Peeking into the Future: Predicting Future Person Activities and Locations in Videos

CVPR 2019 Junwei LiangLu JiangJuan Carlos NieblesAlexander HauptmannLi Fei-Fei

Deciphering human behaviors to predict their future paths/trajectories and what they would do from videos is important in many applications. Motivated by this idea, this paper studies predicting a pedestrian's future path jointly with future activities... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Activity Prediction ActEV Next mAP 0.192 # 1
Trajectory Prediction ActEV Next ADE-8/12 17.99 # 1
FDE-8/12 37.24 # 2
Trajectory Forecasting ActEV Next ADE-8/12 17.99 # 1
Trajectory Prediction ETH/UCY Next ADE-8/12 0.46 # 3