Pith. sign in

REVIEW

Exploring Feature Representation and Training strategies in Temporal Action Localization

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 1905.10608 v2 pith:XZTAQKAC submitted 2019-05-25 cs.CV

classification cs.CV
keywords featurelocalizationmethodsactionperformancerepresentationstrategiestemporal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Temporal action localization has recently attracted significant interest in the Computer Vision community. However, despite the great progress, it is hard to identify which aspects of the proposed methods contribute most to the increase in localization performance. To address this issue, we conduct ablative experiments on feature extraction methods, fixed-size feature representation methods and training strategies, and report how each influences the overall performance. Based on our findings, we propose a two-stage detector that outperforms the state of the art in THUMOS14, achieving a mAP@tIoU=0.5 equal to 44.2%.

Discussion (0). Sign in to comment.

Pith tools