REVIEW 2 cited by
Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge
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
Signed reviews
read the original abstract
Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. We propose a simple, yet effective, method for the temporal detection of activities in temporally untrimmed videos with the help of untrimmed classification. Firstly, our model predicts the top k labels for each untrimmed video by analysing global video-level features. Secondly, frame-level binary classification is combined with dynamic programming to generate the temporally trimmed activity proposals. Finally, each proposal is assigned a label based on the global label, and scored with the score of the temporal activity proposal and the global score. Ultimately, we show that untrimmed video classification models can be used as stepping stone for temporal detection.
Forward citations
Cited by 2 Pith papers
-
Weakly-supervised Action Localization with Background Modeling
Explicitly modeling background frames and using self-generated top-down attention targets improves weakly-supervised temporal action localization, achieving 26.8 AP@IoU=0.5 on THUMOS14.
-
Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization
ASSG, a seed-growing framework with an erasing classifier, achieves state-of-the-art weakly-supervised temporal action localization, with 25.4% mAP at IoU 0.5 on THUMOS'14 and 32.3% on ActivityNet1.3.
Discussion (0). Continue with ORCID to comment.