Picture for Xiaodan Liang

Xiaodan Liang

Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning

Oct 09, 2022
Yi Cheng, Wenge Liu, Wenjie Li, Jiashuo Wang, Ruihui Zhao, Bang Liu, Xiaodan Liang, Yefeng Zheng

Figure 1 for Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning

Figure 2 for Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning

Figure 3 for Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning

Figure 4 for Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning

* Accepted by the main conference of EMNLP 2022

Access Paper or Ask Questions

DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection

Sep 20, 2022
Lewei Yao, Jianhua Han, Youpeng Wen, Xiaodan Liang, Dan Xu, Wei Zhang, Zhenguo Li, Chunjing Xu, Hang Xu

Figure 1 for DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection

Figure 2 for DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection

Figure 3 for DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection

Figure 4 for DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection

* Accepted to NeurIPS 2022

Access Paper or Ask Questions

Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving

Sep 19, 2022
Xiwen Liang, Yangxin Wu, Jianhua Han, Hang Xu, Chunjing Xu, Xiaodan Liang

Figure 1 for Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving

Figure 2 for Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving

Figure 3 for Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving

Figure 4 for Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving

* Accepted at NeurIPS 2022

Access Paper or Ask Questions

ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design

Aug 11, 2022
Xujie Zhang, Yu Sha, Michael C. Kampffmeyer, Zhenyu Xie, Zequn Jie, Chengwen Huang, Jianqing Peng, Xiaodan Liang

Figure 1 for ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design

Figure 2 for ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design

Figure 3 for ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design

Figure 4 for ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design

* Accepted by ACMMM22

Access Paper or Ask Questions

PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on

Jul 27, 2022
Zhenyu Xie, Zaiyu Huang, Fuwei Zhao, Haoye Dong, Michael Kampffmeyer, Xin Dong, Feida Zhu, Xiaodan Liang

Figure 1 for PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on

Figure 2 for PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on

Figure 3 for PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on

Figure 4 for PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on

* arXiv admin note: substantial text overlap with arXiv:2111.10544

Access Paper or Ask Questions

SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

Jul 27, 2022
Mengxue Qu, Yu Wu, Wu Liu, Qiqi Gong, Xiaodan Liang, Olga Russakovsky, Yao Zhao, Yunchao Wei

Figure 1 for SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

Figure 2 for SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

Figure 3 for SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

Figure 4 for SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

* 21 pages (including Supplementary Materials); Accepted to ECCV 2022

Access Paper or Ask Questions

Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding

Jul 19, 2022
Quande Liu, Youpeng Wen, Jianhua Han, Chunjing Xu, Hang Xu, Xiaodan Liang

Figure 1 for Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding

Figure 2 for Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding

Figure 3 for Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding

Figure 4 for Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding

* Accepted to ECCV 2022

Access Paper or Ask Questions