Pith. sign in

REVIEW

Improving Human Activity Recognition Through Ranking and Re-ranking

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1512.03740 v1 pith:Q7QWIAYR submitted 2015-12-11 cs.CV

Improving Human Activity Recognition Through Ranking and Re-ranking

classification cs.CV
keywords re-rankingactivitycalledfeatureshumanmethodsnormalizationperformance
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.