Jen-Hao Cheng — accepted AI-conference papers

2025

MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection

Hou-I Liu, Christine Wu, Jen-Hao Cheng, Wenhao Chai, Shian-Yun Wang, Gaowen Liu +5

CVPR 2025poster

Monocular 3D object detection (Mono3D) holds noteworthy promise for autonomous driving applications owing to the cost-effectiveness and rich visual context of monocular camera sensors. However, depth ambiguity poses a significant challenge, as it requires extracting precise 3D scene geometry from a…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2024

RT-Pose: A 4D Radar-Tensor based 3D Human Pose Estimation and Localization Benchmark

Yuan-Hao Ho, Jen-Hao Cheng, Sheng Yao Kuan, Zhongyu Jiang, Wenhao Chai, Hsiang-Wei Huang +2

ECCV 2024poster

"Traditional methods for human localization and pose estimation (HPE), which mainly rely on RGB images as an input modality, confront substantial limitations in real-world applications due to privacy concerns. In contrast, radar-based HPE methods emerge as a promising alternative, characterized by d…

Cited by 5 Source ↗PDF ↗Scholar ↗