Hongda Yang — accepted AI-conference papers

2025

Accident Anticipation via Temporal Occurrence Prediction

Tianhao Zhao, Yiyang Zou, Zihao Mao, Peilun Xiao, Yulin Huang, Hongda Yang +4

NeurIPS 2025poster

Accident anticipation aims to predict potential collisions in an online manner, enabling timely alerts to enhance road safety. Existing methods typically predict frame-level risk scores as indicators of hazard. However, these approaches rely on ambiguous binary supervision—labeling all frames in acc…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Improving Bird's Eye View Semantic Segmentation by Task Decomposition

Tianhao Zhao, Yongcan Chen, Yu Wu, Tianyang Liu, Bo Du, Peilun Xiao +5

CVPR 2024poster

Semantic segmentation in bird's eye view (BEV) plays a crucial role in autonomous driving. Previous methods usually follow an end-to-end pipeline directly predicting the BEV segmentation map from monocular RGB inputs. However the challenge arises when the RGB inputs and BEV targets from distinct per…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗