288 citations
- University of TsukubaJP49 papers
- Fermi National Accelerator LaboratoryUS44 papers
- University of New MexicoUS44 papers
- Tufts UniversityUS43 papers
- University of LiverpoolGB42 papers
- Waseda UniversityJP42 papers
- Massachusetts Institute of TechnologyUS41 papers
- Okayama UniversityJP41 papers
- University of California, DavisUS41 papers
- University of OxfordGB41 papers
- Yale UniversityUS41 papers
- Academia SinicaTW40 papers
14 papers · 1 filter
Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition
Tatsuhito Hasegawa, Kazuma Kondo
Sensor-based human activity recognition (HAR) is a paramount technology in the Internet of Things services. HAR using representation learning, which automatically learns a feature…
Sketch-based Normal Map Generation with Geometric Sampling
Yi He, Haoran Xie, Chao Zhang +2
Normal map is an important and efficient way to represent complex 3D models. A designer may benefit from the auto-generation of high quality and accurate normal maps from freehand…
Domain-invariant NBV Planner for Active Cross-domain Self-localization
Kanji Tanaka
Pole-like landmark has received increasing attention as a domain-invariant visual cue for visual robot self-localization across domains (e.g., seasons, times of day, weathers). How…
Octave Mix: Data augmentation using frequency decomposition for activity recognition
Tatsuhito Hasegawa
In the research field of activity recognition, although it is difficult to collect a large amount of measured sensor data, there has not been much discussion about data augmentatio…
Deep Patch-based Human Segmentation
Dongbo Zhang, Zheng Fang, Xuequan Lu +4
3D human segmentation has seen noticeable progress in re-cent years. It, however, still remains a challenge to date. In this paper, weintroduce a deep patch-based method for 3D hum…
G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data
Chao Zhang, Xuequan Lu, Katsuya Hotta +1
In this paper we attempt to address the problem of geometric multi-model fitting with resorting to a few weakly annotated (WA) data points, which has been sparsely studied so far.…