Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video

Abstract

In this paper, we tackle the problem of egocentric action anticipation, i.e., predicting what actions the camera wearer will perform in the near future and which objects they will interact with. Specifically, we contribute Rolling-Unrolling LSTM, a learning architecture to anticipate actions from egocentric videos. The method is based on three components: 1) an architecture comprised of two LSTMs to model the sub-tasks of summarizing the past and inferring the future, 2) a Sequence Completion Pre-Training technique which encourages the LSTMs to focus on the different sub-tasks, and 3) a Modality ATTention (MATT) mechanism to efficiently fuse multi-modal predictions performed by processing RGB frames, optical flow fields and object-based features. The proposed approach is validated on EPIC-Kitchens, EGTEA Gaze+ and ActivityNet. The experiments show that the proposed architecture is state-of-the-art in the domain of egocentric videos, achieving top performances in the 2019 EPIC-Kitchens egocentric action anticipation challenge. The approach also achieves competitive performance on ActivityNet with respect to methods not based on unsupervised pre-training and generalizes to the tasks of early action recognition and action recognition. To encourage research on this challenging topic, we made our code, trained models, and pre-extracted features available at our web page: http://iplab.dmi.unict.it/rulstm.

arXiv admin note: substantial text overlap with arXiv:1905.09035

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Sequence to Sequence Learning with Neural Networks
• Two-Stream Convolutional Networks for Action Recognition in Videos
• Spatiotemporal Residual Networks for Video Action Recognition
• Next-Active-Object prediction from Egocentric Videos

Cited by in corpus (5)

• Visual Object Tracking in First Person Vision
• POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World
• Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
• Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
• SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos