13 papers
Feed-forward Motion In-betweening for Any 4D
Hiroki Nishizawa, Hubert P. H. Shum, Yoshihiro Fukuhara +2
4D dynamics (3D geometry evolving over time) is a fundamental representation of the physical world and plays a crucial role in world modeling (e.g., animation and games). Owing to…
Where Will They Go? Modelling Multimodal Pedestrian Manoeuvres from Ego-centric Videos
Yuxuan Xie, Nicolas Pugeault, Chongfeng Wei +2
Pedestrian trajectory prediction from an on-board ego-centric camera is challenging since it depends on complex interactions with vehicles and scene context, as well as the intenti…
Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognition
Ziyi Chang, Kanglei Zhou, Xiaohui Liang +1
Adversarial attacks on skeletal human action recognition have received significant attention. However, existing methods typically introduce noise-like perturbations that degrade mo…
VRUD: A Drone Dataset for Complex Vehicle-VRU Interactions within Mixed Traffic
Ziyu Wang, Hongrui Kou, Cheng Wang +4
The Operational Design Domain (ODD) of urbanoriented Level 4 (L4) autonomous driving, especially for autonomous robotaxis, confronts formidable challenges in complex urban mixed tr…
Benchmarking Autonomous Vehicles: A Driver Foundation Model Framework
Yuxin Zhang, Cheng Wang, Hubert P. H. Shum
Autonomous vehicles (AVs) are poised to revolutionize global transportation systems. However, its widespread acceptance and market penetration remain significantly below expectatio…
KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation
Wenke E, Yixin Sun, Jiaxu Liu +3
We present the first cross-modality distillation framework specifically tailored for single-panoramic-camera Bird's-Eye-View (BEV) segmentation. Our approach leverages a novel LiDA…