Search Results for author:
Found 53 papers, 7 papers with code
FedVAE: Trajectory privacy preserving based on Federated Variational AutoEncoder
The use of trajectory data with abundant spatial-temporal information is pivotal in Intelligent Transport Systems (ITS) and various traffic system tasks.
AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving
This necessitates an expensive process of continuously curating and annotating data with significant human effort.
Using CPI in Loss Given Default Forecasting Models for Commercial Real Estate Portfolio
Forecasting the loss given default (LGD) for defaulted Commercial Real Estate (CRE) loans poses a significant challenge due to the extended resolution and workout time associated with such defaults, particularly in CCAR and CECL framework where the utilization of post-default information, including macroeconomic variables (MEVs) such as unemployment (UER) and various rates, is restricted.
GAN-driven Electromagnetic Imaging of 2-D Dielectric Scatterers
The images reconstructed at the output of the inverse network are validated through comparison with outputs from the forward neural network, addressing the non-uniqueness challenge inherent to electromagnetic (EM) imaging problems.
Design and implementation of multiprotocol framework for residential prosumer incorporation in flexibility markets
This research presents a novel approach to address the challenges of managing flexibility strategies in residential areas, providing a practical solution for prosumers to actively participate in optimizing energy consumption and enhancing the stability and quality of the electricity system amidst the growing integration of distributed renewable energy.
An Exploration to the Correlation Structure and Clustering of Macroeconomic Variables
One of these interesting observations is that, for a list of 132 transformations derived from 44 targeted MEVs that cover 5 different aspects of the U. S. economy (which takes as a subset the 10+ key MEVs published by FRB), compared to benign years where there are typically 20-25 clusters, during the great financial crisis (GFC), i. e., 2007-2010, they exhibited a more synchronized and less diversified pattern of movement, forming roughly 15 clusters.
Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitations
Active recognition, which allows intelligent agents to explore observations for better recognition performance, serves as a prerequisite for various embodied AI tasks, such as grasping, navigation and room arrangements.
Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception
Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions.
Causal Rule Learning: Enhancing the Understanding of Heterogeneous Treatment Effect via Weighted Causal Rules
In the rule discovery phase, we utilize a causal forest to generate a pool of causal rules with corresponding subgroup average treatment effects.
A Grammatical Compositional Model for Video Action Detection
Analysis of human actions in videos demands understanding complex human dynamics, as well as the interaction between actors and context.
Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance
First, prediction uncertainty should be separately quantified as confusion depicting inter-class uncertainties and ignorance identifying out-of-distribution samples.
Beyond Empirical Risk Minimization: Local Structure Preserving Regularization for Improving Adversarial Robustness
In this manner, the attacking effect of adversarial samples lying in the vicinity of clean samples can be alleviated.
ALUM: Adversarial Data Uncertainty Modeling from Latent Model Uncertainty Compensation
Thus, the critical data uncertainty and model uncertainty caused by noisy data can be readily quantified for improving model robustness.
Adaptive Modeling of Uncertainties for Traffic Forecasting
We evaluated QuanTraffic by applying it to five representative DNN models for traffic forecasting across seven public datasets.
An empirical study of the effect of background data size on the stability of SHapley Additive exPlanations (SHAP) for deep learning models
In our empirical study on the MIMIC-III dataset, we show that the two core explanations - SHAP values and variable rankings fluctuate when using different background datasets acquired from random sampling, indicating that users cannot unquestioningly trust the one-shot interpretation from SHAP.
SA-VQA: Structured Alignment of Visual and Semantic Representations for Visual Question Answering
As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality representations.
Morphable Detector for Object Detection on Demand
Once an MD is learned, it is able to use a few samples of a novel class to directly compute its prototype to fulfill the online morphing process.
Toward a Fairness-Aware Scoring System for Algorithmic Decision-Making
Then, we transform the social welfare maximization problem into the risk minimization task in machine learning, and derive a fairness-aware scoring system with the help of mixed integer programming.
Lifespan associations of resting-state brain functional networks with ADHD symptoms
Our findings reveal a lifespan association of brain networks with ADHD symptoms and provide potential shared neural bases of distinct ADHD symptoms in children and adults.
Unsupervised Embedding Learning from Uncertainty Momentum Modeling
We justify that the performance limitation is caused by the gradient vanishing on these sample outliers.
Transition behavior of the seizure dynamics modulated by the astrocyte inositol triphosphate noise
Our simulation results show that the increase of the IP3 noise intensity induces the depolarization-block epileptic seizures together with an increase in neuronal firing frequency.
Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas
By the proposed physical regularization, our method can generate HDRs which are not only visually appealing but also physically plausible.
Multi-dimensional wave steering with higher-order topological phononic crystal
The recent discovery and realizations of higher-order topological insulators enrich the fundamental studies on topological phases.
Applied Physics
Abnormal topological refraction into free medium at sub-wavelength scale in valley phononic crystal plates
In this work we propose a topological valley phononic crystal plate and we extensively investigate the refraction of valley modes into the surrounding homogeneous medium.
Applied Physics
FLAR: A Unified Prototype Framework for Few-Sample Lifelong Active Recognition
To address this demand, in this paper, we propose a unified framework towards Few-sample Lifelong Active Recognition (FLAR), which aims at performing active recognition on progressively arising novel categories that only have few training samples.
Contrastive Learning for Label Efficient Semantic Segmentation
While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have achieved impressive results by using large amounts of labeled training data, their performance drops significantly as the amount of labeled data decreases.
Contrastive Learning for Label-Efficient Semantic Segmentation
While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have achieved impressive results by using large amounts of labeled training data, their performance drops significantly as the amount of labeled data decreases.
Deterministic and probabilistic deep learning models for inverse design of broadband acoustic cloak
Concealing an object from incoming waves (light and/or sound) remained science fiction for a long time due to the absence of wave-shielding materials in nature.
Applied Physics Computational Physics
Object Detection with a Unified Label Space from Multiple Datasets
To address this challenge, we design a framework which works with such partial annotations, and we exploit a pseudo labeling approach that we adapt for our specific case.
Exposing Deep-faked Videos by Anomalous Co-motion Pattern Detection
Recent deep learning based video synthesis approaches, in particular with applications that can forge identities such as "DeepFake", have raised great security concerns.
Uncertainty-aware Score Distribution Learning for Action Quality Assessment
Assessing action quality from videos has attracted growing attention in recent years.
Ranked #4 on
Action Quality Assessment
on AQA-7
Recognizing Part Attributes with Insufficient Data
Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications.
Bimodal Stereo: Joint Shape and Pose Estimation from Color-Depth Image Pair
In the pipeline, the estimated shape is refined by the shape prior from the given depth map under the estimated pose.
Visual Query Answering by Entity-Attribute Graph Matching and Reasoning
Based on GEA and Q, we provide techniques to find matches of Q in GEA, as the answer of Qnl in Img.
A Compositional Textual Model for Recognition of Imperfect Word Images
Printed text recognition is an important problem for industrial OCR systems.
Optical Character Recognition (OCR)
Printed Text Recognition
Conscious Inference for Object Detection
Current Convolutional Neural Network (CNN)-based object detection models adopt strictly feedforward inference to predict the final detection results.
Exploiting Vector Fields for Geometric Rectification of Distorted Document Images
This paper proposes a segment-free method for geometric rectification of a distorted document image captured by a hand-held camera.
Deeply Learned Compositional Models for Human Pose Estimation
This results in a network with a hierarchical compositional architecture and bottom-up/top-down inference stages.
Ranked #11 on
Pose Estimation
on MPII Human Pose
Semi-supervised Transfer Learning for Image Rain Removal
However, previous deep learning methods need to pre-collect a large set of image pairs with/without synthesized rain for training, which tends to make the neural network be biased toward learning the specific patterns of the synthesized rain, while be less able to generalize to real test samples whose rain types differ from those in the training data.
Ranked #8 on
Single Image Deraining
on Test100
Learning Low-Dimensional Temporal Representations
Low-dimensional discriminative representations enhance machine learning methods in both performance and complexity, motivating supervised dimensionality reduction (DR) that transforms high-dimensional data to a discriminative subspace.
Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference Constraints
Multi-shot person re-identification (MsP-RID) utilizes multiple images from the same person to facilitate identification.
Fictitious GAN: Training GANs with Historical Models
Inspired by the fictitious play learning process, a novel training method, referred to as Fictitious GAN, is introduced.
Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification
In contrast to these methods, this paper advocates a different paradigm: part of the learning can be performed online but with nominal costs, so as to achieve online metric adaptation for different input probes.
Towards a Unified Compositional Model for Visual Pattern Modeling
Compositional models represent visual patterns as hierarchies of meaningful and reusable parts.
Learning Reconstruction-Based Remote Gaze Estimation
A common treatment is to use the same local reconstruction in the two spaces, i. e., the reconstruction weights in the appearance space are transferred to the gaze space for gaze reconstruction.
Heteroscedastic Max-Min Distance Analysis
Many discriminant analysis methods such as LDA and HLDA actually maximize the average pairwise distances between classes, which often causes the class separation problem.
Unifying Spatial and Attribute Selection for Distracter-Resilient Tracking
This paper presents a novel method to jointly determine the best spatial location and the optimal metric.
Cross-view Action Modeling, Learning and Recognition
We present a novel multiview spatio-temporal AND-OR graph (MST-AOG) representation for cross-view action recognition, i. e., the recognition is performed on the video from an unknown and unseen view.
Learning Fine-grained Image Similarity with Deep Ranking
This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images. It has higher learning capability than models based on hand-crafted features.
Scalable Matting: A Sub-linear Approach
However, matting by graph Laplacian is still very difficult to solve and gets much harder as the image size grows: current iterative methods slow down as $\mathcal{O}\left(n^2 \right)$ in the resolution $n$.
Detecting and Aligning Faces by Image Retrieval
In order to overcome these challenges, we present a novel and robust exemplarbased face detector that integrates image retrieval and discriminative learning.
Large Displacement Optical Flow from Nearest Neighbor Fields
We use approximate nearest neighbor fields to compute an initial motion field and use a robust algorithm to compute a set of similarity transformations as the motion candidates for segmentation.
