Open AccessPosted Content
Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks.
TLDR
In this paper, a recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people, and predicts socially plausible future by training adversarially against a recurrent discriminator, and encourage diverse predictions with a novel variety loss.Abstract:
Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a history of human motion paths, there are many socially plausible ways that people could move in the future. We tackle this problem by combining tools from sequence prediction and generative adversarial networks: a recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people. We predict socially plausible futures by training adversarially against a recurrent discriminator, and encourage diverse predictions with a novel variety loss. Through experiments on several datasets we demonstrate that our approach outperforms prior work in terms of accuracy, variety, collision avoidance, and computational complexity.read more
Citations
More filters
Proceedings ArticleDOI
Argoverse: 3D Tracking and Forecasting With Rich Maps
Ming-Fang Chang,Deva Ramanan,James Hays,John Lambert,Patsorn Sangkloy,Jasvinder A. Singh,Slawomir Bak,Andrew Hartnett,De Wang,Peter W. Carr,Simon Lucey +10 more
TL;DR: Argoverse includes sensor data collected by a fleet of autonomous vehicles in Pittsburgh and Miami as well as 3D tracking annotations, 300k extracted interesting vehicle trajectories, and rich semantic maps, which contain rich geometric and semantic metadata which are not currently available in any public dataset.
Proceedings ArticleDOI
From Recognition to Cognition: Visual Commonsense Reasoning
TL;DR: To move towards cognition-level understanding, a new reasoning engine is presented, Recognition to Cognition Networks (R2C), that models the necessary layered inferences for grounding, contextualization, and reasoning.
Journal ArticleDOI
Human motion trajectory prediction: a survey:
Andrey Rudenko,Andrey Rudenko,Luigi Palmieri,Michael Herman,Kris M. Kitani,Dariu M. Gavrila,Kai O. Arras +6 more
TL;DR: In this article, the ability of intelligent autonomous systems to perceive, understand, and anticipate human behavior becomes increasingly important in a growing number of intelligent systems in human environments, and the ability to do so is discussed.
Proceedings ArticleDOI
STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction
TL;DR: This work proposes a Spatial-Temporal Graph Attention network (STGAT), based on a sequence-to-sequence architecture to predict future trajectories of pedestrians, which achieves superior performance on two publicly available crowd datasets and produces more "socially" plausible trajectories for pedestrians.
Posted Content
Human Action Recognition and Prediction: A Survey.
TL;DR: The complete state-of-the-art techniques in the action recognition and prediction are surveyed, including existing models, popular algorithms, technical difficulties, popular action databases, evaluation protocols, and promising future directions are provided.
References
More filters
Proceedings ArticleDOI
Abnormal crowd behavior detection using social force model
TL;DR: A novel method to detect and localize abnormal behaviors in crowd videos using Social Force model and it is shown that the social force approach outperforms similar approaches based on pure optical flow.
Posted Content
Conditional Image Synthesis With Auxiliary Classifier GANs
TL;DR: In this article, a variant of GANs employing label conditioning was proposed to generate high resolution images. But the results showed that the high-resolution images were more than twice as discriminable as artificially resized 32x32 images.
Proceedings Article
DRAW: A Recurrent Neural Network For Image Generation
TL;DR: Deep Recurrent Attentive Writer (DRAW) as discussed by the authors combines a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images.
Book ChapterDOI
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
TL;DR: This paper introduces new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell, and proposes a more powerful tree-structure based traversal method.
Posted Content
DRAW: A Recurrent Neural Network For Image Generation
TL;DR: The Deep Recurrent Attentive Writer neural network architecture for image generation substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates images that cannot be distinguished from real data with the naked eye.