12 citations · 13 across the 18 of their papers we have counts for
7 papers · 1 filter
VehDyn: A Driving World Model Benchmark for Vehicle Dynamics
Tianyi Wang, Wangsheng Du, Jiazhou Chen +12
Video world models are emerging as data engines, action planners, and generative simulators for autonomous driving, but existing benchmarks primarily assess visual fidelity and coa…
TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation
Xiangyu Li, Tianyi Wang, Zhihao Dou +2
Existing roadside traffic datasets support perception, forecasting, and visual question answering, but they do not evaluate counterfactual video generation, in which a selected act…
EgoTraj: Real-World Egocentric Human Trajectory Dataset for Multimodal Prediction
Ahmad Yehia, Abduallah Mohamed, Tianyi Wang +4
Accurately forecasting human trajectories from an egocentric perspective plays a central role in applications such as humanoid robotics, wearable sensing systems, and assistive nav…
When to Lock Attention: Training-Free KV Control in Video Diffusion
Tianyi Zeng, Jincheng Gao, Tianyi Wang +8
Maintaining background consistency while enhancing foreground quality remains a core challenge in video editing. Injecting full-image information often leads to background artifact…
UAV-Based Intelligent Traffic Surveillance System: Real-Time Vehicle Detection, Classification, Tracking, and Behavioral Analysis
Ali Khanpour, Tianyi Wang, Afra Vahidi-Shams +4
Traffic congestion and violations pose significant challenges for urban mobility and road safety. Traditional traffic monitoring systems, such as fixed cameras and sensor-based met…
KEPT: Knowledge-Enhanced Prediction of Trajectories from Consecutive Driving Frames with Vision-Language Models
Yujin Wang, Tianyi Wang, Quanfeng Liu +7
Accurate short-horizon trajectory prediction is crucial for safe and reliable autonomous driving. However, existing vision-language models (VLMs) often fail to accurately understan…
HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data
Abduallah Mohamed, Fernando Lejarza, Stephanie Cahail +2
The problem of human activity recognition from mobile sensor data applies to multiple domains, such as health monitoring, personal fitness, daily life logging, and senior care. A c…