Search Results for author:
Found 3 papers, 0 papers with code
MES-Loss: Mutually equidistant separation metric learning loss function
We propose in this paper a new composite DML loss function that, in addition to the intra-class compactness, explicitly implies regulations to enforce the best inter-class separation by mutually equidistantly distributing the centers of the classes.
Ranked #1 on
Image Clustering
on CUB-200-2011
Multi-stage RGB-based Transfer Learning Pipeline for Hand Activity Recognition
For a given RGB image activity sequence, in the first stage, the regions of interest are extracted using a pre-trained neural network (NN).
Efficient Multi-stream Temporal Learning and Post-fusion Strategy for 3D Skeleton-based Hand Activity Recognition
Recognizing first-person hand activity is a challenging task, especially when not enough data are available.
Ranked #1 on
Skeleton Based Action Recognition
on First-Person Hand Action Benchmark
(1:1 Accuracy metric)
