Industrial designers' thinking in the stage of concept generation for social design: themes, strategies and modes.

Social design produces strategic, systematic solutions or new cultures as a response to the complexity of social changes and, in consequence, designers who are used to the traditional way of ideation may not be well prepared for the requirements of social design. This paper identified the characteristics of the concept generation of industrial design students participating in a social design practice as novices. Using the think-aloud protocol, we collected the conversations and self-reports of students (n = 42).

Deeply Unsupervised Patch Re-Identification for Pre-Training Object Detectors.

Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks. However, most state-of-the-art unsupervised methods concentrate on learning global representations for image-level classification tasks instead of discriminative local region representations, which limits their transferability to region-level downstream tasks, such as object detection. To improve the transferability of pre-trained features to object detection, we present Deeply Unsupervised Patch Re-ID (DUPR), a simple yet effective method for unsupervised visual representation learning.

3D Human Pose Machines with Self-Supervised Learning.

Driven by recent computer vision and robotic applications, recovering 3D human poses has become increasingly important and attracted growing interests. In fact, completing this task is quite challenging due to the diverse appearances, viewpoints, occlusions and inherently geometric ambiguities inside monocular images. Most of the existing methods focus on designing some elaborate priors /constraints to directly regress 3D human poses based on the corresponding 2D human pose-aware features or 2D pose predictions.