activity
20172021
most citedUnsupervised Domain Adaptation for Multispectral Pedestrian Detection

4 citations · 11 across the 7 of their papers we have counts for

collaborators

10 papers

cs.CV20211 cited

Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery

Ye Lyu, George Vosselman, Gui-Song Xia +1

Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation. Most of the semantic segmentation research focused on…

cs.CV20201 cited

LGENet: Local and Global Encoder Network for Semantic Segmentation of Airborne Laser Scanning Point Clouds

Yaping Lin, George Vosselman, Yanpeng Cao +1

Interpretation of Airborne Laser Scanning (ALS) point clouds is a critical procedure for producing various geo-information products like 3D city models, digital terrain models and…

cs.CV20201 cited

Plug & Play Convolutional Regression Tracker for Video Object Detection

Ye Lyu, Michael Ying Yang, George Vosselman +1

Video object detection targets to simultaneously localize the bounding boxes of the objects and identify their classes in a given video. One challenge for video object detection is…

cs.CV20191 cited

LIP: Learning Instance Propagation for Video Object Segmentation

Ye Lyu, George Vosselman, Gui-Song Xia +1

In recent years, the task of segmenting foreground objects from background in a video, i.e. video object segmentation (VOS), has received considerable attention. In this paper, we…

cs.CV20194 cited

Unsupervised Domain Adaptation for Multispectral Pedestrian Detection

Dayan Guan, Xing Luo, Yanpeng Cao +4

Multimodal information (e.g., visible and thermal) can generate robust pedestrian detections to facilitate around-the-clock computer vision applications, such as autonomous driving…

cs.CV20193 cited

Robust object extraction from remote sensing data

Sophie Crommelinck, Mila Koeva, Michael Ying Yang +1

The extraction of object outlines has been a research topic during the last decades. In spite of advances in photogrammetry, remote sensing and computer vision, this task remains c…