10.9k citations
- University of Science and Technology of ChinaCN2.2k papers
- Chinese Academy of SciencesCN1.8k papers
- Tsinghua UniversityCN1.8k papers
- Nanjing UniversityCN1.7k papers
- Johannes Gutenberg University MainzDE1.7k papers
- Institute of High Energy PhysicsCN1.6k papers
- Indiana University BloomingtonUS1.6k papers
- Justus-Liebig-Universität GießenDE1.6k papers
- Uppsala UniversitySE1.6k papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT1.6k papers
- Joint Institute for Nuclear ResearchRU1.6k papers
- Shanghai Jiao Tong UniversityCN1.5k papers
5 papers · 2 filters
SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
Long Chen, Hanwang Zhang, Jun Xiao +4
Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spati…
Improved phase-unwrapping method using geometric constraints
Guangliang Du, Minmin Wang, Canlin Zhou +4
Conventional dual-frequency fringe projection algorithm often suffers from phase unwrapping failure when the frequency ratio between the high frequency and the low one is too large…
Enhanced high dynamic range 3D shape measurement based on generalized phase-shifting algorithm
Minmin Wang, Guangliang Du, Canlin Zhou +5
It is a challenge for Phase Measurement Profilometry (PMP) to measure objects with a large range of reflectivity variation across the surface. Saturated or dark pixels in the defor…
FPNN: Field Probing Neural Networks for 3D Data
Yangyan Li, Soeren Pirk, Hao Su +2
Building discriminative representations for 3D data has been an important task in computer graphics and computer vision research. Convolutional Neural Networks (CNNs) have shown to…
Synthesizing Training Images for Boosting Human 3D Pose Estimation
Wenzheng Chen, Huan Wang, Yangyan Li +6
Human 3D pose estimation from a single image is a challenging task with numerous applications. Convolutional Neural Networks (CNNs) have recently achieved superior performance on t…