Scholar

Dong Huang

Google Scholar ID: VeXMKBoAAAAJ

Senior Project Scientist, Carnegie Mellon University

Machine LearningComputer vision

Citations & Impact

All-time

Citations

3,453

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

1 items

2026

Cited

Resume (English only)

Academic Achievements

1. Mono WiFi Scene and Hello 3D to appear at ICRA2024.
2. Hello 3D demo at the Automate 2024 trade show.
3. Mono WiFi Scene is the first technology that enables dense sensing of 3D environments using only a single WiFi device.
4. Dense Pose from Wi-Fi covered by The Economist, BBC News Digital Planet, New Scientist, and Synced.
5. Elaborative Rehearsal for Zero-shot Action Recognition accepted by ICCV 2021.
6. Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs accepted by CVPR 2021 (Oral).
7. Comprehensive Attention Self-Distillation (CASD) accepted by NeurIPS 2020.
8. Representation Self-Challenging (RSC) accepted by ECCV 2020 Oral (top 2%).
9. Multiple Anchor Learning (MAL) accepted by CVPR 2020.
10. Inverted Attention (IA) accepted by WACV 2020.
11. Person-in-WiFi accepted by ICCV 2019.

Research Experience

In the research team at RI CMU, focusing on providing real-time 3D reconstruction capabilities and lightweight Deep Neural Networks (DNNs) for moving platforms such as autonomous machines, drones, and smart camera modules. Developed deep learning approaches that take multiple sensor data (e.g., videos, depth, wearable sensor signals, and WiFi signals) to produce various perception results, such as location, poses, activities, and physical metrics.

Education

Background

Research Interests: Efficient AI perception solutions, Dense Supervision approaches. Specialization: 3D Perception on embedded platforms, Perception in multi-modality systems.

Miscellany