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
Posted Content
Detecting Invisible People
TL;DR: This work re-purpose tracking benchmarks and proposes new metrics for the task of detecting invisible objects, focusing on the illustrative case of people, and is the first work to demonstrate the effectiveness of monocular depth estimation for thetask of tracking and detecting occluded objects.
Posted Content
Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision
TL;DR: In this paper, a hierarchical trajectory forecasting network was proposed to disentangle the overall pedestrian motion into easier to learn subparts by utilizing a pose completion and a decomposition module.
Journal ArticleDOI
Applying deep neural networks and inertial measurement unit in recognizing irregular walking differences in the real world
TL;DR: In this paper, three variations of deep learning models were trained to solve this walking surface recognition problem: convolution neural network (CNN), long short term memory (LSTM) network and 3) LSTM structure with an extra global pooling layer (Global-LstM), which learns the coordination between different data streams (e.g. different channels of the same sensor as well as different sensors).
Journal ArticleDOI
Context-Aware Human Trajectories Prediction via Latent Variational Model
TL;DR: This article proposes a model to address pedestrian trajectory prediction using a latent variable model aware of the human-contextual interaction and relies on contextual information that influences the trajectory of pedestrians to encode human- contextual interaction.
Proceedings ArticleDOI
Socially-Aware Graph Convolutional Network for Human Trajectory Prediction
TL;DR: A socially-aware graph convolutional network (SAGCN) which effectively learns the comprehensive spatial-temporal representation and outperforms state-of-art methods in terms of prediction accuracy is proposed.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Posted Content
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.
Proceedings Article
Auto-Encoding Variational Bayes
Diederik P. Kingma,Max Welling +1 more
TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Posted Content
Image-to-Image Translation with Conditional Adversarial Networks
TL;DR: Conditional Adversarial Network (CA) as discussed by the authors is a general-purpose solution to image-to-image translation problems, which can be used to synthesize photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.