Active Learning for Online Recognition of Human Activities from Streaming Videos

TL;DR

This paper introduces an incremental, parameterless active learning method for recognizing human activities from streaming videos, capable of adapting to arbitrary data streams while maintaining fixed model size and high accuracy.

Contribution

It proposes a novel approach that incrementally learns local classifiers, employs active learning, and remains scalable and parameterless for streaming video recognition.

Findings

Competitive accuracy with non-incremental methods

Outperforms existing active incremental baselines

Maintains fixed model size during streaming

Abstract

Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily long. Furthermore, as parameter tuning is problematic in a streaming setting, suitable approaches should be parameterless, and make no assumptions on what class labels may occur in the stream. We present here an approach to the recognition of human actions from streaming data which meets all these requirements by: (1) incrementally learning a model which adaptively covers the feature space with simple local classifiers; (2) employing an active learning strategy to reduce annotation requests; (3) achieving promising accuracy within a fixed model size. Extensive experiments on standard benchmarks show that our approach is competitive with state-of-the-art non-incremental methods, and outperforms the existing active incremental baselines.