A5100364078- Advanced Image and Video Retrieval Techniques
- Face and Expression Recognition
- Infrared Target Detection Methodologies
- Robot Manipulation and Learning
- Adversarial Robustness in Machine Learning
- Robotics and Sensor-Based Localization
- Guidance and Control Systems
- Multimodal Machine Learning Applications
- Anomaly Detection Techniques and Applications
Aviation Industry Corporation of China (China)
2021
Australian National University
2019
Tulane University
2005
Since a target's operational intention in air combat is realized by series of tactical maneuvers, its state presents the characteristics temporal and dynamic changes. Depending only on single moment to take inference, traditional recognition method neither scientific nor effective enough. Based gated recurrent unit (GRU), bidirectional propagation mechanism attention are introduced proposed aerial target method. The constructs an characteristic set through hierarchical approach, encodes into...
Many classifiers have been proposed for ATR applications. Given a set of training data, classifier is built from the labeled and then applied to predict label new test point. If there enough points are drawn same distribution (i.i.d.) as many perform quite well. However, in reality, will never be data or with limited computational resources we can only use part data. Likewise, might different that whereby not representative In this paper, empirically compare several classifiers, namely...
Understanding physical relations between objects, especially their support relations, is crucial for robotic manipulation. There has been work on reasoning about and structural stability of simple configurations in RGB-D images. In this paper, we propose a method extracting more detailed knowledge from set images taken the same scene but different views using qualitative intuitive models. Rather than providing contact relation graph approximating over convex shapes, our able to provide...