Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment

By Mirco Planamente, Chiara Plizzari, Emanuele Alberti, Barbara Caputo. 2021

13 citations recorded by the source corpus.

First person action recognition is an increasingly researched topic because of the growing popularity of wearable cameras. This is bringing to light cross-domain issues that are yet to be addressed in this context. Indeed, the information extracted from learned representations suffers from an intrinsic environmental bias. This strongly affects the ability to generalize to unseen scenarios, limiting the application of current methods in real settings where trimmed labeled data are not available during training. In this work, we propose to leverage over the intrinsic complementary nature of audio-visual signals to learn a representation that works well on data seen during training, while being able to generalize across different domains. To this end, we introduce an audio-visual loss that aligns the contributions from the two modalities by acting on the magnitude of their feature norm representations. This new loss, plugged into a minimal multi-modal action recognition architecture, leads to strong results in cross-domain first person action recognition, as demonstrated by extensive experiments on the popular EPIC-Kitchens dataset.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Human Action Recognition From Various Data Modalities: A Review (2020, background): “[316] 2020 Feature - - - MAFnet [392] 2021 Feature - - - RNA-Net [393] 2021 Feature,Score - - - IMD-B [394] 2022 Feature - - - MM-ViT [395] 2022 Feature - - - Zhang et al.”