# The role of ego vision in view-invariant action recognition

## TL;DR

This paper investigates how ego-vision influences view-invariant action recognition, leveraging transfer learning in CNNs to understand the capabilities and limitations of egocentric data for recognizing actions across different viewpoints.

## Contribution

It introduces a transfer learning approach in CNNs to analyze view-invariant action recognition in egocentric videos, highlighting the peculiarities and potential of ego-vision.

## Key findings

- Transfer learning improves view-invariance in egocentric action recognition.
- Ego-vision data presents unique challenges for view-invariant recognition.
- The study provides insights into the limitations of current CNN-based methods for egocentric data.

## Abstract

Analysis and interpretation of egocentric video data is becoming more and more important with the increasing availability and use of wearable cameras. Exploring and fully understanding affinities and differences between ego and allo (or third-person) vision is paramount for the design of effective methods to process, analyse and interpret egocentric data. In addition, a deeper understanding of ego-vision and its peculiarities may enable new research perspectives in which first person viewpoints can act either as a mean for easily acquiring large amounts of data to be employed in general-purpose recognition systems, and as a challenging test-bed to assess the usability of techniques specifically tailored to deal with allocentric vision on more challenging settings. Our work, with an eye to cognitive science findings, leverages transfer learning in Convolutional Neural Networks to demonstrate capabilities and limitations of an implicitly learnt view-invariant representation in the specific case of action recognition.