How Can I See My Future? FvTraj: Using First-person View for Pedestrian Trajectory Prediction

no code implementations • ECCV 2020 • Huikun Bi, Ruisi Zhang, Tianlu Mao, Zhigang Deng, Zhaoqi Wang

This work presents a novel First-person View based Trajectory predicting model (FvTraj) to estimate the future trajectories of pedestrians in a scene given their observed trajectories and the corresponding first-person view images.

Pedestrian Trajectory Prediction Trajectory Prediction

Global-to-local Expression-aware Embeddings for Facial Action Unit Detection

no code implementations • 27 Oct 2022 • Rudong An, Wei zhang, Hao Zeng, Wei Chen, Zhigang Deng, Yu Ding

Then, AU feature maps and their corresponding AU masks are multiplied to generate AU masked features focusing on local facial region.

Action Unit Detection Facial Action Unit Detection

Facial Action Units Detection Aided by Global-Local Expression Embedding

no code implementations • 25 Oct 2022 • Zhipeng Hu, Wei zhang, Lincheng Li, Yu Ding, Wei Chen, Zhigang Deng, Xin Yu

We find that AUs and facial expressions are highly associated, and existing facial expression datasets often contain a large number of identities.

3D Face Reconstruction