CVApr 30, 2019

Memory-Augmented Temporal Dynamic Learning for Action Recognition

arXiv:1904.13080v16 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of unsteady dynamics in long-duration motion for video action recognition, representing an incremental advancement in the field.

The paper tackled the problem of modeling long-term motion dynamics in action recognition by proposing a memory-augmented network with a differential memory controller, achieving consistent improvements on UCF101 and HMDB51 datasets over prior works.

Human actions captured in video sequences contain two crucial factors for action recognition, i.e., visual appearance and motion dynamics. To model these two aspects, Convolutional and Recurrent Neural Networks (CNNs and RNNs) are adopted in most existing successful methods for recognizing actions. However, CNN based methods are limited in modeling long-term motion dynamics. RNNs are able to learn temporal motion dynamics but lack effective ways to tackle unsteady dynamics in long-duration motion. In this work, we propose a memory-augmented temporal dynamic learning network, which learns to write the most evident information into an external memory module and ignore irrelevant ones. In particular, we present a differential memory controller to make a discrete decision on whether the external memory module should be updated with current feature. The discrete memory controller takes in the memory history, context embedding and current feature as inputs and controls information flow into the external memory module. Additionally, we train this discrete memory controller using straight-through estimator. We evaluate this end-to-end system on benchmark datasets (UCF101 and HMDB51) of human action recognition. The experimental results show consistent improvements on both datasets over prior works and our baselines.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes