Guo-Jun Qi
Overview
Explore the profile of Guo-Jun Qi including associated specialties, affiliations and a list of published articles.
Author names and details appear as published. Due to indexing inconsistencies, multiple individuals may share a name, and a single author may have variations. MedLuna displays this data as publicly available, without modification or verification
Snapshot
Snapshot
Articles
34
Citations
108
Followers
0
Related Specialties
Related Specialties
Top 10 Co-Authors
Top 10 Co-Authors
Published In
Published In
Affiliations
Affiliations
Soon will be listed here.
Recent Articles
1.
Xu C, Liu P, Chapman J, Wotton K, Qi G, Wang Y, et al.
Insects
. 2024 Oct;
15(10).
PMID: 39452385
Striking a trade-off between migration and reproduction becomes imperative during long-range migration to ensure proper energy allocation. However, the mechanisms involved in this trade-off remain poorly understood. Here, we used...
2.
Gao X, Yang Y, Wu Y, Du S, Qi G
IEEE Trans Image Process
. 2024 Jun;
33:3907-3920.
PMID: 38900622
Inferring 3D human motion is fundamental in many applications, including understanding human activity and analyzing one's intention. While many fruitful efforts have been made to human motion prediction, most approaches...
3.
Liu L, Jiang X, Zheng F, Chen H, Qi G, Huang H, et al.
IEEE Trans Pattern Anal Mach Intell
. 2023 Oct;
46(1):1-16.
PMID: 37812559
Federated learning (FL) allows multiple clients to collaboratively learn a globally shared model through cycles of model aggregation and local model training, without the need to share data. Most existing...
4.
Zhang S, Cao X, Wang R, Qi G, Zhou J
IEEE Trans Image Process
. 2023 Sep;
32:5394-5407.
PMID: 37721874
Human parsing aims to segment each pixel of the human image with fine-grained semantic categories. However, current human parsers trained with clean data are easily confused by numerous image corruptions...
5.
Wang Y, Xuan Z, Ho C, Qi G
IEEE Trans Image Process
. 2023 Aug;
32:4459-4471.
PMID: 37527313
Semi-supervised dense prediction tasks, such as semantic segmentation, can be greatly improved through the use of contrastive learning. However, this approach presents two key challenges: selecting informative negative samples from...
6.
Wang X, Huang Y, Zeng D, Qi G
IEEE Trans Pattern Anal Mach Intell
. 2023 Apr;
45(9):10718-10730.
PMID: 37030807
As a representative self-supervised method, contrastive learning has achieved great successes in unsupervised training of representations. It trains an encoder by distinguishing positive samples from negative ones given query anchors....
7.
Gao G, Xu Z, Li J, Yang J, Zeng T, Qi G
IEEE Trans Image Process
. 2023 Apr;
32:1978-1991.
PMID: 37030697
Recently, deep convolution neural networks (CNNs) steered face super-resolution methods have achieved great progress in restoring degraded facial details by joint training with facial priors. However, these methods have some...
8.
Li Z, Tang H, Peng Z, Qi G, Tang J
IEEE Trans Neural Netw Learn Syst
. 2023 Apr;
PP.
PMID: 37022403
Deep learning-based models have been shown to outperform human beings in many computer vision tasks with massive available labeled training data in learning. However, humans have an amazing ability to...
9.
Wang X, Qi G
IEEE Trans Pattern Anal Mach Intell
. 2022 Sep;
45(5):5549-5560.
PMID: 36049010
Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods are benefited from various data augmentations that are carefully designated to maintain their...
10.
Zhang S, Cao X, Qi G, Song Z, Zhou J
IEEE Trans Image Process
. 2022 Aug;
31:5599-5612.
PMID: 36001523
Most state-of-the-art instance-level human parsing models adopt two-stage anchor-based detectors and, therefore, cannot avoid the heuristic anchor box design and the lack of analysis on a pixel level. To address...