New object-detection and saliency descriptors, combined with uncertainty-weighted feature hallucination, improve RGB-only action recognition on multiple video benchmarks.
In: 2019 IEEE EMBS International Conference on Biomedical Feature Hallucination for Self-supervised Action Recognition 23 0 0.05 0.1 0.15 0.2square diff
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Feature Hallucination for Self-supervised Action Recognition
New object-detection and saliency descriptors, combined with uncertainty-weighted feature hallucination, improve RGB-only action recognition on multiple video benchmarks.