Search Results for author:
Found 7 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
LatentForensics: Towards frugal deepfake detection in the StyleGAN latent space
Combined with other recent studies on the interpretation and manipulation of this latent space, we believe that the proposed approach can further help in developing frugal deepfake classification methods based on interpretable high-level properties of face images.
TwistSLAM++: Fusing multiple modalities for accurate dynamic semantic SLAM
However they are often unable to estimate the canonical pose of the objects and exhibit a low object tracking accuracy.
TwistSLAM: Constrained SLAM in Dynamic Environment
Classical visual simultaneous localization and mapping (SLAM) algorithms usually assume the environment to be rigid.
S3LAM: Structured Scene SLAM
We propose a new SLAM system that uses the semantic segmentation of objects and structures in the scene.
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)
L6DNet: Light 6 DoF Network for Robust and Precise Object Pose Estimation with Small Datasets
Estimating the 3D pose of an object is a challenging task that can be considered within augmented reality or robotic applications.
