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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Xinyu Yang

Xinyu Yang
Alert button

FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer


Jan 20, 2023
Zhijian Liu, Xinyu Yang, Haotian Tang, Shang Yang, Song Han

Add code
Alert button

Figure 1 for FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
Figure 2 for FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
Figure 3 for FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
Figure 4 for FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
* The first two authors contributed equally to this work 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Zebra: Deeply Integrating System-Level Provenance Search and Tracking for Efficient Attack Investigation


Nov 10, 2022
Xinyu Yang, Haoyuan Liu, Ziyu Wang, Peng Gao

Add code
Alert button

Figure 1 for Zebra: Deeply Integrating System-Level Provenance Search and Tracking for Efficient Attack Investigation
Figure 2 for Zebra: Deeply Integrating System-Level Provenance Search and Tracking for Efficient Attack Investigation
Figure 3 for Zebra: Deeply Integrating System-Level Provenance Search and Tracking for Efficient Attack Investigation
Figure 4 for Zebra: Deeply Integrating System-Level Provenance Search and Tracking for Efficient Attack Investigation

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations


Oct 25, 2022
Huaxiu Yao, Xinyu Yang, Allan Zhou, Chelsea Finn

Add code
Alert button

Figure 1 for Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations
Figure 2 for Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations
Figure 3 for Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations
Figure 4 for Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms


Sep 14, 2022
Hang Chen, Keqing Du, Xinyu Yang, Chenguang Li

Add code
Alert button

Figure 1 for A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms
Figure 2 for A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms
Figure 3 for A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms
Figure 4 for A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms
* 26 pages,10 figures. arXiv admin note: text overlap with arXiv:2012.07138, arXiv:1605.08179, arXiv:2203.14237 by other authors 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extraction


Aug 30, 2022
Hang Chen, Xinyu Yang, Xiang Li

Add code
Alert button

Figure 1 for Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extraction
Figure 2 for Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extraction
Figure 3 for Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extraction
Figure 4 for Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extraction

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance Segmentation


Aug 22, 2022
Chengxi Zeng, Xinyu Yang, Majid Mirmehdi, Alberto M Gambaruto, Tilo Burghardt

Add code
Alert button

Figure 1 for Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance Segmentation
Figure 2 for Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance Segmentation
Figure 3 for Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance Segmentation
Figure 4 for Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance Segmentation
* Accepted by International Conference on Machine Vision 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour


Aug 07, 2022
Feixiang Zhou, Xinyu Yang, Fang Chen, Long Chen, Zheheng Jiang, Hui Zhu, Reiko Heckel, Haikuan Wang, Minrui Fei, Huiyu Zhou

Add code
Alert button

Figure 1 for Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour
Figure 2 for Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour
Figure 3 for Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour
Figure 4 for Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

FACM: Correct the Output of Deep Neural Network with Middle Layers Features against Adversarial Samples


Jun 02, 2022
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao

Add code
Alert button

Figure 1 for FACM: Correct the Output of Deep Neural Network with Middle Layers Features against Adversarial Samples
Figure 2 for FACM: Correct the Output of Deep Neural Network with Middle Layers Features against Adversarial Samples
Figure 3 for FACM: Correct the Output of Deep Neural Network with Middle Layers Features against Adversarial Samples
Figure 4 for FACM: Correct the Output of Deep Neural Network with Middle Layers Features against Adversarial Samples

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Mask-Guided Divergence Loss Improves the Generalization and Robustness of Deep Neural Network


Jun 02, 2022
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao

Add code
Alert button

Figure 1 for Mask-Guided Divergence Loss Improves the Generalization and Robustness of Deep Neural Network
Figure 2 for Mask-Guided Divergence Loss Improves the Generalization and Robustness of Deep Neural Network
Figure 3 for Mask-Guided Divergence Loss Improves the Generalization and Robustness of Deep Neural Network
Figure 4 for Mask-Guided Divergence Loss Improves the Generalization and Robustness of Deep Neural Network

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation


May 26, 2022
Zhijian Liu, Haotian Tang, Alexander Amini, Xinyu Yang, Huizi Mao, Daniela Rus, Song Han

Add code
Alert button

Figure 1 for BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
Figure 2 for BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
Figure 3 for BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
Figure 4 for BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
* The first two authors contributed equally to this work. Project page: https://bevfusion.mit.edu 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>