2023.11, I join in MeiTuan as a senior engineer on LLM Applications.
2023.11, We win the 2nd class prize in The first National Digital Health Innovation Application Competition on Medcial AI Track (link ).
2023.08, A paper about "Cross-modality compression" is accepted by IEEE TMM.
2023.08, Two innovation patents are granted.
2023.05, I join in JD as an engineer on AIGC, focusing on LLMs, image generation and multimodal.
2023.04, one paper about "Conceptual Compression" is accepted by IJCV.
2023.02, one paper about "Cross-modality Compression" is accepted by IEEE TCSVT.
2022.12, I achieve the “Super Post-doctor” funding of Shanghai.
2022.07, I join in Lailo Tech as the technology leader.
2022.07, I join in Fudan University as a post-doctor researcher.
2022.07, one paper on semantic based compression is accepted by ACM MM 2022.
2022.07, one paper on conceptual coding is accepted by ACM MM 2022.
2022.06, I earn my Ph.D. at UCAS.
2021.07, one paper on cross modal compression is accepted by ACM MM 2021.
2021.06, one paper on adversarial attack for voice recognition is accepted by ACM TOMM.
2020.11, the opening report is completed。
2020.06, one paper on speech-to-image translation is accepted by IEEE JSTSP.
2020.03, one paper on adversarial attack to voice recognition is accepted ny IEEE ICME 2020.
2020.03, one paper on adversarial attack to voice recognition is accepted by IEEE ICASSP 2020.
2023.11-now, Seninor CV/NLP Engineer (focus on LLM Applications) in MeiTuan.
2023.05-2023.11, CV/NLP Engineer (focus on AIGC, including LLMs, SD and multimodal) in JD.Inc.
2022.07-2023.04, Technical director in Lailo Technology
2022.03-2022.06, research intern on search&recommendation algorithm in JD.inc
2018.09-2020.09, research intern on multimedia processing in Bytedance.Inc
2016.09-2018.09, part-time intern on image processing in VSCENE.
Gao Junlong, Li Jiguo, Jia Chuanmin, Ma Siwei, Gao Wen. Cross Modal Compression with Variable Rate Prompt[J]. IEEE Transactions on Multimedia(TMM). (Published, TMM, SCI, IF 8.182, CCF B)
Chang Jianhui, Zhang Jian, Li Jiguo, Wang Shanshe, Mao Qi, Jia Chuanmin, Ma Siwei, Gao Wen. Semantic-Aware Visual Decomposition for Image Coding. International Journal of Computer Vision(IJCV). (Published, IJCV, SCI, IF 11.369, CCF A)
Zhang Pingping, Wang Shiqi, Wang Meng, Li Jiguo, Wang Xu, Kwong Sam. Rethinking Semantic Image Compression: Scalable Representation with Cross-modality Transfer[J]. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). (Published, IEEE TCSVT, SCI, IF 5.859, CCF B)
Chang Jianhui, Zhang Jian, Youmin Xu, Li jiguo, Ma Siwei, Gao Wen, Consistency-Contrast Learning for Conceptual Coding[C]//Proceedings of the 30th ACM International Conference on Multimedia(ACM MM). 2022. (Published, ACM MM, EI, CCF A)
Li Jiguo, Jia Chuanmin, Zhang Xinfeng, Ma Siwei, Gao Wen. Cross Modal Compression: Towards Human-comprehensible Semantic Compression[C]//Proceedings of the 29th ACM International Conference on Multimedia(ACM MM). 2021: 4230-4238. (Published, EI, CCF A, First Author)
Li Jiguo, Zhang Xinfeng, Jia Chuanmin, Xu Jizheng, Zhang Li, Wang Yue, Ma Siwei, Gao Wen. Direct speech-to-image translation[J]. IEEE Journal of Selected Topics in Signal Processing(JSTSP), 2020, 14(3): 517-529. (Published, SCI, IF 7.695, First Author, Homepage)
Li Jiguo, Zhang Xinfeng, Xu Jizheng, Ma Siwei, Gao Wen. Learning to Fool the Speaker Recognition[J]. ACM Transactions on Multimedia Computing, Communications, and Applications(TOMM). (Published, ACM TOMM, CCF B, SCI, IF 3.275, First Author, Homepage)
Li Jiguo, Zhang Xinfeng, Jia Chuanmin, Xu Jizheng, Zhang Li, Wang Yue, Ma Siwei, Gao Wen. Universal adversarial perturbations generative network for speaker recognition[C]//2020 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2020: 1-6. (Published, CCF B, EI, First Author, Homepage)
Li Jiguo, Zhang Xinfeng, Xu Jizheng, Zhang Li, Wang Yue, Ma Siwei, Gao Wen. Learning to fool the speaker recognition[C]//2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020: 2937-2941. (Published, CCF B, EI, First Author, Homepage)
黎吉国, 王悦, 张新峰, 马思伟, 高文. 一种鱼眼视频全景拼接中的亮度补偿算法[J]. 中国科学: 信息科学, 2018. (Published, CCF A, 一作, 论文)
黎吉国, 许继征, 马思伟, 王悦. 基于语音的图像生成方法、装置和电子设备. 公开号: 201910042614.9 (授权, link)
马思伟, 黎吉国, 贾川民, 赵政辉, 王苫社. 数据压缩的方法、装置、设备及存储介质. 公开号: 202010604773.6 (公开, link)
黎吉国, 许继征, 张莉, 王悦, 马思伟. 音频对抗扰动的测试方法、设备及存储介质. 公开号: 202011024815.5 (公开, link)
王悦, 姜晓龙, 魏建超, 黎吉国, 孟德国, 刘鑫. 一种全景视频处理制作系统及方法. 公开号: 201711100069.1 (公开, link)
施澍, 黎吉国, 张莉, 马思伟, 王悦. 一种系统延时确定方法、装置、设备和存储介质. 公开号: 202110172567.7 (授权, link)
黎吉国, 许继征, 张莉, 王悦, 马思伟. 声音识别方法、装置以及存储指令的计算机可读存储介质. 公开号: 202010694750.9 (公开, link)
黎吉国, 邹卓, 郑立荣. 一种基于因素分解的从文本到图像的跨模态生成方法. 公开号: 202310415768.4 (公开, link)
2022.12, Super Post-doctor of Shanghai.
2017.10, Best Student Paper Award of 17th China VR.
2017.12, AVS Industrial Innovation Award in 2017.
2015.10, National Scholarship in 2015.
I am a reviewer of following transactions/journals or conferences:
- IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT),
- IEEE Multimedia,
- IEEE CVPR 2021-2023,
- IEEE ICASSP 2021-2023,
- IEEE ICME 2020-2023,
Links to my mentors and friends
Dr. Qi Mao,
Dr. Xiaobin Liu,
Dr. Lingbo Yang,
Dr. Xuesong Niu,
Dr. Chuanmin Jia,
Prof. Xinfeng Zhang,
Prof. Shiqi Wang,
Prof. Lirong Zheng,
Prof. Siwei Ma,
Prof. Wen Gao,
Dr. Jizheng Xu,
Dr. Shu Shi,
Dr. Li Zhang,
Dr. Yue Wang
