A5001303961- Advanced Neural Network Applications
- Multimodal Machine Learning Applications
- Domain Adaptation and Few-Shot Learning
- Adversarial Robustness in Machine Learning
- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- Image Processing Techniques and Applications
Beijing Academy of Artificial Intelligence
2022-2023
University of Chinese Academy of Sciences
2022-2023
Institute of Automation
2023
Chinese Academy of Sciences
2022-2023
Shandong Institute of Automation
2022
Object goal visual navigation is a challenging task that aims to guide robot find the target object based on its observation, and limited classes pre-defined in training stage. However, real households, there may exist numerous needs deal with, it hard for all of these be contained To address this challenge, we study zero-shot task, which at guiding robots targets belonging novel without any samples. end, also propose framework called semantic similarity network (SSNet). Our use detection...
The task of zero-shot object goal visual navigation (ZSON) aims to enable robots locate previously "unseen" objects by observations. This presents a significant challenge since the robot must transfer policy learned from "seen" through auxiliary semantic information without training samples, process known as learning. In order address this challenge, we propose novel approach termed Semantic Policy Network (SPNet). SPNet consists two modules that are deeply integrated with embeddings: Actor...
Active interaction with environments is one of the striking characteristics robotic active vision, which allows robots to move facilitate visual tasks. Recently, several embodied AI platforms have been proposed as synthetic study without needing interact in real world. However, by using data, model trained on these will suffer performance degradation when applied reality. In this letter, a 3D dataset for learning. The consists point cloud data densely collected 7 real-world indoor scenes....
Object goal visual navigation is a challenging task that aims to guide robot find the target object based on its observation, and limited classes pre-defined in training stage. However, real households, there may exist numerous needs deal with, it hard for all of these be contained To address this challenge, we study zero-shot task, which at guiding robots targets belonging novel without any samples. end, also propose framework called semantic similarity network (SSNet). Our use detection...