Search Results for author: Mario Sznaier

Found 23 papers, 1 papers with code

On the Hardness of Learning to Stabilize Linear Systems

no code implementations18 Nov 2023 Xiong Zeng, Zexiang Liu, Zhe Du, Necmiye Ozay, Mario Sznaier

Inspired by the work of Tsiamis et al. \cite{tsiamis2022learning}, in this paper we study the statistical hardness of learning to stabilize linear time-invariant systems.

Inferring Relational Potentials in Interacting Systems

no code implementations23 Oct 2023 Armand Comas-Massagué, Yilun Du, Christian Fernandez, Sandesh Ghimire, Mario Sznaier, Joshua B. Tenenbaum, Octavia Camps

In this work, we propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions that enables greater flexibility in trajectory modeling: it discovers a set of relational potentials, represented as energy functions, which when minimized reconstruct the original trajectory.

Trajectory Forecasting Trajectory Modeling

Cross-view Action Recognition via Contrastive View-invariant Representation

no code implementations2 May 2023 Yuexi Zhang, Dan Luo, Balaji Sundareshan, Octavia Camps, Mario Sznaier

Cross view action recognition (CVAR) seeks to recognize a human action when observed from a previously unseen viewpoint.

Action Recognition

Peak Estimation and Recovery with Occupation Measures

no code implementations14 Sep 2020 Jared Miller, Didier Henrion, Mario Sznaier

Peak Estimation aims to find the maximum value of a state function achieved by a dynamical system.

Systems and Control Systems and Control Algebraic Geometry Dynamical Systems 37M99

Key Frame Proposal Network for Efficient Pose Estimation in Videos

1 code implementation ECCV 2020 Yuexi Zhang, Yin Wang, Octavia Camps, Mario Sznaier

Human pose estimation in video relies on local information by either estimating each frame independently or tracking poses across frames.

Pose Estimation

Solving Interpretable Kernel Dimensionality Reduction

no code implementations NeurIPS 2019 Chieh Wu, Jared Miller, Yale Chang, Mario Sznaier, Jennifer Dy

While KDR methods can be easily solved by keeping the most dominant eigenvectors of the kernel matrix, its features are no longer easy to interpret.

Clustering Dimensionality Reduction

Iterative Spectral Method for Alternative Clustering

no code implementations8 Sep 2019 Chieh Wu, Stratis Ioannidis, Mario Sznaier, Xiangyu Li, David Kaeli, Jennifer G. Dy

Given a dataset and an existing clustering as input, alternative clustering aims to find an alternative partition.

Clustering

Solving Interpretable Kernel Dimension Reduction

no code implementations6 Sep 2019 Chieh Wu, Jared Miller, Yale Chang, Mario Sznaier, Jennifer Dy

While KDR methods can be easily solved by keeping the most dominant eigenvectors of the kernel matrix, its features are no longer easy to interpret.

Clustering Dimensionality Reduction

Spectral Non-Convex Optimization for Dimension Reduction with Hilbert-Schmidt Independence Criterion

no code implementations6 Sep 2019 Chieh Wu, Jared Miller, Yale Chang, Mario Sznaier, Jennifer Dy

The Hilbert Schmidt Independence Criterion (HSIC) is a kernel dependence measure that has applications in various aspects of machine learning.

Clustering Dimensionality Reduction

DYAN: A Dynamical Atoms-Based Network for Video Prediction

no code implementations ECCV 2018 Wenqian Liu, Abhishek Sharma, Octavia Camps, Mario Sznaier

The ability to anticipate the future is essential when making real time critical decisions, provides valuable information to understand dynamic natural scenes, and can help unsupervised video representation learning.

Generative Adversarial Network Representation Learning +1

MoNet: Moments Embedding Network

no code implementations CVPR 2018 Mengran Gou, Fei Xiong, Octavia Camps, Mario Sznaier

In addition, we propose a novel sub-matrix square-root layer, which can be used to normalize the output of the convolution layer directly and mitigate the dimensionality problem with off-the-shelf compact pooling methods.

Multi-camera Multi-Object Tracking

no code implementations20 Sep 2017 Wenqian Liu, Octavia Camps, Mario Sznaier

For multi-camera system tracking problem, efficient data association across cameras, and at the same time, across frames becomes more important than single-camera system tracking.

Multi-Object Tracking Object +1

Subspace Clustering With Priors via Sparse Quadratically Constrained Quadratic Programming

no code implementations CVPR 2016 Yongfang Cheng, Yin Wang, Mario Sznaier, Octavia Camps

This paper considers the problem of recovering a subspace arrangement from noisy samples, potentially corrupted with outliers.

Clustering

Solving Temporal Puzzles

no code implementations CVPR 2016 Caglayan Dicle, Burak Yilmaz, Octavia Camps, Mario Sznaier

Many physical phenomena, within short time windows, can be explained by low order differential relations.

Time Series Time Series Analysis

Person Re-identification in Appearance Impaired Scenarios

no code implementations1 Apr 2016 Mengran Gou, Xikang Zhang, Angels Rates-Borras, Sadjad Asghari-Esfeden, Mario Sznaier, Octavia Camps

Our experiments on the original and the appearance impaired datasets demonstrate the benefits of incorporating dynamics-based information with appearance-based information to re-identification algorithms.

Person Re-Identification

Self Scaled Regularized Robust Regression

no code implementations CVPR 2015 Yin Wang, Caglayan Dicle, Mario Sznaier, Octavia Camps

Linear Robust Regression (LRR) seeks to find the parameters of a linear mapping from noisy data corrupted from outliers, such that the number of inliers (i. e. pairs of points where the fitting error of the model is less than a given bound) is maximized.

regression

A Convex Optimization Approach to Robust Fundamental Matrix Estimation

no code implementations CVPR 2015 Yongfang Cheng, Jose A. Lopez, Octavia Camps, Mario Sznaier

This paper considers the problem of recovering a subspace arrangement from noisy samples, potentially corrupted with outliers.

Robust Anomaly Detection Using Semidefinite Programming

no code implementations3 Apr 2015 Jose A. Lopez, Octavia Camps, Mario Sznaier

This paper presents a new approach, based on polynomial optimization and the method of moments, to the problem of anomaly detection.

Anomaly Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.