Wentao Wang

Wentao Wang

Auto-generated profile, based on publicly available information

Wentao Wang

School of Electronic Information and Electrical Engineering, and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 August 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XYXue Yang
Xue Yang
GZGefan Zhang
Gefan Zhang
XYXiaojiang Yang
Xiaojiang Yang
YZYue Zhou
Yue Zhou
WWWentao Wang
Wentao Wang
Junchi YanJunchi Yan
Junchi Yan
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection, especially for high-precision detection with high IoU (e.g. 0.75). Instead, we propose to model the rotated objects as Gaussian distributions. A direct advantage is that our new regression loss regarding the distance between two Gaussians e.g. Kullback-Leibler Divergence (KLD), can well align the actual detection performance metric, which is not well addressed in existing methods. Moreover, the two bottlenecks i.e. boundary discontinuity and square-like problem also disappear. We also propose an efficient Gaussian metric-based label assignment strategy to further boost the performance. Interestingly, by analyzing the BBox parameters' gradients under our Gaussian-based KLD loss, we show that these parameters are dynamically updated with interpretable physical meaning, which help explain the effectiveness of our approach, especially for high-precision detection. We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation, and experimental results on twelve public datasets (2-D/3-D, aerial/text/face images) with various base detectors show its superiority.

19 December 2022 in Pattern Recognition
Verified
Journal Article
Closed access
WWWentao Wang
Wentao Wang
LHLu He
Lu He
LNLi Niu
Li Niu
JZJianfu Zhang
Jianfu Zhang
YLYue Liu
Yue Liu
LZLiqing Zhang
Liqing Zhang

11 September 2020 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
JZJianfu Zhang
Jianfu Zhang
PYPeiming Yang
Peiming Yang
WWWentao Wang
Wentao Wang
YHYan Hong
Yan Hong
LZLiqing Zhang
Liqing Zhang
Image editing is one of the most popular directions in computer vision. Recently, many methods have benefited from the advances in deep learning, showing promising performance in the image editing task by inpainting the editing areas. These methods take advantage of edge information as user guidance to generate the desired content. However, they are suffering from generating color discrepancy and inconsistent boundaries. In this letter, we propose a deep image editing method based on a self-attention network which copies information for each of the small patches from distant spatial locations. The proposed method smooths the image, computes segmentation maps, and utilizes the segmentation information for guiding the self-attention layers to explicitly leverage image features from surrounding areas with similar appearances. Experimental results show that the proposed method achieves better performance, is flexible for different purposes, and fast for implementation.