Author name cluster

Sejong Yoon

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

IJCAI Conference 2022 Conference Paper

Harnessing Fourier Isovists and Geodesic Interaction for Long-Term Crowd Flow Prediction

Samuel S. Sohn
Seonghyeon Moon
Honglu Zhou
Mihee Lee
Sejong Yoon
Vladimir Pavlovic
Mubbasir Kapadia

With the rise in popularity of short-term Human Trajectory Prediction (HTP), Long-Term Crowd Flow Prediction (LTCFP) has been proposed to forecast crowd movement in large and complex environments. However, the input representations, models, and datasets for LTCFP are currently limited. To this end, we propose Fourier Isovists, a novel input representation based on egocentric visibility, which consistently improves all existing models. We also propose GeoInteractNet (GINet), which couples the layers between a multi-scale attention network (M-SCAN) and a convolutional encoder-decoder network (CED). M-SCAN approximates a super-resolution map of where humans are likely to interact on the way to their goals and produces multi-scale attention maps. The CED then uses these maps in either its encoder's inputs or its decoder's attention gates, which allows GINet to produce super-resolution predictions with substantially higher accuracy than existing models even with Fourier Isovists. In order to evaluate the scalability of models to large and complex environments, which the only existing LTCFP dataset is unsuitable for, a new synthetic crowd dataset with both real and synthetic environments has been generated. In its nascent state, LTCFP has much to gain from our key contributions. The Supplementary Materials, dataset, and code are available at sssohn. github. io/GeoInteractNet.

PDF Details DOI

AAAI Conference 2018 Conference Paper

The Role of Data-Driven Priors in Multi-Agent Crowd Trajectory Estimation

Gang Qiao
Sejong Yoon
Mubbasir Kapadia
Vladimir Pavlovic

Trajectory interpolation, the process of ﬁlling-in the gaps and removing noise from observed agent trajectories, is an essential task for the motion inference in a multi-agent setting. A desired trajectory interpolation method should be robust to noise, changes in environments or agent densities, while also being able to yield realistic group movement behaviors. Such realistic behaviors are, however, challenging to model as they require avoidance of agent-agent or agent-environment collisions and, at the same time, demand computational efﬁciency. In this paper, we propose a novel framework composed of data-driven priors (local, global or combined) and an efﬁcient optimization strategy for multi-agent trajectory interpolation. The data-driven priors implicitly encode the dependencies of movements of multiple agents and the collision-avoiding desiderata, enabling elimination of costly pairwise collision constraints, resulting in reduced computational complexity and often improved estimation. Various combinations of priors and optimization algorithms are evaluated in comprehensive simulated experiments. Our experimental results reveal important insights, including the signiﬁcance of the global ﬂow prior and the lesser-than-expected inﬂuence of datadriven collision priors.

PDF Details

AAAI Conference 2016 Conference Paper

Decentralized Approximate Bayesian Inference for Distributed Sensor Network

Behnam Gholami
Sejong Yoon
Vladimir Pavlovic

Bayesian models provide a framework for probabilistic modelling of complex datasets. Many such models are computationally demanding, especially in the presence of large datasets. In sensor network applications, statistical (Bayesian) parameter estimation usually relies on decentralized algorithms, in which both data and computation are distributed across the nodes of the network. In this paper we propose a framework for decentralized Bayesian learning using Bregman Alternating Direction Method of Multipliers (B- ADMM). We demonstrate the utility of our framework, with Mean Field Variational Bayes (MFVB) as the primitive for distributed afﬁne structure from motion (SfM).

PDF Details

AAAI Conference 2016 Conference Paper

Fast ADMM Algorithm for Distributed Optimization with Adaptive Penalty

Changkyu Song
Sejong Yoon
Vladimir Pavlovic

We propose new methods to speed up convergence of the Alternating Direction Method of Multipliers (ADMM), a common optimization tool in the context of large scale and distributed learning. The proposed method accelerates the speed of convergence by automatically deciding the constraint penalty needed for parameter consensus in each iteration. In addition, we also propose an extension of the method that adaptively determines the maximum number of iterations to update the penalty. We show that this approach effectively leads to an adaptive, dynamic network topology underlying the distributed optimization. The utility of the new penalty update schemes is demonstrated on both synthetic and real data, including an instance of the probabilistic matrix factorization task known as the structure-from-motion problem.

PDF Details

NeurIPS Conference 2012 Conference Paper

Distributed Probabilistic Learning for Camera Networks with Missing Data

Sejong Yoon
Vladimir Pavlovic

Probabilistic approaches to computer vision typically assume a centralized setting, with the algorithm granted access to all observed data points. However, many problems in wide-area surveillance can benefit from distributed modeling, either because of physical or computational constraints. Most distributed models to date use algebraic approaches (such as distributed SVD) and as a result cannot explicitly deal with missing data. In this work we present an approach to estimation and learning of generative probabilistic models in a distributed context where certain sensor data can be missing. In particular, we show how traditional centralized models, such as probabilistic PCA and missing-data PPCA, can be learned when the data is distributed across a network of sensors. We demonstrate the utility of this approach on the problem of distributed affine structure from motion. Our experiments suggest that the accuracy of the learned probabilistic structure and motion models rivals that of traditional centralized factorization methods while being able to handle challenging situations such as missing or noisy observations.

PDF Details