Liang Lin

OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup

Jan 03, 2023
Zhijing Yang, Junyang Chen, Yukai Shi, Hao Li, Tianshui Chen, Liang Lin

Figure 2 for OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup

Figure 3 for OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup

Figure 4 for OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup

* To be published in IEEE T-MM; Code is available at: https://github.com/JyChen9811/DOC-VTON

Access Paper or Ask Questions

Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification

Jan 02, 2023
Ziyi Tang, Ruimao Zhang, Zhanglin Peng, Jinrui Chen, Liang Lin

Figure 2 for Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification

Figure 3 for Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification

Figure 4 for Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification

* This manuscript was just accepted for publication as a regular paper in the IEEE Transactions on Multimedia. We have uploaded source PdfLateX files this time

Access Paper or Ask Questions

UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression

Dec 06, 2022
Jiaqi Chen, Tong Li, Jinghui Qin, Pan Lu, Liang Lin, Chongyu Chen, Xiaodan Liang

Figure 2 for UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression

Figure 3 for UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression

Figure 4 for UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression

Access Paper or Ask Questions

DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Contrastive Prompt-Tuning

Nov 21, 2022
Ziyi Dong, Pengxu Wei, Liang Lin

Figure 2 for DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Contrastive Prompt-Tuning

Figure 3 for DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Contrastive Prompt-Tuning

Figure 4 for DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Contrastive Prompt-Tuning

Access Paper or Ask Questions

Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels

Nov 15, 2022
Tao Pu, Qianru Lao, Hefeng Wu, Tianshui Chen, Liang Lin

Figure 2 for Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels

Figure 3 for Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels

Figure 4 for Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels

* arXiv admin note: text overlap with arXiv:2205.13092

Access Paper or Ask Questions

Structure-Preserving 3D Garment Modeling with Neural Sewing Machines

Nov 12, 2022
Xipeng Chen, Guangrun Wang, Dizhong Zhu, Xiaodan Liang, Philip H. S. Torr, Liang Lin

Figure 2 for Structure-Preserving 3D Garment Modeling with Neural Sewing Machines

Figure 3 for Structure-Preserving 3D Garment Modeling with Neural Sewing Machines

Figure 4 for Structure-Preserving 3D Garment Modeling with Neural Sewing Machines

* NeurIPS 2022

Access Paper or Ask Questions

Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

Nov 12, 2022
Ziyi Zhang, Weikai Chen, Hui Cheng, Zhen Li, Siyuan Li, Liang Lin, Guanbin Li

Figure 2 for Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

Figure 3 for Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

Figure 4 for Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

* NeurIPS 2022 Accept

Access Paper or Ask Questions

OhMG: Zero-shot Open-vocabulary Human Motion Generation

Oct 28, 2022
Junfan Lin, Jianlong Chang, Lingbo Liu, Guanbin Li, Liang Lin, Qi Tian, Chang-wen Chen

Figure 2 for OhMG: Zero-shot Open-vocabulary Human Motion Generation

Figure 3 for OhMG: Zero-shot Open-vocabulary Human Motion Generation

Figure 4 for OhMG: Zero-shot Open-vocabulary Human Motion Generation

Access Paper or Ask Questions

Layer-wise Shared Attention Network on Dynamical System Perspective

Oct 27, 2022
Zhongzhan Huang, Senwei Liang, Mingfu Liang, Weiling He, Liang Lin

Figure 2 for Layer-wise Shared Attention Network on Dynamical System Perspective

Figure 3 for Layer-wise Shared Attention Network on Dynamical System Perspective

Figure 4 for Layer-wise Shared Attention Network on Dynamical System Perspective

* Work in progress. arXiv admin note: text overlap with arXiv:1905.10671

Access Paper or Ask Questions

Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

Aug 15, 2022
Yang Liu, Guanbin Li, Liang Lin

Figure 2 for Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

Figure 3 for Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

Figure 4 for Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering

* 18 pages, 10 figures. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Access Paper or Ask Questions