Training Physical and Geometrical Mid-Points for Multi-person Pose Estimation and Human Detection Under Congestion and Low Resolution.

This paper introduces the design and evaluation of NeoPose which is developed for multi-person pose estimation and human detection. The design of NeoPose is targeting the issue of human detection under congested situation and with low resolution in the image. Under such situations, we compared the performance of different versions of NeoPose as well as other existing algorithms in a human detection task. Throughout the task, the usefulness of two kinds of mid-point (physical and geometrical mid-points) and a deconvolution structure was discussed. Experiment results indicated that NeoPose which applied geometrical mid-points and deconvolution structure performed the best in terms of both precision and recall in the evaluation.

FaceLooks: A Smart Headband for Signaling Face-to-Face Behavior.

Eye-to-eye contact and facial expressions are key communicators, yet there has been little done to evaluate the basic properties of face-to-face; mutual head orientation behaviors. This may be because there is no practical device available to measure the behavior. This paper presents a novel headband-type wearable device called FaceLooks, used for measuring the time of the face-to-face state with identity of the partner, using an infrared emitter and receiver. It can also be used for behavioral healthcare applications, such as for children with developmental disorders who exhibit difficulties with the behavior, by providing awareness through the visual feedback from the partner’s device. Two laboratory experiments showed the device’s detection range and response time, tested with a pair of dummy heads. Another laboratory experiment was done with human participants with gaze trackers and showed the device’s substantial agreement with a human observer. We then conducted two field studies involving children with intellectual disabilities and/or autism spectrum disorders. The first study showed that the devices could be used in the school setting, observing the children did not remove the devices. The second study showed that the durations of children’s face-to-face behavior could be increased under a visual feedback condition. The device shows its potential to be used in therapy and experimental fields because of its wearability and its ability to quantify and shape face-to-face behavior.