Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters

26 May 2016  ·  AJ Piergiovanni, Chenyou Fan, Michael S. Ryoo ·

In this paper, we newly introduce the concept of temporal attention filters, and describe how they can be used for human activity recognition from videos. Many high-level activities are often composed of multiple temporal parts (e.g., sub-events) with different duration/speed, and our objective is to make the model explicitly learn such temporal structure using multiple attention filters and benefit from them. Our temporal filters are designed to be fully differentiable, allowing end-of-end training of the temporal filters together with the underlying frame-based or segment-based convolutional neural network architectures. This paper presents an approach of learning a set of optimal static temporal attention filters to be shared across different videos, and extends this approach to dynamically adjust attention filters per testing video using recurrent long short-term memory networks (LSTMs). This allows our temporal attention filters to learn latent sub-events specific to each activity. We experimentally confirm that the proposed concept of temporal attention filters benefits the activity recognition, and we visualize the learned latent sub-events.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Activity Recognition In Videos DogCentric VTFSA Accuracy 98.55 # 1

Methods


No methods listed for this paper. Add relevant methods here