Improving Human Activity Recognition Through Ranking and Re-ranking
This work addresses the problem of enhancing accuracy in human activity recognition systems, which is important for applications like surveillance and healthcare, but it is incremental as it builds on existing state-of-the-art features.
The paper tackled improving human activity recognition by proposing two ranking-based methods, rank normalization and multi-class iterative re-ranking, which significantly enhanced performance on six real-world datasets.
We propose two well-motivated ranking-based methods to enhance the performance of current state-of-the-art human activity recognition systems. First, as an improvement over the classic power normalization method, we propose a parameter-free ranking technique called rank normalization (RaN). RaN normalizes each dimension of the video features to address the sparse and bursty distribution problems of Fisher Vectors and VLAD. Second, inspired by curriculum learning, we introduce a training-free re-ranking technique called multi-class iterative re-ranking (MIR). MIR captures relationships among action classes by separating easy and typical videos from difficult ones and re-ranking the prediction scores of classifiers accordingly. We demonstrate that our methods significantly improve the performance of state-of-the-art motion features on six real-world datasets.