from marker lanes containing molecular size standards. Automated identification of restriction fragments involves se...