Search Results for author:
Found 4 papers, 1 papers with code
Robust Unsupervised Multi-Object Tracking in Noisy Environments
We resolve this problem by introducing a robust unsupervised multi-object tracking (MOT) model: AttU-Net.
Cycle-Contrast for Self-Supervised Video Representation Learning
We present Cycle-Contrastive Learning (CCL), a novel self-supervised method for learning video representation.
Augmented Hard Example Mining for Generalizable Person Re-Identification
Although the performance of person re-identification (Re-ID) has been much improved by using sophisticated training methods and large-scale labelled datasets, many existing methods make the impractical assumption that information of a target domain can be utilized during training.
General Classification
Generalizable Person Re-identification
Active Generative Adversarial Network for Image Classification
Sufficient supervised information is crucial for any machine learning models to boost performance.
