ECO: Efficient Convolutional Network for Online Video Understanding
This addresses the need for efficient online video understanding for applications like fast video retrieval or classification of long-term activities, representing a strong incremental improvement.
The paper tackles the problems of missing long-term relationships and inefficiency in video understanding by introducing a network architecture that merges long-term content internally and uses a sampling strategy to reduce redundancy, achieving competitive performance while being 10x to 80x faster than state-of-the-art methods, with speeds up to 230 videos per second.
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.