Junfeng Wu
PhD Candidate
Wuhan, Hubei, China
Summary
🤩
RockstarJunfeng Wu is a PhD candidate at Huazhong University of Science and Technology specializing in computer vision, with seven years of hands-on experience in research and engineering. Based in Wuhan, he blends academic rigor with practical implementation, tackling visual recognition and perception problems that bridge theory and application. Though primarily research-focused, his GitHub presence signals active experimentation and tooling around vision tasks. Colleagues describe him as methodical and curious, often exploring less obvious cross-disciplinary approaches to improve model robustness. He aims to translate novel vision techniques into reproducible code and impactful publications.
7 years of coding experience
Github Skills (18)
autoregressive-models10
transformer-architecture10
text-to-image9
detectron9
generative-ai9
generative9
object-detection9
transformer8
tokenizer8
instance-segmentation8
image-reconstruction8
large-language-models7
language-model6
large-scale5
multimodal5
Programming languages (2)
Github contributions (5)
FoundationVision/VNext
Jul 2022 - Nov 2022
Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))
Contributions:17 commits, 35 pushes, 3 branches in 3 months
detectroninstance-segmentationobject-detectiontransformervideo-instance-segmentation
wjf5203/SeqFormer
Dec 2021 - Jul 2022
SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022 Oral)
Contributions:17 commits, 13 pushes, 14 comments in 7 months
instance-segmentationvideo-instance-segmentationtransformer-architecture
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.