activity
20162022
most citedThe scientific payload on-board the HERMES-TP and HERMES-SP CubeSat missions

28 citations · 91 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV20208 cited

Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory

Xinyu Zhang, Dong Gong, Jiewei Cao +1

Unsupervised cross-domain person re-identification (Re-ID) aims to adapt the information from the labelled source domain to an unlabelled target domain. Due to the lack of supervis…

cs.CV2019

End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization

Bo Chen, Alvaro Parra, Jiewei Cao +2

Deep networks excel in learning patterns from large amounts of data. On the other hand, many geometric vision tasks are specified as optimization problems. To seamlessly combine de…

cs.CV2019

Part-Guided Attention Learning for Vehicle Instance Retrieval

Xinyu Zhang, Rufeng Zhang, Jiewei Cao +3

Vehicle instance retrieval often requires one to recognize the fine-grained visual differences between vehicles. Besides the holistic appearance of vehicles which is easily affecte…

cs.CV2019

Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement

Bo Chen, Jiewei Cao, Alvaro Parra +1

We propose an approach to estimate the 6DOF pose of a satellite, relative to a canonical pose, from a single image. Such a problem is crucial in many space proximity operations, su…

cs.CV2019

Self-training with progressive augmentation for unsupervised cross-domain person re-identification

Xinyu Zhang, Jiewei Cao, Chunhua Shen +1

Person re-identification (Re-ID) has achieved great improvement with deep learning and a large amount of labelled training data. However, it remains a challenging task for adapting…

cs.CV2019

V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices

Damien Teney, Peng Wang, Jiewei Cao +3

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over…