Search Results for author:
Found 9 papers, 5 papers with code
Towards a Real-Time Facial Analysis System
Facial analysis is an active research area in computer vision, with many practical applications.
On the Importance of Encrypting Deep Features
On the other hand, it is advisable to encrypt feature vectors, especially for a machine learning model in production.
FlipReID: Closing the Gap between Training and Inference in Person Re-Identification
More specifically, models using the FlipReID structure are trained on the original images and the flipped images simultaneously, and incorporating the flipping loss minimizes the mean squared error between feature vectors of corresponding image pairs.
Ranked #3 on
Person Re-Identification
on MSMT17
Adaptive L2 Regularization in Person Re-Identification
We introduce an adaptive L2 regularization mechanism in the setting of person re-identification.
Ranked #6 on
Person Re-Identification
on MSMT17
Vehicle Attribute Recognition by Appearance: Computer Vision Methods for Vehicle Type, Make and Model Classification
This paper studies vehicle attribute recognition by appearance.
Block-optimized Variable Bit Rate Neural Image Compression
In this work, we propose an end-to-end block-based auto-encoder system for image compression.
Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations
We show the effect of l2 normalization on anomaly detection accuracy.
Memory-Efficient Deep Salient Object Segmentation Networks on Gridized Superpixels
By using these encoded images, we train a memory-efficient network using only 0. 048\% of the number of parameters that other deep salient object detection networks have.
Video Ladder Networks
Thanks to the recurrent connections, the decoder can exploit temporal summaries generated from all layers of the encoder.
