The existing pose estimation approaches often require a large number of annotated images
to attain good estimation performance, which are laborious to acquire. To reduce the human …

Active learning seeks to achieve strong performance with fewer training samples. It does this
by iteratively asking an oracle to label newly selected samples in a human-in-the-loop …

Existing datasets for 3D hand-object interaction are limited either in the data cardinality, data
variations in interaction scenarios, or the quality of annotations. In this work, we present a …

Despite the substantial progress in 3D hand pose estimation, inferring plausible and
accurate poses in the presence of severe self-occlusion and high self-similarity remains an …

We present an overview of the SignGuide project. Its main goal is to develop a prototype
interactive museum guide system for deaf visitors using mobile devices that will be able to …

As the amount of labeled data increases, the performance of deep neural networks tends to
improve. However, annotating a large volume of data can be expensive. Active learning …

Active learning continues to remain significant in the industry since it is data efficient. Not
only is it cost effective on a constrained budget, continuous refinement of the model allows …

The ability to retrieve a photo by mere free-hand sketching highlights the immense potential
of Fine-grained sketch-based image retrieval (FG-SBIR). However, its rapid practical …