Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Yibing Song

Yibing Song

AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition

May 26, 2022
Shoufa Chen, Chongjian Ge, Zhan Tong, Jiangliu Wang, Yibing Song, Jue Wang, Ping Luo

Figure 1 for AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition

Figure 2 for AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition

Figure 3 for AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition

Figure 4 for AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition

* Technical report. Project page: http://www.shoufachen.com/adaptformer-page/

Access Paper or Ask Questions

Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

Apr 01, 2022
Liang Chen, Yong Zhang, Yibing Song, Lingqiao Liu, Jue Wang

Figure 1 for Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

Figure 2 for Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

Figure 3 for Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

Figure 4 for Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

* Accepted by CVPR 2022 (Oral presentation)

Access Paper or Ask Questions

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Mar 23, 2022
Zhan Tong, Yibing Song, Jue Wang, Limin Wang

Figure 1 for VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Figure 2 for VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Figure 3 for VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Figure 4 for VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

* Technical report

Access Paper or Ask Questions

Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Feb 16, 2022
Youwei Liang, Chongjian Ge, Zhan Tong, Yibing Song, Jue Wang, Pengtao Xie

Figure 1 for Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Figure 2 for Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Figure 3 for Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Figure 4 for Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

* ICLR 2022 Spotlight

Access Paper or Ask Questions

MetaDance: Few-shot Dancing Video Retargeting via Temporal-aware Meta-learning

Jan 13, 2022
Yuying Ge, Yibing Song, Ruimao Zhang, Ping Luo

Figure 1 for MetaDance: Few-shot Dancing Video Retargeting via Temporal-aware Meta-learning

Figure 2 for MetaDance: Few-shot Dancing Video Retargeting via Temporal-aware Meta-learning

Figure 3 for MetaDance: Few-shot Dancing Video Retargeting via Temporal-aware Meta-learning

Figure 4 for MetaDance: Few-shot Dancing Video Retargeting via Temporal-aware Meta-learning

Access Paper or Ask Questions

Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning

Oct 11, 2021
Chongjian Ge, Youwei Liang, Yibing Song, Jianbo Jiao, Jue Wang, Ping Luo

Figure 1 for Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning

Figure 2 for Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning

Figure 3 for Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning

Figure 4 for Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning

* Accepted by NeurIPS 2021

Access Paper or Ask Questions

PD-GAN: Probabilistic Diverse GAN for Image Inpainting

May 05, 2021
Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao

Figure 1 for PD-GAN: Probabilistic Diverse GAN for Image Inpainting

Figure 2 for PD-GAN: Probabilistic Diverse GAN for Image Inpainting

Figure 3 for PD-GAN: Probabilistic Diverse GAN for Image Inpainting

Figure 4 for PD-GAN: Probabilistic Diverse GAN for Image Inpainting

* Accepted by CVPR 2021

Access Paper or Ask Questions

ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

Apr 09, 2021
Jie An, Siyu Huang, Yibing Song, Dejing Dou, Wei Liu, Jiebo Luo

Figure 1 for ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

Figure 2 for ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

Figure 3 for ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

Figure 4 for ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

* CVPR 2021 Accepted

Access Paper or Ask Questions