Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition
This work addresses activity recognition from first-person videos, which is important for applications like assistive technology, but it is incremental as it builds on existing attention-based approaches.
The paper tackles egocentric activity recognition by developing a spatial attention mechanism that focuses on object regions in videos, achieving up to +6% accuracy improvement over the previous state-of-the-art method on standard benchmarks.
In this paper we propose an end-to-end trainable deep neural network model for egocentric activity recognition. Our model is built on the observation that egocentric activities are highly characterized by the objects and their locations in the video. Based on this, we develop a spatial attention mechanism that enables the network to attend to regions containing objects that are correlated with the activity under consideration. We learn highly specialized attention maps for each frame using class-specific activations from a CNN pre-trained for generic image recognition, and use them for spatio-temporal encoding of the video with a convolutional LSTM. Our model is trained in a weakly supervised setting using raw video-level activity-class labels. Nonetheless, on standard egocentric activity benchmarks our model surpasses by up to +6% points recognition accuracy the currently best performing method that leverages hand segmentation and object location strong supervision for training. We visually analyze attention maps generated by the network, revealing that the network successfully identifies the relevant objects present in the video frames which may explain the strong recognition performance. We also discuss an extensive ablation analysis regarding the design choices.