Alert button
Picture for Wankou Yang

Wankou Yang

Alert button

Object-level Geometric Structure Preserving for Natural Image Stitching

Feb 20, 2024
Wenxiao Cai, Wankou Yang

Viaarxiv icon

Correlation-Embedded Transformer Tracking: A Single-Branch Framework

Jan 23, 2024
Fei Xie, Wankou Yang, Chunyu Wang, Lei Chu, Yue Cao, Chao Ma, Wenjun Zeng

Viaarxiv icon

SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition

Dec 11, 2023
Jifeng Shen, Teng Guo, Xin Zuo, Heng Fan, Wankou Yang

Figure 1 for SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition
Figure 2 for SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition
Figure 3 for SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition
Figure 4 for SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition
Viaarxiv icon

CLIP for Lightweight Semantic Segmentation

Oct 11, 2023
Ke Jin, Wankou Yang

Viaarxiv icon

ADNet: Lane Shape Prediction via Anchor Decomposition

Aug 21, 2023
Lingyu Xiao, Xiang Li, Sen Yang, Wankou Yang

Figure 1 for ADNet: Lane Shape Prediction via Anchor Decomposition
Figure 2 for ADNet: Lane Shape Prediction via Anchor Decomposition
Figure 3 for ADNet: Lane Shape Prediction via Anchor Decomposition
Figure 4 for ADNet: Lane Shape Prediction via Anchor Decomposition
Viaarxiv icon

GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds

Aug 16, 2023
Ziyu Li, Jingming Guo, Tongtong Cao, Liu Bingbing, Wankou Yang

Figure 1 for GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds
Figure 2 for GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds
Figure 3 for GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds
Figure 4 for GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds
Viaarxiv icon

ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection

Aug 15, 2023
Jifeng Shen, Yifei Chen, Yue Liu, Xin Zuo, Heng Fan, Wankou Yang

Figure 1 for ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
Figure 2 for ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
Figure 3 for ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
Figure 4 for ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
Viaarxiv icon

VDD: Varied Drone Dataset for Semantic Segmentation

May 23, 2023
Wenxiao Cai, Ke Jin, Jinyan Hou, Cong Guo, Letian Wu, Wankou Yang

Figure 1 for VDD: Varied Drone Dataset for Semantic Segmentation
Figure 2 for VDD: Varied Drone Dataset for Semantic Segmentation
Figure 3 for VDD: Varied Drone Dataset for Semantic Segmentation
Figure 4 for VDD: Varied Drone Dataset for Semantic Segmentation
Viaarxiv icon

[CLS] Token is All You Need for Zero-Shot Semantic Segmentation

Apr 13, 2023
Letian Wu, Wenyao Zhang, Tengping Jiang, Wankou Yang, Xin Jin, Wenjun Zeng

Figure 1 for [CLS] Token is All You Need for Zero-Shot Semantic Segmentation
Figure 2 for [CLS] Token is All You Need for Zero-Shot Semantic Segmentation
Figure 3 for [CLS] Token is All You Need for Zero-Shot Semantic Segmentation
Figure 4 for [CLS] Token is All You Need for Zero-Shot Semantic Segmentation
Viaarxiv icon

Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens

Mar 01, 2023
Sen Yang, Wen Heng, Gang Liu, Guozhong Luo, Wankou Yang, Gang Yu

Figure 1 for Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens
Figure 2 for Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens
Figure 3 for Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens
Figure 4 for Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens
Viaarxiv icon