X
Xingang Wang
Researcher at Chinese Academy of Sciences
Publications - 50
Citations - 1097
Xingang Wang is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Monocular vision & Feature (computer vision). The author has an hindex of 12, co-authored 47 publications receiving 692 citations.
Papers
More filters
Proceedings ArticleDOI
Attention-Guided Unified Network for Panoptic Segmentation
TL;DR: In this article, an attention-guided unified network (AUNet) is proposed for panoptic segmentation, in which foreground objects provide complementary cues to assist background understanding, and two sources of attentions are added to the foreground objects to provide object-level and pixel-level attentions, respectively.
Proceedings ArticleDOI
Learning Dynamic Routing for Semantic Segmentation
TL;DR: A conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing, which generates data-dependent routes, adapting to the scale distribution of each image, and compares with several static architectures, which can be modeled as special cases in the routing space.
Posted Content
Attention-guided Unified Network for Panoptic Segmentation
TL;DR: The underlying relationship between FG objects and BG contents is revealed, in particular, FG objects provide complementary cues to assist BG understanding, and the Attention-guided Unified Network (AUNet) is named, a unified framework with two branches for FG and BG segmentation simultaneously.
Journal ArticleDOI
Face Detection With Different Scales Based on Faster R-CNN
TL;DR: A different scales face detector (DSFD) based on Faster R-CNN is proposed that achieves promising performance on popular benchmarks including FDDB, AFW, PASCAL faces, and WIDER FACE.
Journal ArticleDOI
Robust Visual Detection–Learning–Tracking Framework for Autonomous Aerial Refueling of UAVs
TL;DR: The experimental results on several challenging video sequences validate the effectiveness and robustness of the proposed robust visual detection-learning-tracking framework for autonomous aerial refueling of unmanned aerial vehicles.