Search Results for author:
Found 20 papers, 5 papers with code
Continuously Reliable Detection of New-Normal Misinformation: Semantic Masking and Contrastive Smoothing in High-Density Latent Regions
Toxic misinformation campaigns have caused significant societal harm, e. g., affecting elections and COVID-19 information awareness.
Time-Aware Datasets are Adaptive Knowledgebases for the New Normal
Recent advances in text classification and knowledge capture in language models have relied on availability of large-scale text datasets.
ATEAM: Knowledge Integration from Federated Datasets for Vehicle Feature Extraction using Annotation Team of Experts
We evaluate ATEAM and KID for vehicle recognition problems and show that our integrated dataset can help off-the-shelf models achieve excellent accuracy on VMMR and vehicle re-id with no changes to model architectures.
EdnaML: A Declarative API and Framework for Reproducible Deep Learning
We present several examples of ML pipelines with EdnaML, including a large-scale fake news labeling and classification system with six sub-pipelines managed by EdnaML.
Constructive Interpretability with CoLabel: Corroborative Integration, Complementary Features, and Collaborative Learning
CoLabel performs VMMR with a composite of interpretable features such as vehicle color, type, and make, all based on interpretable annotations of the ground truth labels.
MiDAS: Multi-integrated Domain Adaptive Supervision for Fake News Detection
Given a set of fake news models trained on multiple domains, we propose an adaptive decision module to select the best-fit model for a new sample.
Evaluating Generalizability of Fine-Tuned Models for Fake News Detection
However, on some subsets of unseen data that overlap with training data, models have higher accuracy.
Challenges and Opportunities in Rapid Epidemic Information Propagation with Live Knowledge Aggregation from Social Media
We describe the EDNA/LITMUS tools that implement EBKA, integrating social media such as Twitter and Facebook with authoritative sources such as WHO and CDC, creating and updating live knowledge on the COVID-19 pandemic.
EDNA-COVID: A Large-Scale Covid-19 Dataset Collected with the EDNA Streaming Toolkit
To address this, we present (i) the EDNA streaming toolkit for consuming and processing streaming data, and (ii) EDNA-Covid, a multilingual, large-scale dataset of coronavirus-related tweets collected with EDNA since January 25, 2020.
Social and Information Networks
ODIN: Automated Drift Detection and Recovery in Video Analytics
In this paper, we present a visual data analytics system, called ODIN, that automatically detects and recovers from drift.
Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention
Vehicle re-identification (re-id) is a fundamental problem for modern surveillance camera networks.
Small, Accurate, and Fast Vehicle Re-ID on the Edge: the SAFR Approach
We propose a Small, Accurate, and Fast Re-ID (SAFR) design for flexible vehicle re-id under a variety of compute environments such as cloud, mobile, edge, or embedded devices by only changing the re-id model backbone.
EventMapper: Detecting Real-World Physical Events Using Corroborative and Probabilistic Sources
EventMapper integrates high-latency, high-accuracy corroborative sources such as physical sensors with low-latency, noisy probabilistic sources such as social media streams to deliver real-time, global event recognition.
Robust, Extensible, and Fast: Teamed Classifiers for Vehicle Tracking and Vehicle Re-ID in Multi-Camera Networks
Current frameworks for management are designed for multi-camera networks in a closed dataset environment where there is limited variability in cameras and characteristics of the surveillance environment are well known.
Event Detection in Noisy Streaming Data with Combination of Corroborative and Probabilistic Sources
The ubiquity of social networks and human sensors in the field provides a tremendous amount of real-time, live data about true physical events from around the world.
Concept Drift Adaptive Physical Event Detection for Social Media Streams
Our application has high performance: using classifiers trained in 2014, achieving event detection accuracy of 0. 988, compared to 0. 762 for static approaches.
ASSED -- A Framework for Identifying Physical Events through Adaptive Social Sensor Data Filtering
Specifically, ASSED is a framework to support continuous filter generation and updates with machine learning using streaming data from high-confidence sources (physical and annotated sensors) and social networks.
Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks
Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs).
Differentially Private Model Publishing for Deep Learning
However, when the training datasets are crowdsourced from individuals and contain sensitive information, the model parameters may encode private information and bear the risks of privacy leakage.
A Comparative Measurement Study of Deep Learning as a Service Framework
Big data powered Deep Learning (DL) and its applications have blossomed in recent years, fueled by three technological trends: a large amount of digitized data openly accessible, a growing number of DL software frameworks in open source and commercial markets, and a selection of affordable parallel computing hardware devices.
