Where Will They Go? Predicting Fine-Grained Adversarial Multi-agent Motion Using Conditional Variational Autoencoders
| Autor: | Panna Felsen, Patrick Lucey, Sujoy Ganguly |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
0209 industrial biotechnology
Computer science business.industry Volume (computing) 020207 software engineering 02 engineering and technology Autoencoder Motion (physics) Adversarial system 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering State (computer science) Artificial intelligence Focus (optics) business |
| Zdroj: | Computer Vision – ECCV 2018 ISBN: 9783030012519 ECCV (11) |
| DOI: | 10.1007/978-3-030-01252-6_45 |
| Popis: | 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). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|