The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
— This paper presents an overview of the systematic creation of a human-robot instruction system from a multi-modal corpus. The corpus has been collected from human-to-human card...
This work addresses the problem of human action recognition by introducing a representation of a human action as a collection of short trajectories that are extracted in areas of ...
Antonios Oikonomopoulos, Ioannis Patras, Maja Pant...
This paper presents a method for human action recognition based on patterns of motion. Previous approaches to action recognition use either local features describing small patches...
Abstract. We propose a novel model-based approach to activity recognition using high-level primitives that are derived from a human body model estimated from sensor data. Using sho...