1.4k citations
- The University of TokyoJP46 papers
- Kyoto UniversityJP23 papers
- University of TsukubaJP16 papers
- Tokyo Institute of TechnologyJP12 papers
- National Institute of Advanced Industrial Science and TechnologyJP8 papers
- Centre National de la Recherche ScientifiqueFR7 papers
- National Institute for Materials ScienceJP7 papers
- The University of OsakaJP7 papers
- Nagoya UniversityJP6 papers
- Keio UniversityJP5 papers
- Tohoku UniversityJP5 papers
- Chiba UniversityJP4 papers
6 papers · 2 filters
Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
Kourosh Meshgi, Maryam Sadat Mirzaei, Shigeyuki Oba
Different layers in CNNs provide not only different levels of abstraction for describing the objects in the input but also encode various implicit information about them. The activ…
Learning from Multimodal and Multitemporal Earth Observation Data for Building Damage Mapping
Bruno Adriano, Naoto Yokoya, Junshi Xia +4
Earth observation technologies, such as optical imaging and synthetic aperture radar (SAR), provide excellent means to monitor ever-growing urban environments continuously. Notably…
More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification
Danfeng Hong, Lianru Gao, Naoto Yokoya +4
Classification and identification of the materials lying over or beneath the Earth's surface have long been a fundamental but challenging research topic in geoscience and remote se…
Illumination invariant hyperspectral image unmixing based on a digital surface model
Tatsumi Uezato, Naoto Yokoya, Wei He
Although many spectral unmixing models have been developed to address spectral variability caused by variable incident illuminations, the mechanism of the spectral variability is s…
X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data
Danfeng Hong, Naoto Yokoya, Gui-Song Xia +2
This paper addresses the problem of semi-supervised transfer learning with limited cross-modality data in remote sensing. A large amount of multi-modal earth observation images, su…
AnimGAN: A Spatiotemporally-Conditioned Generative Adversarial Network for Character Animation
Maryam Sadat Mirzaei, Kourosh Meshgi, Etienne Frigo +1
Producing realistic character animations is one of the essential tasks in human-AI interactions. Considered as a sequence of poses of a humanoid, the task can be considered as a se…