Where Will They Go? Predicting Fine-Grained Adversarial Multi-Agent Motion Using Conditional Variational Autoencoders
COMPUTER VISION - ECCV 2018, PT XI(2018)
摘要
Simultaneously and accurately forecasting the behavior of many interacting agents is imperative for computer vision applications to be widely deployed (e.g., autonomous vehicles, security, surveillance, sports). In this paper, we present a technique using conditional variational autoencoder which learns a model that "personalizes" prediction to individual agent behavior within a group representation. Given the volume of data available and its adversarial nature, we focus on the sport of basketball and show that our approach efficiently predicts context-specific agent motions. We find that our model generates results that are three times as accurate as previous state of the art approaches (5.74 ft vs. 17.95 ft).
更多查看译文
关键词
Forecasting, Motion prediction, Multi-agent tracking, Context aware prediction, Conditional variational autoencoders
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要