Search Results for author:
Found 2 papers, 2 papers with code
TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition
The first stage locates the action by learning a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature (e. g. background).
SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
