ECO: Efficient Convolutional Network for Online Video Understanding

TL;DR

This paper introduces ECO, a convolutional network architecture that efficiently captures long-term video content for online understanding, enabling fast processing and high-quality classification and captioning.

Contribution

ECO integrates long-term content modeling directly into the network, significantly improving speed and accuracy for online video understanding tasks.

Findings

Achieves up to 230 videos per second processing speed.

Outperforms state-of-the-art methods by 10x to 80x in speed.

Maintains competitive accuracy across multiple datasets.

Abstract

The state of the art in video understanding suffers from two problems: (1) The major part of reasoning is performed locally in the video, therefore, it misses important relationships within actions that span several seconds. (2) While there are local methods with fast per-frame processing, the processing of the whole video is not efficient and hampers fast video retrieval or online classification of long-term activities. In this paper, we introduce a network architecture that takes long-term content into account and enables fast per-video processing at the same time. The architecture is based on merging long-term content already in the network rather than in a post-hoc fusion. Together with a sampling strategy, which exploits that neighboring frames are largely redundant, this yields high-quality action classification and video captioning at up to 230 videos per second, where each video can consist of a few hundred frames. The approach achieves competitive performance across all datasets while being 10x to 80x faster than state-of-the-art methods.