ECO: Efficient Convolutional Network for Online Video Understanding

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.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Action Recognition Something-Something V1 ECO-Net Top 1 Accuracy 46.4 # 64

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Uses Extra
Training Data
Source Paper Compare
Action Recognition Something-Something V1 ECO-Net (ImageNet pretrained) Top 1 Accuracy 46.4 # 64

Methods


No methods listed for this paper. Add relevant methods here