Lulu Tang

Papers

Total Citations

H-Index

About

Lulu Tang’s research bridges the frontiers of 3D computer vision, deep learning, and intelligent robotics. Her most influential work, “Multi-View CNN Feature Aggregation with ELM Auto-Encoder for 3D Shape Recognition” (2018), has garnered 55 citations and stands as a key contribution to 3D object understanding. In this paper, Tang pioneered a novel hybrid architecture that fuses multi-view convolutional neural network features with an extreme learning machine auto-encoder, enabling more efficient and accurate 3D shape recognition. This approach significantly advanced the field by reducing computational complexity while maintaining high classification performance. Tang also made notable strides in robotics with her work on “Robust GA Based Global Path Planning for IoP Oriented Mobil Robot” (2018), where she developed a genetic algorithm-based path planning method tailored for Internet of Plants (IoP) applications. This research introduced a novel search area determination strategy for indoor environments, enhancing robustness and efficiency in autonomous navigation. Through these contributions, Tang has demonstrated a unique ability to integrate machine learning with real-world robotic systems, establishing herself as a promising researcher at the intersection of computer vision and intelligent control.