Temporal Convolutional Networks for Action Segmentation and Detection

TL;DR

This paper introduces Temporal Convolutional Networks (TCNs), a new class of models for fine-grained action segmentation and detection in videos, demonstrating superior accuracy and training efficiency over traditional RNN-based methods.

Contribution

The paper proposes TCN architectures with hierarchical and dilated convolutions for improved temporal modeling in action segmentation tasks.

Findings

TCNs outperform RNNs in accuracy and training speed.

Hierarchical TCN captures long-range dependencies effectively.

Large improvements over state-of-the-art on three datasets.

Abstract

The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting local spatiotemporal features from video frames and then feeding them into a temporal classifier that captures high-level temporal patterns. We introduce a new class of temporal models, which we call Temporal Convolutional Networks (TCNs), that use a hierarchy of temporal convolutions to perform fine-grained action segmentation or detection. Our Encoder-Decoder TCN uses pooling and upsampling to efficiently capture long-range temporal patterns whereas our Dilated TCN uses dilated convolutions. We show that TCNs are capable of capturing action compositions, segment durations, and long-range dependencies, and are over a magnitude faster to train than competing LSTM-based Recurrent Neural Networks. We apply these models to three challenging fine-grained datasets and show large improvements over the state of the art.