ProFormer: Learning Data-efficient Representations of Body Movement with Prototype-based Feature Augmentation and Visual Transformers

Abstract

Automatically understanding human behaviour allows household robots to identify the most critical needs and plan how to assist the human according to the current situation. However, the majority of such methods are developed under the assumption that a large amount of labelled training examples is available for all concepts-of-interest. Robots, on the other hand, operate in constantly changing unstructured environments, and need to adapt to novel action categories from very few samples. Methods for data-efficient recognition from body poses increasingly leverage skeleton sequences structured as image-like arrays and then used as input to convolutional neural networks. We look at this paradigm from the perspective of transformer networks, for the first time exploring visual transformers as data-efficient encoders of skeleton movement. In our pipeline, body pose sequences cast as image-like representations are converted into patch embeddings and then passed to a visual transformer backbone optimized with deep metric learning. Inspired by recent success of feature enhancement methods in semi-supervised learning, we further introduce PROFORMER -an improved training strategy which uses soft-attention applied on iteratively estimated action category PROtotypes used to augment the embeddings and compute an auxiliary consistency loss. Extensive experiments consistently demonstrate the effectiveness of our approach for one-shot recognition from body poses, achieving state-of-the-art results on multiple datasets and surpassing the best published approach on the challenging NTU-120 one-shot benchmark by 1.84%. Our code will be made publicly available at https: //github.com/KPeng9510/ProFormer.

TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration

“…In modern times, transformer backbones have shown strong capacity in establishing longrange dependency information in image or video data [16], which prove beneficial for many downstream tasks. Based on the pioneering work of Vision Transformer (ViT) [36] for image recognition, architectures of dense prediction transformers [37], [38] and video classification transformers [5], [11], [13], [39], [40] are created. In the activity recognition area, Trear [41] proposes a transformer-based RGB-D egocentric activity recognition framework by adapting self-attention to model temporal structure from different modalities.…”