Search Results for author:
Found 35 papers, 15 papers with code
RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images
Recent methods for people detection in overhead, fisheye images either use radially-aligned bounding boxes to represent people, assuming people always appear along image radius or require significant pre-/post-processing which radically increases computational complexity.
BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen Videos
In order to reduce the chance of overfitting, we also introduce a new data-augmentation technique which mitigates the impact of illumination difference between the background frames and the current frame.
BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtraction
In this work, we introduce spatio-temporal data augmentations and apply them to one of the leading video-agnostic BGS algorithms, BSUV-Net.
BSUV-Net: A Fully-Convolutional Neural Network forBackground Subtraction of Unseen Videos
In order to reduce the chance of overfitting, we also introduce a new data-augmentation technique which mitigates the impact of illumination difference between the background frames and the current frame.
Supervised Contrastive Learning with Hard Negative Samples
In this paper, motivated by the effectiveness of hard-negative sampling strategies in H-UCL and the usefulness of label information in SCL, we propose a contrastive learning framework called hard-negative supervised contrastive learning (H-SCL).
Hard Negative Sampling via Regularized Optimal Transport for Contrastive Representation Learning
We study the problem of designing hard negative sampling distributions for unsupervised contrastive representation learning.
OpenFraming: We brought the ML; you bring the data. Interact with your data and discover its frames
The degree of user involvement is flexible: they can run models that have been pre-trained on select issues; submit labeled documents and train a new model for frame classification; or submit unlabeled documents and obtain potential frames of the documents.
Node Embedding via Word Embedding for Network Community Discovery
Neural node embeddings have recently emerged as a powerful representation for supervised learning tasks involving graph-structured data.
Barycentric-alignment and reconstruction loss minimization for domain generalization
To bridge this gap between theory and practice, we introduce a new upper bound that is free of terms having such dual dependence, resulting in a fully optimizable risk upper bound for the unseen domain.
OpenFraming: Open-sourced Tool for Computational Framing Analysis of Multilingual Data
We propose and guide users through a five-step end-to-end computational framing analysis framework grounded in media framing theory in communication research.
Conditional entropy minimization principle for learning domain invariant representation features
Invariance-principle-based methods such as Invariant Risk Minimization (IRM), have recently emerged as promising approaches for Domain Generalization (DG).
Trade-off between reconstruction loss and feature alignment for domain generalization
To deal with challenging settings in DG where both data and label of the unseen domain are not available at training time, the most common approach is to design the classifiers based on the domain-invariant representation features, i. e., the latent representations that are unchanged and transferable between domains.
A principled approach to model validation in domain generalization
Domain generalization aims to learn a model with good generalization ability, that is, the learned model should not only perform well on several seen domains but also on unseen domains with different data distributions.
VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition
Reliable facial expression recognition plays a critical role in human-machine interactions.
Facial Expression Recognition
Facial Expression Recognition (FER)
+4
Privacy-Preserving Adversarial Networks
We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive information.
Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions
Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos.
Necessary and Sufficient Conditions and a Provably Efficient Algorithm for Separable Topic Discovery
We develop necessary and sufficient conditions and a novel provably consistent and efficient algorithm for discovering topics (latent factors) from observations (documents) that are realized from a probabilistic mixture of shared latent factors that have certain properties.
Learning Mixed Membership Mallows Models from Pairwise Comparisons
Our key algorithmic insight for estimation is to establish a statistical connection between M4 and topic models by viewing pairwise comparisons as words, and users as documents.
A Topic Modeling Approach to Ranking
We propose a topic modeling approach to the prediction of preferences in pairwise comparisons.
Sensing-Aware Kernel SVM
We propose a novel approach for designing kernels for support vector machines (SVMs) when the class label is linked to the observation through a latent state and the likelihood function of the observation given the state (the sensing model) is available.
Necessary and Sufficient Conditions for Novel Word Detection in Separable Topic Models
The simplicial condition and other stronger conditions that imply it have recently played a central role in developing polynomial time algorithms with provable asymptotic consistency and sample complexity guarantees for topic estimation in separable topic models.
An Impossibility Result for High Dimensional Supervised Learning
We study high-dimensional asymptotic performance limits of binary supervised classification problems where the class conditional densities are Gaussian with unknown means and covariances and the number of signal dimensions scales faster than the number of labeled training samples.
BUOCA: Budget-Optimized Crowd Worker Allocation
We next train a machine learning system (BUOCA-ML) that predicts an optimal number of crowd workers needed to maximize the accuracy of the labeling.
A Cyclically-Trained Adversarial Network for Invariant Representation Learning
Specifically, we propose a cyclically-trained adversarial network to learn a mapping from image space to latent representation space and back such that the latent representation is invariant to a specified factor of variation (e. g., identity).
VAE/WGAN-Based Image Representation Learning For Pose-Preserving Seamless Identity Replacement In Facial Images
We present a novel variational generative adversarial network (VGAN) based on Wasserstein loss to learn a latent representation from a face image that is invariant to identity but preserves head-pose information.
Low-Resolution Overhead Thermal Tripwire for Occupancy Estimation
We propose a people counting system which uses a low-resolution thermal sensor.
Multi-Label and Multilingual News Framing Analysis
News framing refers to the practice in which aspects of specific issues are highlighted in the news to promote a particular interpretation.
Ergodic Limits, Relaxations, and Geometric Properties of Random Walk Node Embeddings
This paper studies properties of random walk based node embeddings in the unsupervised setting of discovering hidden block structure in the network, i. e., learning node representations whose cluster structure in Euclidean space reflects their adjacency structure within the network.
Detecting Frames in News Headlines and Lead Images in U.S. Gun Violence Coverage
Such perspectives are called “frames” in communication research. We study, for the first time, the value of combining lead images and their contextual information with text to identify the frame of a given news article.
Joint covariate-alignment and concept-alignment: a framework for domain generalization
Particularly, our framework proposes to jointly minimize both the covariate-shift as well as the concept-shift between the seen domains for a better performance on the unseen domain.
An Unsupervised Approach to Discover Media Frames
We discuss the effectiveness of our approach by comparing the frames it generates in an unsupervised manner to the domain-expert-derived frames for the issue of gun violence, for which a supervised learning model for frame recognition exists.
FRIDA: Fisheye Re-Identification Dataset with Annotations
Person re-identification (PRID) from side-mounted rectilinear-lens cameras is a well-studied problem.
Spatio-Visual Fusion-Based Person Re-Identification for Overhead Fisheye Images
Person re-identification (PRID) has been thoroughly researched in typical surveillance scenarios where various scenes are monitored by side-mounted, rectilinear-lens cameras.
Estimating Distances Between People using a Single Overhead Fisheye Camera with Application to Social-Distancing Oversight
Unobtrusive monitoring of distances between people indoors is a useful tool in the fight against pandemics.
On neural and dimensional collapse in supervised and unsupervised contrastive learning with hard negative sampling
For a widely-studied data model and general loss and sample-hardening functions we prove that the Supervised Contrastive Learning (SCL), Hard-SCL (HSCL), and Unsupervised Contrastive Learning (UCL) risks are minimized by representations that exhibit Neural Collapse (NC), i. e., the class means form an Equianglular Tight Frame (ETF) and data from the same class are mapped to the same representation.
