Personal information

Emails & domains

Verified email addresses

Verified email domains

Websites & social links

google scholar

Keywords

Computer Vision, Deep Learning, Generative AI, Biometric,

Countries

China

Biography

Computer vision researcher @megvii. I am Interested in generative AI, computer vision and deep learning.

Activities

Collapse all

Employment (4)

Kuaishou Technology: Beijing, Beijing, CN

2024-11-11 to present | Senior Researcher (KwaiVGI)
Employment
Source: Self-asserted source
Jiajun Liang

Megvii Technology Limited: Haidian, CN

2018-07-01 to 2024-11-04 | Director (Research)
Employment
Source: Self-asserted source
Jiajun Liang

Megvii Technology Limited: Haidian, CN

2017-07-01 to 2018-07-01 | Researcher (Research)
Employment
Source: Self-asserted source
Jiajun Liang

Megvii Technology Limited: Haidian, CN

2016-04-01 to 2017-07-01 | intern (Research)
Employment
Source: Self-asserted source
Jiajun Liang

Education and qualifications (2)

Tsinghua University: Beijing, Beijing, CN

2014 to 2017 | master (CS)
Education
Source: Self-asserted source
Jiajun Liang

Huazhong University of Science and Technology: Wuhan, CN

2010 to 2014 | Bachelor (EE)
Education
Source: Self-asserted source
Jiajun Liang

Works (48)

Cascade Prompt Learning for Vision-Language Model Adaptation

2025 | Book chapter
DOI: 10.1007/978-3-031-72973-7_18
Contributors: Ge Wu; Xin Zhang; Zheng Li; Zhaowei Chen; Jiajun Liang; Jian Yang; Xiang Li
Source: check_circle
Crossref

Enhancing knowledge distillation for semantic segmentation through text-assisted modular plugins

Pattern Recognition
2025-05 | Journal article
DOI: 10.1016/j.patcog.2024.111329
Contributors: Letian Wu; Shen Zhang; Chuankai Zhang; Zhenyu Zhao; Jiajun Liang; Wankou Yang
Source: check_circle
Crossref

A Simple Baseline for Efficient Hand Mesh Reconstruction

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2024 | Conference paper
Contributors: Zhou, Zhishan; Zhou, Shihao; Lv, Zhi; Zou, Minqiang; Tang, Yao; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects

arXiv preprint arXiv:2403.16428
2024 | Journal article
Contributors: Fan, Zicong; Ohkawa, Takehiko; Yang, Linlin; Lin, Nie; Zhou, Zhishan; Zhou, Shihao; Liang, Jiajun; Gao, Zhong; Zhang, Xuanyang; Zhang, Xue et al.
Source: Self-asserted source
Jiajun Liang

Cascade Prompt Learning for Vision-Language Model Adaptation

arXiv preprint arXiv:2409.17805
2024 | Journal article
Contributors: Wu, Ge; Zhang, Xin; Li, Zheng; Chen, Zhaowei; Liang, Jiajun; Yang, Jian; Li, Xiang
Source: Self-asserted source
Jiajun Liang

MegActor-$$\backslash$Sigma $: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer

arXiv preprint arXiv:2408.14975
2024 | Journal article
Contributors: Yang, Shurong; Li, Huadong; Wu, Juhao; Jing, Minhao; Li, Linze; Ji, Renhe; Liang, Jiajun; Fan, Haoqiang; Wang, Jin
Source: Self-asserted source
Jiajun Liang

MegActor: Harness the Power of Raw Video for Vivid Portrait Animation

arXiv preprint arXiv:2405.20851
2024 | Journal article
Contributors: Yang, Shurong; Li, Huadong; Wu, Juhao; Jing, Minhao; Li, Linze; Ji, Renhe; Liang, Jiajun; Fan, Haoqiang
Source: Self-asserted source
Jiajun Liang

Revisiting Prompt Pretraining of Vision-Language Models

arXiv preprint arXiv:2409.06166
2024 | Journal article
Contributors: Chen, Zhenyuan; Yang, Lingfeng; Chen, Shuo; Chen, Zhaowei; Liang, Jiajun; Li, Xiang
Source: Self-asserted source
Jiajun Liang

Solution of Multiview Egocentric Hand Tracking Challenge ECCV2024

arXiv preprint arXiv:2409.19362
2024 | Journal article
Contributors: Zou, Minqiang; Lv, Zhi; Jin, Riqiang; Zhan, Tian; Yu, Mochen; Tang, Yao; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

Towards RGB-NIR Cross-modality Image Registration and Beyond

arXiv preprint arXiv:2405.19914
2024 | Journal article
Contributors: Li, Huadong; Dong, Shichao; Wang, Jin; Fu, Rong; Jing, Minhao; Liang, Jiajun; Fan, Haoqiang; Ji, Renhe
Source: Self-asserted source
Jiajun Liang

1st Place Solution of Egocentric 3D Hand Pose Estimation Challenge 2023 Technical Report: A Concise Pipeline for Egocentric Hand Pose Reconstruction

arXiv preprint arXiv:2310.04769
2023 | Journal article
Contributors: Zhou, Zhishan; Lv, Zhi; Zhou, Shihao; Zou, Minqiang; Wu, Tong; Yu, Mochen; Tang, Yao; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

Boosting Generalization with Adaptive Style Techniques for Fingerprint Liveness Detection

arXiv preprint arXiv:2310.13573
2023 | Journal article
Contributors: Zhu, Kexin; Lin, Bo; Qiu, Yang; Yule, Adam; Tang, Yao; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

Boosting semi-supervised learning by exploiting all unlabeled data

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2023 | Conference paper
Contributors: Chen, Yuhao; Tan, Xin; Zhao, Borui; Chen, Zhaowei; Song, Renjie; Liang, Jiajun; Lu, Xuequan
Source: Self-asserted source
Jiajun Liang

Cumulative spatial knowledge distillation for vision transformers

Proceedings of the IEEE/CVF International Conference on Computer Vision
2023 | Conference paper
Contributors: Zhao, Borui; Song, Renjie; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

DOT: A Distillation-Oriented Trainer

Proceedings of the IEEE/CVF International Conference on Computer Vision
2023 | Conference paper
Contributors: Zhao, Borui; Cui, Quan; Song, Renjie; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

FAAC: Facial Animation Generation with Anchor Frame and Conditional Control for Superior Fidelity and Editability

arXiv preprint arXiv:2312.03775
2023 | Journal article
Contributors: Li, Linze; Fan, Sunqi; Pu, Hengjun; Bing, Zhaodong; Tang, Yao; Ye, Tianzhu; Yang, Tong; Chen, Liangyu; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

HiDiffusion: Unlocking High-Resolution Creativity and Efficiency in Low-Resolution Trained Diffusion Models

arXiv preprint arXiv:2311.17528
2023 | Journal article
Contributors: Zhang, Shen; Chen, Zhaowei; Zhao, Zhenyu; Chen, Zhenyuan; Tang, Yao; Chen, Yuhao; Cao, Wengang; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

Implicit identity leakage: The stumbling block to improving deepfake detection generalization

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2023 | Conference paper
Contributors: Dong, Shichao; Wang, Jin; Ji, Renhe; Liang, Jiajun; Fan, Haoqiang; Ge, Zheng
Source: Self-asserted source
Jiajun Liang

Joint token pruning and squeezing towards more aggressive compression of vision transformers

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2023 | Conference paper
Contributors: Wei, Siyuan; Ye, Tianzhu; Zhang, Shen; Tang, Yao; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion

arXiv preprint arXiv:2312.00844
2023 | Journal article
Contributors: Li, Huadong; Jing, Minhao; Liang, Jiajun; Fan, Haoqiang; Ji, Renhe
Source: Self-asserted source
Jiajun Liang

Darkvisionnet: Low-light imaging via rgb-nir fusion with deep inconsistency prior

Proceedings of the AAAI Conference on Artificial Intelligence
2022 | Conference paper
Contributors: Jin, Shuangping; Yu, Bingbing; Jing, Minhao; Zhou, Yi; Liang, Jiajun; Ji, Renhe
Source: Self-asserted source
Jiajun Liang

DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior

2022 | Journal article
Source: Self-asserted source
Jiajun Liang

DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior

Proceedings of the AAAI Conference on Artificial Intelligence
2022 | Conference paper
Source: Self-asserted source
Jiajun Liang

Decoupled knowledge distillation

Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition
2022 | Conference paper
Contributors: Zhao, Borui; Cui, Quan; Song, Renjie; Qiu, Yiyu; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

Decoupled Knowledge Distillation

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2022 | Conference paper
Source: Self-asserted source
Jiajun Liang

Discriminability-transferability trade-off: An information-theoretic perspective

European Conference on Computer Vision
2022 | Conference paper
Contributors: Cui, Quan; Zhao, Bingchen; Chen, Zhao-Min; Zhao, Borui; Song, Renjie; Zhou, Boyan; Liang, Jiajun; Yoshie, Osamu
Source: Self-asserted source
Jiajun Liang

Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective

arXiv preprint arXiv:2203.03871
2022 | Journal article
Source: Self-asserted source
Jiajun Liang

Dynamic mlp for fine-grained image classification by leveraging geographical and temporal information

Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
2022 | Conference paper
Contributors: Yang, Lingfeng; Li, Xiang; Song, Renjie; Zhao, Borui; Tao, Juntian; Zhou, Shihao; Liang, Jiajun; Yang, Jian
Source: Self-asserted source
Jiajun Liang

Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
2022 | Conference paper
Source: Self-asserted source
Jiajun Liang

Efficient one pass self-distillation with zipf’s label smoothing

European conference on computer vision
2022 | Conference paper
Contributors: Liang, Jiajun; Li, Linze; Bing, Zhaodong; Zhao, Borui; Tang, Yao; Lin, Bo; Fan, Haoqiang
Source: Self-asserted source
Jiajun Liang

Efficient One Pass Self-distillation with Zipf’s Label Smoothing

2022 | Book chapter
DOI: 10.1007/978-3-031-20083-0_7
Contributors: Jiajun Liang; Linze Li; Zhaodong Bing; Borui Zhao; Yao Tang; Bo Lin; Haoqiang Fan
Source: check_circle
Crossref

Explaining deepfake detection by analysing image matching

European conference on computer vision
2022 | Conference paper
Contributors: Dong, Shichao; Wang, Jin; Liang, Jiajun; Fan, Haoqiang; Ji, Renhe
Source: Self-asserted source
Jiajun Liang

SimpleDG: Simple Domain Generalization Baseline Without Bells and Whistles

European Conference on Computer Vision
2022 | Conference paper
Contributors: Lv, Zhi; Lin, Bo; Liang, Siyuan; Wang, Lihua; Yu, Mochen; Tang, Yao; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

Towards a robust deepfake detector: Common artifact deepfake detection model

arXiv preprint arXiv:2210.14457
2022 | Journal article
Contributors: Dong, Shichao; Wang, Jin; Ji, Renhe; Liang, Jiajun; Fan, Haoqiang; Ge, Zheng
Source: Self-asserted source
Jiajun Liang

Augmentation data synthesis via gans: Boosting latent fingerprint reconstruction

ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2020 | Conference paper
Contributors: Xu, Ying; Wang, Yi; Liang, Jiajun; Jiang, Yong
Source: Self-asserted source
Jiajun Liang

Augmentation data synthesis via gans: Boosting latent fingerprint reconstruction

ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2020 | Conference paper
Source: Self-asserted source
Jiajun Liang

Scene text recognition from two-dimensional perspective

Proceedings of the AAAI conference on artificial intelligence
2019 | Conference paper
Contributors: Liao, Minghui; Zhang, Jian; Wan, Zhaoyi; Xie, Fengming; Liang, Jiajun; Lyu, Pengyuan; Yao, Cong; Bai, Xiang
Source: Self-asserted source
Jiajun Liang

Scene text recognition from two-dimensional perspective

Proceedings of the AAAI Conference on Artificial Intelligence
2019 | Conference paper
Source: Self-asserted source
Jiajun Liang

East: an efficient and accurate scene text detector

Proceedings of the IEEE conference on Computer Vision and Pattern Recognition
2017 | Conference paper
Contributors: Zhou, Xinyu; Yao, Cong; Wen, He; Wang, Yuzhi; Zhou, Shuchang; He, Weiran; Liang, Jiajun
Source: Self-asserted source
Jiajun Liang

East: an efficient and accurate scene text detector

Proceedings of the IEEE conference on Computer Vision and Pattern Recognition
2017 | Conference paper
Source: Self-asserted source
Jiajun Liang

Big data application in education: dropout prediction in edx MOOCs

2016 IEEE second international conference on multimedia big data (BigMM)
2016 | Conference paper
Contributors: Liang, Jiajun; Yang, Jian; Wu, Yongji; Li, Chao; Zheng, Li
Source: Self-asserted source
Jiajun Liang

Big data application in education: dropout prediction in edx MOOCs

2016 IEEE second international conference on multimedia big data (BigMM)
2016 | Conference paper
Source: Self-asserted source
Jiajun Liang

Discover learning behavior patterns to predict certification

2016 11th International Conference on Computer Science & Education (ICCSE)
2016 | Conference paper
Contributors: Zhao, Chongchong; Yang, Jian; Liang, Jiajun; Li, Chao
Source: Self-asserted source
Jiajun Liang

Discover learning behavior patterns to predict certification

2016 11th International Conference on Computer Science & Education (ICCSE)
2016 | Conference paper
Source: Self-asserted source
Jiajun Liang

Machine learning application in MOOCs: Dropout prediction

2016 11th International conference on computer science & education (ICCSE)
2016 | Conference paper
Contributors: Liang, Jiajun; Li, Chao; Zheng, Li
Source: Self-asserted source
Jiajun Liang

Machine learning application in MOOCs: Dropout prediction

2016 11th International Conference on Computer Science & Education (ICCSE)
2016 | Conference paper
Source: Self-asserted source
Jiajun Liang

Supplementary Materials for “Dynamic MLP for Fine-Grained Image Classification”

Journal article
Contributors: Yang, Lingfeng; Li, Xiang; Song, Renjie; Zhao, Borui; Tao, Juntian; Zhou, Shihao; Liang, Jiajun; Yang, Jian
Source: Self-asserted source
Jiajun Liang

Supplementary Materials for “Dynamic MLP for Fine-Grained Image Classification”

Journal article
Source: Self-asserted source
Jiajun Liang
How many people are using ORCID?