1var data = { 2 "publications": 3 [ 4 // { 5 // "highlight": true, 6 // "img": "", 7 // "title": "", 8 // "authors": "", 9 // "conference": "", 10 // "year": , 11 // "arxiv": "", 12 // "github": "", 13 // }, 14 { 15 "highlight": true, 16 "img": "images/StableGuard.png", 17 "title": "StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models", 18 "authors": "Haoxin Yang, Bangzhen Liu, Xuemiao Xu, Cheng Xu✉, Yuyang Yu, Zikai Huang, Yi Wang, and Shengfeng He", 19 // "preprint": "arXiv", 20 "conference": "The Thirty-ninth Annual Conference on Neural Information Processing Systems (<b>NeurIPS</b>)", 21 "year": 2025, 22 "arxiv": "", 23 "pdf": "https://cschengxu.github.io/", 24 }, 25 { 26 "highlight": true, 27 "img": "images/FR2Seg.png", 28 "title": "FR<sup>2</sup>Seg: Continual Segmentation Across Multiple Sites via Fourier Style Replay and Adaptive Consistency Regularization", 29 "authors": "Cheng Xu, Weiwen Zhang, Hongrui Zhang, Xuemiao Xu, Huaidong Zhang, Jing Zou, and Jing Qin", 30 // "preprint": "arXiv", 31 "conference": "The Thirty-Ninth AAAI Conference on Artificial Intelligence (<b>AAAI</b>)", 32 "year": 2025, 33 "arxiv": "", 34 "pdf": "https://cschengxu.github.io/", 35 }, 36 { 37 "highlight": true, 38 "img": "images/Tongue.png", 39 "title": "Dr. Tongue: Sign-Oriented Multi-label Detection for Remote Tongue Diagnosis", 40 "authors": "Yiliang Chen, Steven SC Ho, Cheng Xu✉, Yao Jie Xie, Wing Fai Yeung, Shengfeng He, and Jing Qin", 41 "conference": "The Thirty-Ninth AAAI Conference on Artificial Intelligence (<b>AAAI</b>)", 42 "year": 2025, 43 "pdf": "https://cschengxu.github.io/", 44 "github": "", 45 }, 46 { 47 "highlight": false, 48 "img": "images/Tongue.png", 49 "title": "SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation", 50 "authors": "Weihong Chen, Xuemiao Xu, Haoxin Yang, Yi Xie, Peng Xiao, Cheng Xu, Huaidong Zhang, and Pheng-Ann Heng", 51 "conference": "IEEE International Conference on Multimedia\&Expo 2025 (<b>ICME</b>)", 52 "year": 2025, 53 "pdf": "https://cschengxu.github.io/", 54 "github": "", 55 }, 56 57 { 58 "highlight": true, 59 "img": "images/Dance.png", 60 "title": "Beat-It: Beat-Synchronized Multi-Condition 3D Dance Generation", 61 "authors": "Zikai Huang, Xuemiao Xu, Cheng Xu✉, Huaidong Zhang, Chenxi Zheng, Jing Qin, and Shengfeng He", 62 "conference": "The European Conference on Computer Vision (<b>ECCV</b>)", 63 "year": 2024, 64 "oral": "Oral, 2.0%", 65 "pdf": "https://cschengxu.github.io/", 66 "github": "", 67 }, 68 69 { 70 "highlight": true, 71 "img": "images/Portrait_shadow.png", 72 "title": "Portrait Shadow Removal via Self-Exemplar Illumination Equalization", 73 "authors": "Qian Huang*, Cheng Xu*, Guiqing Li, Ziheng Wu, Shengxin Liu, and Shengfeng He", 74 // "preprint": "arXiv", 75 "conference": "The 32nd ACM International Conference on Multimedia (<b>ACM MM</b>)", 76 "year": 2024, 77 "oral": "Oral, 3.97%", 78 "pdf": "https://cschengxu.github.io/", 79 "github": "", 80 }, 81 82 { 83 "highlight": false, 84 "img": "images/Portrait_shadow.png", 85 "title": "Exploiting Multi-View Clues for Context-Aware Unified Lumbar MRI Identification and Diagnosis", 86 "authors": "Weiwen Zhang*, Cheng Xu*, Xuemiao Xu, Huaidong Zhang, Rongchen Zhao, and Jing Qin", 87 // "preprint": "arXiv", 88 "conference": "2024 International Joint Conference on Neural Networks (<b>IJCNN</b>)", 89 "year": 2024, 90 "pdf": "https://cschengxu.github.io/", 91 "github": "", 92 }, 93 { 94 "highlight": true, 95 "img": "images/CIRI.png", 96 "title": "CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting", 97 "authors": "Weiying Zheng*, Cheng Xu*, Xuemiao Xu, Wenxi Liu, and Shengfeng He", 98 "conference": "International Conference on Computer Vision (<b>ICCV</b>)", 99 "year": 2023, 100 "pdf": "https://cschengxu.github.io/", 101 "github": "", 102 }, 103 104 { 105 "highlight": false, 106 "img": "images/Portrait_shadow.png", 107 "title": "Spatial-Aware GAN for Instance-Guided Cross-Spectral Face Hallucination", 108 "authors": "Wenpeng Xiao, Cheng Xu, Huaidong Zhang, and Xuemiao Xu", 109 // "preprint": "arXiv", 110 "conference": "Artificial Intelligence: Second CAAI International Conference (<b>CICAI</b>)", 111 "year": 2022, 112 "pdf": "https://cschengxu.github.io/", 113 "github": "", 114 }, 115 116 { 117 "highlight": false,
118 "img": "images/MM2024_QGround.jpg", 119 "title": "GDFace: Gated Deformation for Multi-view Face Image Synthesis", 120 "authors": "Xuemiao Xu, Keke Li, Cheng Xu, and Shengfeng He", 121 "conference": "The Thirty-Fourth AAAI Conference on Artificial Intelligence (<b>AAAI</b>)", 122 "year": 2020, 123 "pdf": "https://cschengxu.github.io/", 124 "github": "", 125 }, 126 127 // ======================================== 128 // Journal papers 129 // ======================================== 130 { 131 "highlight": true, 132 "img": "images/GenPoly.png", 133 "title": "GenPoly: Learning Generalized and Tessellated Shape Priors via 3D Polymorphic Evolving", 134 "authors": "Bangzhen Liu, Yuyang Yu, Xuemiao Xu, Cheng Xu✉, Chenxi Zheng, Haoxin Yang, Shaoyu Huang, and Shengfeng He", 135 "journal": "IEEE Transactions on Pattern Analysis and Machine Intelligence (<b>TPAMI</b>)", 136 "year": "2025", 137 "pdf": "https://cschengxu.github.io/", 138 "github": "", 139 }, 140 { 141 "highlight": true, 142 "img": "images/Pointcloud_generalization.png", 143 "title": "Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning", 144 "authors": "Bangzhen Liu, Chenxi Zheng, Xuemiao Xu, Cheng Xu✉, Huaidong Zhang, and Shengfeng He", 145 "journal": "IEEE Transactions on Pattern Analysis and Machine Intelligence (<b>TPAMI</b>)", 146 "year": "2025", 147 "pdf": "https://cschengxu.github.io/", 148 "github": "", 149 }, 150 { 151 "highlight": true, 152 "img": "images/Think2sing.png", 153 "title": "Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation", 154 "authors": "Zikai Huang, Yihan Zhou, Xuemiao Xu, Cheng Xu✉, Xiaofen Xing, Jing Qin, and Shengfeng He", 155 "journal": "IEEE Transactions on Visualization and Computer Graphics (<b>TVCG</b>)", 156 "year": "2025", 157 "pdf": "https://cschengxu.github.io/", 158 "github": "", 159 }, 160 { 161 "highlight": true, 162 "img": "images/Human_rendering.png", 163 "title": "Delving into Invisible Semantics for Generalized One-shot Neural Human Rendering", 164 "authors": "Yihong Lin, Xuemiao Xu, Huaidong Zhang, Cheng Xu✉, Weijie Li, Yi Xie, Jing Qin, and Shengfeng He", 165 "journal": "IEEE Transactions on Visualization and Computer Graphics (<b>TVCG</b>)", 166 "year": "2025", 167 "pdf": "https://cschengxu.github.io/" 168 }, 169 { 170 "highlight": true, 171 "img": "images/StarPose.png", 172 "title": "StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion", 173 "authors": "Haoxin Yang, Weihong Chen, Xuemiao Xu, Cheng Xu✉, Peng Xiao, Cuifeng Sun, Shaoyu Huang, and Shengfeng He", 174 "journal": "IEEE Transactions on Circuits and Systems for Video Technology (<b>TCSVT</b>)", 175 "year": "2025", 176 "pdf": "https://cschengxu.github.io/", 177 "github": "", 178 }, 179 { 180 "highlight": true, 181 "img": "images/Mix_domain.png", 182 "title": "Open-set Mixed Domain Adaptation via Visual-Linguistic Focal Evolving", 183 "authors": "Bangzhen Liu, Yangyang Xu, Cheng Xu✉, Xuemiao Xu, and Shengfeng He", 184 "journal": "IEEE Transactions on Circuits and Systems for Video Technology (<b>TCSVT</b>)", 185 "year": "2025", 186 "pdf": "https://cschengxu.github.io/", 187 "github": "", 188 }, 189 { 190 "highlight": false, 191 "img": "images/TIP2020_SPARNet.png", 192 "title": "VolumeSwap: Volumetric Decomposed 3D-Aware Face Swapping", 193 "authors": "Yuyuan Chen, Cheng Xu, Xuemiao Xu, Yangyang Xu, Weiying Zheng, Huaidong Zhang, and Shengfeng He", 194 "journal": "Computer Graphics Forum (<b>CGF</b>)", 195 "year": "2025", 196 "pdf": "https://cschengxu.github.io/", 197 "github": "", 198 }, 199 { 200 "highlight": false, 201 "img": "images/TIP2020_SPARNet.png", 202 "title": "Towards Label-free Defect Detection in Additive Manufacturing via Dual-classifier Semi-supervised Learning for Vision-language Models", 203 "authors": "Kang Wang, Lanqing Liu, Cheng Xu, Jing Zou, Haoneng Lin, Naiyu Fang, and Jingchao Jiang", 204 "journal": "Journal of Intelligent Manufacturing (<b>JIMS</b>)", 205 "year": 2025, 206 "pdf": "https://cschengxu.github.io/", 207 "github": "", 208 }, 209 { 210 "highlight": true, 211 "img": "images/Face_anonymization.png", 212 "title": "G<sup>2</sup>Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors", 213 "authors": "Haoxin Yang, Xuemiao Xu, Cheng Xu✉, Huaidong Zhang, Jing Qin, Yi Wang, Pheng-Ann Heng, and Shengfeng He", 214 "journal": "IEEE Transactions on Information Forensics and
214Security (<b>TIFS</b>)", 215 "year": 2024, 216 "pdf": "https://cschengxu.github.io/", 217 "github": "", 218 }, 219 { 220 "highlight": false, 221 "img": "images/TIP2020_SPARNet.png", 222 "title": "Unambiguous Granularity Distillation for Asymmetric Image Retrieval", 223 "authors": "Hongrui Zhang, Yi Xie, Haoquan Zhang, Cheng Xu, Xuandi Luo, Donglei Chen, Xuemiao Xu, Huaidong Zhang, Pheng-Ann Heng, and Shengfeng He", 224 "journal": "Neural Networks (<b>NN</b>)", 225 "year": 2024, 226 "pdf": "https://cschengxu.github.io/", 227 "github": "", 228 }, 229 { 230 "highlight": false, 231 "img": "images/TIP2020_SPARNet.png", 232 "title": "IM-Diff: Implicit Multi-contrast Diffusion Model for Arbitrary Scale MRI Super-Resolution", 233 "authors": "Lanqing Liu, Jing Zou, Cheng Xu, Kang Wang, Jun Lyu, Xuemiao Xu, Zhanli Hu, and Jing Qin", 234 "journal": "Journal of Biomedical and Health Informatics (<b>JBHI</b>)", 235 "year": 2024, 236 "pdf": "https://cschengxu.github.io/", 237 "github": "", 238 }, 239 { 240 "highlight": false, 241 "img": "images/TIP2020_SPARNet.png", 242 "title": "Dual-space High-frequency Learning for Transformer-based MRI Super-resolution", 243 "authors": "Haoneng Lin, Jing Zou, Kang Wang, Yidan Feng, Cheng Xu, Jun Lyu, and Jing Qin", 244 "journal": "Computer Methods and Programs in Biomedicine (<b>CMPB</b>)", 245 "year": 2024, 246 "pdf": "https://cschengxu.github.io/", 247 "github": "", 248 }, 249 { 250 "highlight": true, 251 "img": "images/Human_synthesis.png", 252 "title": "Pose and Attribute Consistent Person Image Synthesis", 253 "authors": "Cheng Xu, Zejun Chen, Jiajie Mai, Xuemiao Xu, and Shengfeng He", 254 "journal": "ACM Transactions Multimedia Computing, Communications, and Applications (<b>TOMM</b>)", 255 "year": 2023, 256 "pdf": "https://cschengxu.github.io/", 257 "github": "", 258 }, 259 { 260 "highlight": true, 261 "img": "images/Cartoon_animations.png", 262 "title": "Multi-scale Flow-based Occluding Effect and Content Separation for Cartoon Animations", 263 "authors": "Cheng Xu, Wei Qu, Xuemiao Xu, and Xueting Liu", 264 "journal": "IEEE Transactions on Visualization and Computer Graphics (<b>TVCG</b>)", 265 "year": "2022", 266 "pdf": "https://cschengxu.github.io/", 267 "github": "", 268 }, 269 { 270 "highlight": true, 271 "img": "images/FDFace.png", 272 "title": "Fully Deformable Network for Multi-view Face Image Synthesis", 273 "authors": "Cheng Xu, Keke Li, Xuandi Luo, Xuemiao Xu, Shengfeng He, and Kun Zhang", 274 "journal": "IEEE Transactions on Neural Networks and Learning Systems (<b>TNNLS</b>)", 275 "year": 2022, 276 "pdf": "https://cschengxu.github.io/", 277 "project": "", 278 }, 279 { 280 "highlight": true, 281 "img": "images/Portrait2Anime.png", 282 "title": "Appearance-preserved Portrait-to-anime Translation via Proxy-guided Domain Adaptation", 283 "authors": "Wenpeng Xiao*, Cheng Xu*, Jiajie Mai, Xuemiao Xu, Chengze Li, Xueting Liu, and Shengfeng He", 284 "journal": "IEEE Transactions on Visualization and Computer Graphics (<b>TVCG</b>)", 285 "year": 2022, 286 "pdf": "https://cschengxu.github.io/", 287 "github": "", 288 }, 289 { 290 "highlight": false, 291 "img": "images/TIP2020_SPARNet.png", 292 "title": "Multi-View Face Synthesis via Progressive Face Flow", 293 "authors": "Yangyang Xu, Xuemiao Xu, Jianbo Jiao, Keke Li, Cheng Xu, and Shengfeng He", 294 "journal": "IEEE Transactions on Image Processing (<b>TIP</b>)", 295 "year": 2021, 296 "pdf": "https://cschengxu.github.io/", 297 "github": "", 298 } 299 ], 300 "fields": 301 { 302 "arxiv": "arxiv", 303 "pdf": "PDF", 304 "github": "Github", 305 }, 306 "author_links": 307 { 308 "Xuemiao Xu": "https://www2.scut.edu.cn/cs/2017/0629/c22284a328094/page.htm", 309 "Shengfeng He": "https://shengfenghe.github.io/", 310 "Jing Qin": "https://harry-qinjing.github.io/", 311 "Huaidong Zhang": "https://www2.scut.edu.cn/ft/2021/1102/c29779a495444/page.htm", 312 "Yangyang Xu":"https://cnnlstm.github.io/", 313 "Pheng-Ann Heng":"https://www.cse.cuhk.edu.hk/~pheng/", 314 "Xueting Liu":"https://www.sfu.edu.hk/en/schools-and-offices/schools-and-departments/school-of-computing-and-information-sciences/staff-directory/dr-tina-liu-xueting/index.html", 315 "Chengze Li":"https://www.sfu.edu.hk/en/schools-and-offices/schools-and-departments/school-of-computing-and-information-sciences/staff-directory/dr-li-chengze/index.html", 316 } 317};
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.