106 citations
- Meta (United States)US2 papers
- Shenzhen Institutes of Advanced TechnologyCN2 papers
- University of Maryland, College ParkUS2 papers
- Aalto UniversityFI1 paper
- China University of GeosciencesCN1 paper
- Chinese Academy of SciencesCN1 paper
- Chinese University of Hong Kong, ShenzhenCN1 paper
- Commonwealth Scientific and Industrial Research OrganisationAU1 paper
- Data61AU1 paper
- GE Global Research (United States)US1 paper
- General Electric (United States)US1 paper
- Huazhong University of Science and TechnologyCN1 paper
5 papers · 2 filters
Generate, Segment and Refine: Towards Generic Manipulation Segmentation
Peng Zhou, Bor-Chun Chen, Xintong Han +4
Detecting manipulated images has become a significant emerging challenge. The advent of image sharing platforms and the easy availability of advanced photo editing software have re…
Deep Metric Learning with Hierarchical Triplet Loss
Weifeng Ge, Weilin Huang, Dengke Dong +1
We present a novel hierarchical triplet loss (HTL) capable of automatically collecting informative training samples (triplets) via a defined hierarchical tree that encodes global c…
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
Sheng Guo, Weilin Huang, Haozhi Zhang +4
We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using te…
DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
Zuxuan Wu, Xintong Han, Yen-Liang Lin +4
Harvesting dense pixel-level annotations to train deep neural networks for semantic segmentation is extremely expensive and unwieldy at scale. While learning from synthetic data wh…
An end-to-end TextSpotter with Explicit Alignment and Attention
Tong He, Zhi Tian, Weilin Huang +3
Text detection and recognition in natural images have long been considered as two separate tasks that are processed sequentially. Training of two tasks in a unified framework is no…