Search Results for author:
Found 85 papers, 29 papers with code
Bridging the Generalization Gap in Text-to-SQL Parsing with Schema Expansion
Text-to-SQL parsers map natural language questions to programs that are executable over tables to generate answers, and are typically evaluated on large-scale datasets like Spider (Yu et al., 2018).
Sparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph Construction
Depth completion is a widely studied problem of predicting a dense depth map from a sparse set of measurements and a single RGB image.
Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence Annotation
This paper investigates whether models can learn to find evidence from a large corpus, with only distant supervision from answer labels for model training, thereby generating no additional annotation cost.
What’s in a Name? Answer Equivalence For Open-Domain Question Answering
We incorporate answers for two settings: evaluation with additional answers and model training with equivalent answers.
Just a Glimpse: Rethinking Temporal Information for Video Continual Learning
Studying continual learning in the video domain poses even more challenges, as video data contains a large number of frames, which places a higher burden on the replay memory.
Mixture of Prompt Experts for Generalizable and Interpretable Question Answering
By strategically selecting the best specialized model for each given question, our MOPE system significantly outperforms any single specialized model on a collection of 12 QA datasets from four reasoning types.
Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs
Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consistency.
Coronary Artery Semantic Labeling using Edge Attention Graph Matching Network
The presence of atherosclerotic lesions in coronary arteries is the underlying pathophysiological basis of CAD, and accurate extraction of individual arterial branches using invasive coronary angiography (ICA) is crucial for stenosis detection and CAD diagnosis.
A new method using deep learning to predict the response to cardiac resynchronization therapy
The DL model outperformed the ML models, showcasing the additional predictive benefit of utilizing SPECT MPI polarmaps.
Multi-crop Contrastive Learning for Unsupervised Image-to-Image Translation
Recently, image-to-image translation methods based on contrastive learning achieved state-of-the-art results in many tasks.
Large-capacity and Flexible Video Steganography via Invertible Neural Network
For large-capacity, we present a reversible pipeline to perform multiple videos hiding and recovering through a single invertible neural network (INN).
Spectral Normalized Dual Contrastive Regularization for Image-to-Image Translation
In order to improve the global structure information of the generated images, we formulate a semantically contrastive loss to make the global semantic structure of the generated images similar to the real images from the target domain in the semantic feature space.
CLCLSA: Cross-omics Linked embedding with Contrastive Learning and Self Attention for multi-omics integration with incomplete multi-omics data
Integration of heterogeneous and high-dimensional multi-omics data is becoming increasingly important in understanding genetic data.
FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
In this work, we propose a training-Free conditional Diffusion Model (FreeDoM) used for various conditions.
A Unified Continual Learning Framework with General Parameter-Efficient Tuning
The "pre-training $\rightarrow$ downstream adaptation" presents both new opportunities and challenges for Continual Learning (CL).
Open Set Action Recognition via Multi-Label Evidential Learning
Existing methods for open-set action recognition focus on novelty detection that assumes video clips show a single action, which is unrealistic in the real world.
A novel method using machine learning to integrate features from lung and epicardial adipose tissue for detecting the severity of COVID-19 infection
A generalized linear regression model for detecting the severity of COVID-19 was built in a derivation cohort and evaluated in internal (125, cohort1) and external (100, cohort2) validation cohorts.
An Automated Vulnerability Detection Framework for Smart Contracts
With the increase of the adoption of blockchain technology in providing decentralized solutions to various problems, smart contracts have become more popular to the point that billions of US Dollars are currently exchanged every day through such technology.
AGMN: Association Graph-based Graph Matching Network for Coronary Artery Semantic Labeling on Invasive Coronary Angiograms
Semantic labeling of coronary arterial segments in invasive coronary angiography (ICA) is important for automated assessment and report generation of coronary artery stenosis in the computer-aided diagnosis of coronary artery disease (CAD).
Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content.
xFBD: Focused Building Damage Dataset and Analysis
This new challenge involves a new dataset and metrics indicating solution performance when damage is more local and limited than in xBD.
Localizing Objects in 3D from Egocentric Videos with Visual Queries
With the recent advances in video and 3D understanding, novel 4D spatio-temporal challenges fusing both concepts have emerged.
LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation
Object location priors have been shown to be critical for the standard 6D object pose estimation setting, where the training and testing objects are the same.
Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content.
Estimating more camera poses for ego-centric videos is essential for VQ3D
Visual queries 3D localization (VQ3D) is a task in the Ego4D Episodic Memory Benchmark.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Multi-view information fusion using multi-view variational autoencoders to predict proximal femoral strength
The aim of this paper is to design a deep learning-based model to predict proximal femoral strength using multi-view information fusion.
A New Hip Fracture Risk Index Derived from FEA-Computed Proximal Femur Fracture Loads and Energies-to-Failure
The results showed that the average of the area under the receive operating characteristic curve (AUC) using PC1 was always higher than that using all FE parameters combined in the male subjects.
DCE: Offline Reinforcement Learning With Double Conservative Estimates
Previous conservative estimation methods are usually difficult to avoid the impact of OOD actions on Q-value estimates.
On the Relation between Sensitivity and Accuracy in In-context Learning
In-context learning (ICL) suffers from oversensitivity to the prompt, making it unreliable in real-world scenarios.
Automatic reorientation by deep learning to generate short axis SPECT myocardial perfusion images
Five-fold cross-validation with 180 stress and 201 rest MPIs was used for training and internal validation; the remaining images were used for testing.
Automatic extraction of coronary arteries using deep learning in invasive coronary angiograms
A deep learning model U-Net 3+, which incorporates the full-scale skip connections and deep supervisions, was proposed for automatic extraction of coronary arteries from ICAs.
A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images
Conclusion: Our proposed method achieved a high accuracy in extracting LV myocardial contours and assessing LV function.
Re-Examining Calibration: The Case of Question Answering
Building on those observations, we propose a new calibration metric, MacroCE, that better captures whether the model assigns low confidence to wrong predictions and high confidence to correct predictions.
Adaptive Fairness-Aware Online Meta-Learning for Changing Environments
Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision.
ETAD: Training Action Detection End to End on a Laptop
We propose to sequentially forward the snippet frame through the video encoder, and backward only a small necessary portion of gradients to update the encoder.
When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search
TNAS performs a modified bi-level Breadth-First Search in the proposed trees to discover a high-performance architecture.
End-to-End Active Speaker Detection
Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage process: feature extraction and spatio-temporal context aggregation.
Ranked #4 on
Audio-Visual Active Speaker Detection
on AVA-ActiveSpeaker
(using extra training data)
R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning
After RRL, the classification head is refined with global class-balanced classification loss to address the data imbalance issue as well as learn the decision boundaries between new and previous classes.
Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction
To the best of our knowledge, the proposed method is the first to mine 3D semantic consistent keypoints from a mutual reconstruction view.
Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects
In this paper, we tackle the task of estimating the 3D orientation of previously-unseen objects from monocular images.
SegTAD: Precise Temporal Action Detection via Semantic Segmentation
To address these issues and precisely model temporal action detection, we formulate the task of temporal action detection in a novel perspective of semantic segmentation.
Layer Adaptive Deep Neural Networks for Out-of-distribution Detection
During the forward pass of Deep Neural Networks (DNNs), inputs gradually transformed from low-level features to high-level conceptual labels.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos
We validate our approach in two large-scale datasets, EPIC-Kitchens, and HOMAGE.
MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions
The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable data-intensive machine learning techniques.
Ranked #2 on
Natural Language Moment Retrieval
on MAD
Ego4D: Around the World in 3,000 Hours of Egocentric Video
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite.
Spatial-temporal V-Net for automatic segmentation and quantification of right ventricles in gated myocardial perfusion SPECT images
By integrating the spatial features from each cardiac frame of the gated MPS and the temporal features from the sequential cardiac frames of the gated MPS, we developed a Spatial-Temporal V-Net (ST-VNet) for automatic extraction of RV endocardial and epicardial contours.
Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation
Open-domain question answering answers a question based on evidence retrieved from a large corpus.
Automatic Identification of the End-Diastolic and End-Systolic Cardiac Frames from Invasive Coronary Angiography Videos
More specifically, a detection algorithm is first used to detect the key points of coronary arteries, and then an optical flow method is employed to track the trajectories of the selected key points.
What's in a Name? Answer Equivalence For Open-Domain Question Answering
We incorporate answers for two settings: evaluation with additional answers and model training with equivalent answers.
Fairness-Aware Online Meta-learning
To overcome such issues and bridge the gap, in this paper for the first time we proposed a novel online meta-learning algorithm, namely FFML, which is under the setting of unfairness prevention.
A method using deep learning to discover new predictors of CRT response from mechanical dyssynchrony on gated SPECT MPI
Correlation analysis was used to explain the relationships between new parameters with conventional LVMD parameters.
FedSup: A Communication-Efficient Federated Learning Fatigue Driving Behaviors Supervision Framework
With the proliferation of edge smart devices and the Internet of Vehicles (IoV) technologies, intelligent fatigue detection has become one of the most-used methods in our daily driving.
Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces.
Complex Factoid Question Answering with a Free-Text Knowledge Graph
DELFT's advantage comes from both the high coverage of its free-text knowledge graph-more than double that of dbpedia relations-and the novel graph neural network which reasons on the rich but noisy free-text evidence.
A Deep Learning-based Method to Extract Lumen and Media-Adventitia in Intravascular Ultrasound Images
In this paper, we aim to develop a deep learning-based method using an encoder-decoder deep architecture to automatically extract both lumen and MA border.
A Deep Learning-Based Approach to Extracting Periosteal and Endosteal Contours of Proximal Femur in Quantitative CT Images
In this study, we proposed an approach based on deep learning for the automatic extraction of the periosteal and endosteal contours of proximal femur in order to differentiate cortical and trabecular bone compartments.
Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
In this paper, we propose a general scheme to analyze the gradient vanishing phenomenon, also known as the barren plateau phenomenon, in training quantum neural networks with the ZX-calculus.
A new approach to extracting coronary arteries and detecting stenosis in invasive coronary angiograms
We aim to develop an automatic algorithm by deep learning to extract coronary arteries from ICAs. In this study, a multi-input and multi-scale (MIMS) U-Net with a two-stage recurrent training strategy was proposed for the automatic vessel segmentation.
Progressive Correspondence Pruning by Consensus Learning
Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences.
Wetting equilibrium in a rectangular channel
When a capillary channel with corners is wetted by a fluid, there are regions where the fluid fills the whole cross-section and regions where only the corners are filled by the fluid.
Soft Condensed Matter
Video Self-Stitching Graph Network for Temporal Action Localization
In VSS, we focus on a short period of a video and magnify it along the temporal dimension to obtain a larger scale.
Ranked #10 on
Temporal Action Localization
on ActivityNet-1.3
A Nested Bi-level Optimization Framework for Robust Few Shot Learning
Model-Agnostic Meta-Learning (MAML), a popular gradient-based meta-learning framework, assumes that the contribution of each task or instance to the meta-learner is equal.
On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries
Large-scale semantic parsing datasets annotated with logical forms have enabled major advances in supervised approaches.
A Primal-Dual Subgradient Approachfor Fair Meta Learning
In this work, we propose a Primal-Dual Fair Meta-learning framework, namely PDFM, which learns to train fair machine learning models using only a few examples based on data from related tasks.
Unfairness Discovery and Prevention For Few-Shot Regression
In this work, we first discover discrimination from data using a causal Bayesian knowledge graph which not only demonstrates the dependency of the protected variable on target but also indicates causal effects between all variables.
Fair Meta-Learning For Few-Shot Classification
Artificial intelligence nowadays plays an increasingly prominent role in our life since decisions that were once made by humans are now delegated to automated systems.
Rank-Based Multi-task Learning for Fair Regression
In this work, we develop a novel fairness learning approach for multi-task regression models based on a biased training dataset, using a popular rank-based non-parametric independence test, i. e., Mann Whitney U statistic, for measuring the dependency between target variable and protected variables.
A Novel Method for ECG Signal Classification via One-Dimensional Convolutional Neural Network
This paper presents an end-to-end ECG signal classification method based on a novel segmentation strategy via 1D Convolutional Neural Networks (CNN) to aid the classification of ECG signals.
A Deep Learning-Based Method for Automatic Segmentation of Proximal Femur from Quantitative Computed Tomography Images
During the experiments for the entire cohort then for male and female subjects separately, 90% of the subjects were used in 10-fold cross-validation for training and internal validation, and to select the optimal parameters of the proposed models; the rest of the subjects were used to evaluate the performance of models.
Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention
Transformers have achieved new heights modeling natural language as a sequence of text tokens.
Ranked #47 on
Question Answering
on HotpotQA
QDNN: DNN with Quantum Neural Network Layers
In this paper, we introduce a quantum extension of classical DNN, QDNN.
Learning Semantic Neural Tree for Human Parsing
In this paper, we design a novel semantic neural tree for human parsing, which uses a tree architecture to encode physiological structure of human body, and designs a coarse to fine process in a cascade manner to generate accurate results.
G-TAD: Sub-Graph Localization for Temporal Action Detection
In this work, we propose a graph convolutional network (GCN) model to adaptively incorporate multi-level semantic context into video features and cast temporal action detection as a sub-graph localization problem.
Ranked #3 on
Temporal Action Localization
on FineAction
Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis.
Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
Specifically, we incorporate convolutional operations along edges of the tree structure, and use the routing functions in each node to determine the root-to-leaf computational paths within the tree.
Ranked #31 on
Fine-Grained Image Classification
on Stanford Cars
Fine-Grained Image Classification
Fine-Grained Visual Categorization
Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence
Matching corresponding features between two images is a fundamental task to computer vision with numerous applications in object recognition, robotics, and 3D reconstruction.
Comparative evaluation of 2D feature correspondence selection algorithms
Correspondence selection aiming at seeking correct feature correspondences from raw feature matches is pivotal for a number of feature-matching-based tasks.
Learning to Fuse Local Geometric Features for 3D Rigid Data Matching
This paper presents a simple yet very effective data-driven approach to fuse both low-level and high-level local geometric features for 3D rigid data matching.
ThumbNet: One Thumbnail Image Contains All You Need for Recognition
Although deep convolutional neural networks (CNNs) have achieved great success in computer vision tasks, its real-world application is still impeded by its voracious demand of computational resources.
NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences
Feature correspondence selection is pivotal to many feature-matching based tasks in computer vision.
A dataset and baselines for sequential open-domain question answering
Previous work on question-answering systems mainly focuses on answering individual questions, assuming they are independent and devoid of context.
LightNet: A Versatile, Standalone Matlab-based Environment for Deep Learning
LightNet is a lightweight, versatile and purely Matlab-based deep learning framework.
Analyzing Time Series Changes of Correlation between Market Share and Concerns on Companies measured through Search Engine Suggests
We finally propose how to predict the market share of a specific product genre based on the rates of concerns of those who search for Web pages.
Image Compressive Sensing Recovery Using Adaptively Learned Sparsifying Basis via L0 Minimization
From many fewer acquired measurements than suggested by the Nyquist sampling theory, compressive sensing (CS) theory demonstrates that, a signal can be reconstructed with high probability when it exhibits sparsity in some domain.
