Jianman Lin

Jianman Lin

Jianman Lin (linjianman). M.Eng. in Electronic Information @ SCUT. Research interests: computer vision, generative AI, controllable image synthesis.

Posts by Collection

portfolio

publications

Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation

Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 — Highlight (top 2.8%) · CCF-A, 2024

ASCCL models spatial-coherent correlations across emotions with a difference-aware adaptive strategy (DAAS); CVPR 2024 Highlight (top 2.8%).

Recommended citation: Tianshui Chen, Jianman Lin, Zhijing Yang, Chunmei Qing, Liang Lin. Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation. CVPR, 2024.
Download Paper

Multiscale Exploration of Informative Latent Features for Accurate Deep Eutectic Solvents Viscosity Prediction

Published in AIChE Journal — flagship journal of AIChE; top-tier in chemical engineering, 2025

Interdisciplinary AI4Science: multiscale latent features for predicting deep eutectic solvent viscosity (AIChE Journal).

Recommended citation: Jianman Lin, et al. Multiscale Exploration of Informative Latent Features for Accurate Deep Eutectic Solvents Viscosity Prediction. AIChE Journal. https://doi.org/10.1002/aic.18924
Download Paper

Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation

Published in International Journal of Computer Vision, Vol. 133, pp. 3822–3838, 2025 · CCF-A, 2025

CDRL: contrastive decoupling of content and emotion with audio and VLM priors for SPFEM.

Recommended citation: Tianshui Chen, Jianman Lin*, Zhijing Yang, Chunmei Qing, Yukai Shi, Liang Lin. (*Co-first author.) Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation. IJCV, 133, 3822–3838, 2025.
Download Paper

Neural Scene Designer: Self-Styled Semantic Image Manipulation

Published in IEEE Transactions on Image Processing, Vol. 34, pp. 6577–6588, 2025 · CCF-A, 2025

Diffusion framework with dual parallel cross-attention for joint text and self-supervised style control (NSD).

Recommended citation: Jianman Lin, Tianshui Chen, Chunmei Qing, Zhijing Yang, Shuangping Huang, Yuheng Ren, Liang Lin. Neural Scene Designer: Self-Styled Semantic Image Manipulation. IEEE TIP, 34, 6577–6588, 2025.
Download Paper

Geometry-Editable and Appearance-Preserving Object Composition

Published in International Journal of Computer Vision (IJCV) — under review · CCF-A, 2025

A geometry-first, appearance-follows paradigm for object composition with diffusion models (DGAD).

Recommended citation: Jianman Lin, Haojie Li, Chunmei Qing, Zhijing Yang, Liang Lin, Tianshui Chen. Geometry-Editable and Appearance-Preserving Object Composition. IJCV (submitted). arXiv:2505.20914.
Download Paper

Learning Spatial-Temporal Coherent Correlations for Speech-Preserving Facial Expression Manipulation

Published in IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) — major revision · CCF-A, 2026

Extension of our CVPR 2024 Highlight work with spatial-temporal coherent modeling for speech-preserving expression editing.

Recommended citation: Tianshui Chen, Jianman Lin*, Zhijing Yang, Chunmei Qing, Liang Lin. (*Co-first author.) Learning Spatial-Temporal Coherent Correlations for Speech-Preserving Facial Expression Manipulation. IEEE TPAMI (under major revision).

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.