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

Add to Chrome

Add to Firefox

Picture for Si Liu

Si Liu

Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks

Aug 21, 2022
Zhaodi Zhang, Yiting Wu, Si Liu, Jing Liu, Min Zhang

Figure 1 for Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks

Figure 2 for Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks

Figure 3 for Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks

Figure 4 for Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks

* Accepted at ASE 2022

Access Paper or Ask Questions

PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation

Aug 16, 2022
Wentao Jiang, Sheng Jin, Wentao Liu, Chen Qian, Ping Luo, Si Liu

Figure 1 for PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation

Figure 2 for PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation

Figure 3 for PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation

Figure 4 for PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation

* Accepted by ECCV 2022

Access Paper or Ask Questions

PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding

Aug 11, 2022
Zihan Ding, Zi-han Ding, Tianrui Hui, Junshi Huang, Xiaoming Wei, Xiaolin Wei, Si Liu

Figure 1 for PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding

Figure 2 for PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding

Figure 3 for PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding

Figure 4 for PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding

* Accepted by ACM MM 2022

Access Paper or Ask Questions

Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation

Jun 08, 2022
Zihan Ding, Tianrui Hui, Junshi Huang, Xiaoming Wei, Jizhong Han, Si Liu

Figure 1 for Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation

Figure 2 for Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation

Figure 3 for Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation

Figure 4 for Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation

* Accepted by CVPR 2022

Access Paper or Ask Questions

Reinforced Structured State-Evolution for Vision-Language Navigation

Apr 20, 2022
Jinyu Chen, Chen Gao, Erli Meng, Qiong Zhang, Si Liu

Figure 1 for Reinforced Structured State-Evolution for Vision-Language Navigation

Figure 2 for Reinforced Structured State-Evolution for Vision-Language Navigation

Figure 3 for Reinforced Structured State-Evolution for Vision-Language Navigation

Figure 4 for Reinforced Structured State-Evolution for Vision-Language Navigation

* Accepted to CVPR 2022

Access Paper or Ask Questions

3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection

Apr 13, 2022
Junyu Luo, Jiahui Fu, Xianghao Kong, Chen Gao, Haibing Ren, Hao Shen, Huaxia Xia, Si Liu

Figure 1 for 3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection

Figure 2 for 3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection

Figure 3 for 3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection

Figure 4 for 3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection

* CVPR 2022, Oral

Access Paper or Ask Questions