Search Results for author:
Found 276 papers, 115 papers with code
Leveraging Capsule Routing to Associate Knowledge with Medical Literature Hierarchically
Integrating knowledge into text is a promising way to enrich text representation, especially in the medical field.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise
Leveraging these modified representations, DEGNN subsequently addresses downstream tasks, ensuring robustness against noise present in both edges and node features of real-world graphs.
Future-Proofing Class Incremental Learning
Exemplar-Free Class Incremental Learning is a highly challenging setting where replay memory is unavailable.
EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs
In this work, we propose an initial comprehensive framework called EventGround, which aims to tackle the problem of grounding free-texts to eventuality-centric KGs for contextualized narrative reasoning.
Decentralized Stochastic Subgradient Methods for Nonsmooth Nonconvex Optimization
Furthermore, we establish that our proposed framework encompasses a wide range of existing efficient decentralized subgradient methods, including decentralized stochastic subgradient descent (DSGD), DSGD with gradient-tracking technique (DSGD-T), and DSGD with momentum (DSGDm).
Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection
We find that in graph anomaly detection, the homophily distribution differences between different classes are significantly greater than those in homophilic and heterophilic graphs.
Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study
We show that CLIP leads to a significant robustness drop compared to supervised ImageNet models on our benchmark, especially under synthetic distribution shift and adversarial attacks.
Advancing Generalizable Remote Physiological Measurement through the Integration of Explicit and Implicit Prior Knowledge
Remote photoplethysmography (rPPG) is a promising technology that captures physiological signals from face videos, with potential applications in medical health, emotional computing, and biosecurity recognition.
Answering Diverse Questions via Text Attached with Key Audio-Visual Clues
Audio-visual question answering (AVQA) requires reference to video content and auditory information, followed by correlating the question to predict the most precise answer.
Audio-visual Question Answering
Audio-Visual Question Answering (AVQA)
+3
ACT-MNMT Auto-Constriction Turning for Multilingual Neural Machine Translation
Large language model (LLM) has achieved promising performance in multilingual machine translation tasks through zero/few-shot prompts or prompt-tuning.
Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs), i. e., graph data augmentation and attack.
Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models
Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning.
Ranked #62 on
Visual Question Answering
on MM-Vet
AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors
Facial Action Units (AU) is a vital concept in the realm of affective computing, and AU detection has always been a hot research topic.
Ranked #1 on
Facial Action Unit Detection
on DISFA
Recent Advances, Applications, and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2023 Symposium
The organization of the research roundtables at the conference involved 17 Senior Chairs and 19 Junior Chairs across 11 tables.
Multi-modal Attribute Prompting for Vision-Language Models
To address this issue, we propose a Multi-modal Attribute Prompting method (MAP) by jointly exploring textual attribute prompting, visual attribute prompting, and attribute-level alignment.
A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection
Camouflaged object detection (COD) and salient object detection (SOD) are two distinct yet closely-related computer vision tasks widely studied during the past decades.
FedUV: Uniformity and Variance for Heterogeneous Federated Learning
Based on this finding, we introduce two regularization terms for local training to continuously emulate IID settings: (1) variance in the dimension-wise probability distribution of the classifier and (2) hyperspherical uniformity of representations of the encoder.
OncoGPT: A Medical Conversational Model Tailored with Oncology Domain Expertise on a Large Language Model Meta-AI (LLaMA)
The primary aim of this research was to develop a specialized language model that demonstrates improved accuracy in providing advice related to oncology.
Learning to Schedule Online Tasks with Bandit Feedback
These render reward and cost hard to model thus unknown before decision making.
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Training LLMs at this scale brings unprecedented challenges to training efficiency and stability.
Convergence Analysis of Split Federated Learning on Heterogeneous Data
We further extend the analysis to non-convex objectives and where some clients may be unavailable during training.
Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging
Such demographic biases present over a wide range of pathologies and demographic attributes.
AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation
Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study.
Safety of Multimodal Large Language Models on Images and Text
In this paper, we systematically survey current efforts on the evaluation, attack, and defense of MLLMs' safety on images and text.
Fast Adversarial Training against Textual Adversarial Attacks
Based on the observation that the adversarial perturbations crafted by single-step and multi-step gradient ascent are similar, FAT uses single-step gradient ascent to craft adversarial examples in the embedding space to expedite the training process.
CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning
The sequential process of conceptualization and instantiation is essential to generalizable commonsense reasoning as it allows the application of existing knowledge to unfamiliar scenarios.
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
The rapid development of open-source large language models (LLMs) has been truly remarkable.
Adversarially Trained Actor Critic for offline CMDPs
Theoretically, we demonstrate that when the actor employs a no-regret optimization oracle, SATAC achieves two guarantees: (i) For the first time in the offline RL setting, we establish that SATAC can produce a policy that outperforms the behavior policy while maintaining the same level of safety, which is critical to designing an algorithm for offline RL.
Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation
Although many applications require the use of knowledge for explanations, the utilization of abductive reasoning in conjunction with structured knowledge, such as a knowledge graph, remains largely unexplored.
Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns
The goal of session-based recommendation in E-commerce is to predict the next item that an anonymous user will purchase based on the browsing and purchase history.
Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration
This paper studies safe Reinforcement Learning (safe RL) with linear function approximation and under hard instantaneous constraints where unsafe actions must be avoided at each step.
AutoAugment Input Transformation for Highly Transferable Targeted Attacks
However, few of them are dedicated to input transformation. In this work, we observe a positive correlation between the logit/probability of the target class and diverse input transformation methods in targeted attacks.
MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied.
From Classification to Clinical Insights: Towards Analyzing and Reasoning About Mobile and Behavioral Health Data With Large Language Models
Passively collected behavioral health data from ubiquitous sensors holds significant promise to provide mental health professionals insights from patient's daily lives; however, developing analysis tools to use this data in clinical practice requires addressing challenges of generalization across devices and weak or ambiguous correlations between the measured signals and an individual's mental health.
ALPHA: AnomaLous Physiological Health Assessment Using Large Language Models
Our findings reveal that LLMs exhibit exceptional performance in determining medical indicators, including a Mean Absolute Error (MAE) of less than 1 beat per minute for heart rate and less than 1% for oxygen saturation (SpO2).
4K-Resolution Photo Exposure Correction at 125 FPS with ~8K Parameters
The illumination of improperly exposed photographs has been widely corrected using deep convolutional neural networks or Transformers.
Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts
This results in a set of candidate answers.
AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph
Cognitive research indicates that abstraction ability is essential in human intelligence, which remains under-explored in language models.
Training Robust Deep Physiological Measurement Models with Synthetic Video-based Data
However, there exists a significant gap between synthetic and real-world data, which hinders the generalization of neural models trained on these synthetic datasets.
P-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models
Lastly, P-Bench performs existing privacy attacks on LMs with pre-defined privacy objectives as the empirical evaluation results.
IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models
Then, we pair each sample with a bias indicator representing its bias degree, and use these extended samples to train a sample generator.
Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations
The spatial modulation utilizes the feature with large receptive field to modulate the feature with small receptive field.
LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses
For evaluation, we construct CaT, a benchmark consisting of eight text generation tasks, covering responses ranging from short phrases to paragraphs.
Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detection
Commonsense Knowledge Graphs (CSKGs) are crucial for commonsense reasoning, yet constructing them through human annotations can be costly.
QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering
Zero-shot commonsense Question-Answering (QA) requires models to reason about general situations beyond specific benchmarks.
On the Convergence of Federated Averaging under Partial Participation for Over-parameterized Neural Networks
Federated learning (FL) is a widely employed distributed paradigm for collaboratively training machine learning models from multiple clients without sharing local data.
Predicting Emergent Abilities with Infinite Resolution Evaluation
With PassUntil, we conduct a quantitative investigation into the scaling law of task performance.
ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery
Ideal unsupervised skill discovery methods are able to produce diverse and qualified skills in the absence of extrinsic reward, while the discovered skill set can efficiently adapt to downstream tasks in various ways.
Self-Consistent Narrative Prompts on Abductive Natural Language Inference
However, the inter-sentential coherence and the model consistency have not been well exploited in the previous works on this task.
Federated Linear Bandit Learning via Over-the-Air Computation
In this context, we propose a customized federated linear bandits scheme, where each device transmits an analog signal, and the server receives a superposition of these signals distorted by channel noise.
Video BagNet: short temporal receptive fields increase robustness in long-term action recognition
Previous work on long-term video action recognition relies on deep 3D-convolutional models that have a large temporal receptive field (RF).
Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks
To effectively learn the optimal EV charging control strategy, a federated deep reinforcement learning algorithm named FedSAC is further proposed.
Edit Temporal-Consistent Videos with Image Diffusion Model
In addition to the utilization of a pretrained T2I 2D Unet for spatial content manipulation, we establish a dedicated temporal Unet architecture to faithfully capture the temporal coherence of the input video sequences.
Dual-Stream Diffusion Net for Text-to-Video Generation
In particular, the designed two diffusion streams, video content and motion branches, could not only run separately in their private spaces for producing personalized video variations as well as content, but also be well-aligned between the content and motion domains through leveraging our designed cross-transformer interaction module, which would benefit the smoothness of generated videos.
Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection
Anatomically, there are innumerable correlations between AUs, which contain rich information and are vital for AU detection.
Ranked #2 on
Facial Action Unit Detection
on DISFA
CasCIFF: A Cross-Domain Information Fusion Framework Tailored for Cascade Prediction in Social Networks
Existing approaches for information cascade prediction fall into three main categories: feature-driven methods, point process-based methods, and deep learning-based methods.
Objects do not disappear: Video object detection by single-frame object location anticipation
2) Improved efficiency by only doing the expensive feature computations on a small subset of all frames.
Ranked #1 on
Video Object Detection
on Waymo Open Dataset
MSECNet: Accurate and Robust Normal Estimation for 3D Point Clouds by Multi-Scale Edge Conditioning
MSECNet consists of a backbone network and a multi-scale edge conditioning (MSEC) stream.
Gait Event Detection and Travel Distance Using Waist-Worn Accelerometers across a Range of Speeds: Automated Approach
The approach involves a combination of clinical observation, machine-learning-based step detection, and regression-based stride length prediction.
Exploring and Characterizing Large Language Models For Embedded System Development and Debugging
We leverage this finding to study how human programmers interact with these tools, and develop an human-AI based software engineering workflow for building embedded systems.
Class-Incremental Learning using Diffusion Model for Distillation and Replay
Experiments on the competitive benchmarks CIFAR100, ImageNet-Subset, and ImageNet demonstrate how this new approach can be used to further improve the performance of state-of-the-art methods for class-incremental learning on large scale datasets.
rPPG-MAE: Self-supervised Pre-training with Masked Autoencoders for Remote Physiological Measurement
However, they focus on the contrastive learning between samples, which neglect the inherent self-similar prior in physiological signals and seem to have a limited ability to cope with noisy.
A Simple yet Effective Self-Debiasing Framework for Transformer Models
In this way, the top-layer sentence representation will be trained to ignore the common biased features encoded by the low-layer sentence representation and focus on task-relevant unbiased features.
Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints
Traditional neural complex query answering (CQA) approaches mostly work on entity-centric KGs.
Optimizing Airbnb Search Journey with Multi-task Learning
The long and exploratory nature of the search journey, as well as the need to balance both guest and host preferences, present unique challenges for Airbnb search ranking.
Large Language Models are Few-Shot Health Learners
Large language models (LLMs) can capture rich representations of concepts that are useful for real-world tasks.
CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering
The task of zero-shot commonsense question answering evaluates models on their capacity to reason about general scenarios beyond those presented in specific datasets.
BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases
Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints.
StereoVAE: A lightweight stereo matching system through embedded GPUs
We present a lightweight system for stereo matching through embedded GPUs.
DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition
Implicit Discourse Relation Recognition (IDRR) is a sophisticated and challenging task to recognize the discourse relations between the arguments with the absence of discourse connectives.
Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees
In this paper, we present a comprehensive study on the convergence properties of Adam-family methods for nonsmooth optimization, especially in the training of nonsmooth neural networks.
Walk4Me: Telehealth Community Mobility Assessment, An Automated System for Early Diagnosis and Disease Progression
Our system achieves this by 1) enabling early diagnosis, 2) identifying early indicators of clinical severity, and 3) quantifying and tracking the progression of the disease across the ambulatory phase of the disease.
ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations
This paper aims to quantitatively evaluate the performance of ChatGPT, an interactive large language model, on inter-sentential relations such as temporal relations, causal relations, and discourse relations.
Recognizable Information Bottleneck
The recent PAC-Bayes IB uses information complexity instead of information compression to establish a connection with the mutual information generalization bound.
PIAT: Parameter Interpolation based Adversarial Training for Image Classification
Besides, we suggest to use the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the clean and adversarial examples.
NVAutoNet: Fast and Accurate 360$^{\circ}$ 3D Visual Perception For Self Driving
Achieving robust and real-time 3D perception is fundamental for autonomous vehicles.
BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological Measurements
As an example, perception occurs at different scales both spatially and temporally, suggesting that the extraction of salient visual information may be made more effective by paying attention to specific features at varying scales.
Motion Matters: Neural Motion Transfer for Better Camera Physiological Measurement
Our findings illustrate the usefulness of motion transfer as a data augmentation technique for improving the generalization of models for camera-based physiological sensing.
Facial Affect Recognition based on Transformer Encoder and Audiovisual Fusion for the ABAW5 Challenge
In this paper, we present our solutions for the 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW), which includes four sub-challenges of Valence-Arousal (VA) Estimation, Expression (Expr) Classification, Action Unit (AU) Detection and Emotional Reaction Intensity (ERI) Estimation.
Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning
We construct a large-scale unpaired HDR-LDR video dataset to facilitate the unsupervised training process for video tone mapping.
X-ray Spectral Estimation using Dictionary Learning
As computational tools for X-ray computed tomography (CT) become more quantitatively accurate, knowledge of the source-detector spectral response is critical for quantitative system-independent reconstruction and material characterization capabilities.
Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing
In this paper, we investigate three key factors (i. e., inputs, pre-training, and finetuning) in ViT for multimodal FAS with RGB, Infrared (IR), and Depth.
Cross-domain Random Pre-training with Prototypes for Reinforcement Learning
CRPTpro significantly outperforms the next best Proto-RL(C) on 11/12 cross-domain downstream tasks with only 54\% wall-clock pre-training time, exhibiting state-of-the-art pre-training performance with greatly improved pre-training efficiency.
MMPD: Multi-Domain Mobile Video Physiology Dataset
Second, most datasets are relatively small and therefore are limited in diversity, both in appearance (e. g., skin tone), behaviors (e. g., motion) and environment (e. g., lighting conditions).
Online Nonstochastic Control with Adversarial and Static Constraints
This subroutine also achieves the state-of-the-art regret and constraint violation bounds for constrained online convex optimization problems, which is of independent interest.
Feature Selection: Key to Enhance Node Classification with Graph Neural Networks
Graphs help to define the relationships between entities in the data.
Ranked #1 on
Node Classification
on twitch-gamers
C2ST: Cross-Modal Contextualized Sequence Transduction for Continuous Sign Language Recognition
In this paper, we propose a Cross-modal Contextualized Sequence Transduction (C2ST) for CSLR, which effectively incorporates the knowledge of gloss sequence into the process of video representation learning and sequence transduction.
Progressive Neighbor Consistency Mining for Correspondence Pruning
In the end, we develop a Neighbor Consistency Mining Network (NCMNet) for accurately recovering camera poses and identifying inliers.
Scalable and Sample Efficient Distributed Policy Gradient Algorithms in Multi-Agent Networked Systems
The proposed algorithm is distributed in two aspects: (i) the learned policy is a distributed policy that maps a local state of an agent to its local action and (ii) the learning/training is distributed, during which each agent updates its policy based on its own and neighbors' information.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
On the Discredibility of Membership Inference Attacks
We argue that current membership inference attacks can identify memorized subpopulations, but they cannot reliably identify which exact sample in the subpopulation was used during the training.
Efficient stereo matching on embedded GPUs with zero-means cross correlation
By combining this technique with the domain transformation (DT) algorithm, our system show real-time processing speed of 32 fps, on a Jetson Tx2 GPU for 1, 280x384 pixel images with a maximum disparity of 128.
Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraints
This paper studies the problem of stochastic continuum-armed bandit with constraints (SCBwC), where we optimize a black-box reward function $f(x)$ subject to a black-box constraint function $g(x)\leq 0$ over a continuous space $\mathcal X$.
Federated Learning Hyper-Parameter Tuning from a System Perspective
In this paper, we propose FedTune, an automatic FL hyper-parameter tuning algorithm tailored to applications' diverse system requirements in FL training.
FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery
Understanding users' intentions in e-commerce platforms requires commonsense knowledge.
Quantifying the Impact of Label Noise on Federated Learning
Federated Learning (FL) is a distributed machine learning paradigm where clients collaboratively train a model using their local (human-generated) datasets.
Getting the Most out of Simile Recognition
Simile recognition involves two subtasks: simile sentence classification that discriminates whether a sentence contains simile, and simile component extraction that locates the corresponding objects (i. e., tenors and vehicles).
Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform
However, the performance of the hyperbolic KG embedding models for non-transitive relations is still unpromising, while the complex hyperbolic embeddings do not deal with multi-relations.
GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalization
We envision our multi-year datasets can support the ML community in developing generalizable longitudinal behavior modeling algorithms.
Client Selection in Federated Learning: Principles, Challenges, and Opportunities
As a privacy-preserving paradigm for training Machine Learning (ML) models, Federated Learning (FL) has received tremendous attention from both industry and academia.
Opportunistic Episodic Reinforcement Learning
In this paper, we propose and study opportunistic reinforcement learning - a new variant of reinforcement learning problems where the regret of selecting a suboptimal action varies under an external environmental condition known as the variation factor.
Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance
Explainability plays an increasingly important role in machine learning.
Self-Supervised Learning via Maximum Entropy Coding
To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the learned representation is less biased and thus generalizes better to unseen downstream tasks.
GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs
First, unlike previous methods, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning.
Not All Neighbors are Friendly: Learning to Choose Hop Features to Improve Node Classification
With extensive experiments, we show that our proposed model outperforms the state-of-the-art GNN models with remarkable improvements up to 27. 8%.
MMTSA: Multimodal Temporal Segment Attention Network for Efficient Human Activity Recognition
The efficiency evaluation on an edge device showed that MMTSA achieved significantly better accuracy, lower computational load, and lower inference latency than SOTA methods.
ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
In this paper, we present ByteTransformer, a high-performance transformer boosted for variable-length inputs.
SimPer: Simple Self-Supervised Learning of Periodic Targets
From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes.
rPPG-Toolbox: Deep Remote PPG Toolbox
Camera-based physiological measurement is a fast growing field of computer vision.
Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation
The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism.
Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation
Second, we experimentally observe and verify the edge enhancement and suppression behavior.
Ranked #3 on
3D Part Segmentation
on ShapeNet-Part
Rethinking Efficiency and Redundancy in Training Large-scale Graphs
Thereby, we propose to drop redundancy and improve efficiency of training large-scale graphs with GNNs, by rethinking the inherent characteristics in a graph.
A Variance-Reduced Stochastic Gradient Tracking Algorithm for Decentralized Optimization with Orthogonality Constraints
Decentralized optimization with orthogonality constraints is found widely in scientific computing and data science.
Incoporating Weighted Board Learning System for Accurate Occupational Pneumoconiosis Staging
Occupational pneumoconiosis (OP) staging is a vital task concerning the lung healthy of a subject.
A high-resolution dynamical view on momentum methods for over-parameterized neural networks
Due to the simplicity and efficiency of the first-order gradient method, it has been widely used in training neural networks.
BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation
These brain-inspired AI models have been effectively validated on various supervised, unsupervised, and reinforcement learning tasks, and they can be used to enable AI models to be with multiple brain-inspired cognitive functions.
Brain-inspired Graph Spiking Neural Networks for Commonsense Knowledge Representation and Reasoning
For the fields of neuroscience and cognitive science, the work in this paper provided the foundation of computational modeling for further exploration of the way the human brain represents commonsense knowledge.
Enhancing Local Feature Learning Using Diffusion for 3D Point Cloud Understanding
Learning point clouds is challenging due to the lack of connectivity information, i. e., edges.
Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution
Modeling the local surface geometry is challenging in 3D point cloud understanding due to the lack of connectivity information.
Cross-Silo Federated Learning: Challenges and Opportunities
Federated learning (FL) is an emerging technology that enables the training of machine learning models from multiple clients while keeping the data distributed and private.
FedSSO: A Federated Server-Side Second-Order Optimization Algorithm
In this work, we propose FedSSO, a server-side second-order optimization method for federated learning (FL).
Boosting Graph Structure Learning with Dummy Nodes
We extend graph kernels and graph neural networks with dummy nodes and conduct experiments on graph classification and subgraph isomorphism matching tasks.
A Multi-task Framework for Infrared Small Target Detection and Segmentation
First, with the use of UNet as the backbone to maintain resolution and semantic information, our model can achieve a higher detection accuracy than other state-of-the-art methods by attaching a simple anchor-free head.
SCAMPS: Synthetics for Camera Measurement of Physiological Signals
The use of cameras and computational algorithms for noninvasive, low-cost and scalable measurement of physiological (e. g., cardiac and pulmonary) vital signs is very attractive.
Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment
To understand the exploration, exploitation, and engagement in these systems, we propose a new model, called MAB-A where "A" stands for abandonment and the abandonment probability depends on the current recommended item and the user's past experience (called state).
An Inexact Augmented Lagrangian Algorithm for Training Leaky ReLU Neural Network with Group Sparsity
Moreover, we show the relationship between the new model and the original problem.
Selective clustering ensemble based on kappa and F-score
Clustering ensemble has an impressive performance in improving the accuracy and robustness of partition results and has received much attention in recent years.
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
This challenge includes three tracks.
A Convergence Analysis of Nesterov's Accelerated Gradient Method in Training Deep Linear Neural Networks
To the best of our knowledge, this is the first theoretical guarantee for the convergence of NAG to the global minimum in training deep neural networks.
Ethereum Fraud Detection with Heterogeneous Graph Neural Networks
Specifically, we evaluated the model performance of representative homogeneous GNN models which consider single-type nodes and edges and heterogeneous GNN models which support different types of nodes and edges.
Federated Remote Physiological Measurement with Imperfect Data
The growing need for technology that supports remote healthcare is being acutely highlighted by an aging population and the COVID-19 pandemic.
User-Level Membership Inference Attack against Metric Embedding Learning
In this paper, we develop a user-level MI attack where the goal is to find if any sample from the target user has been used during training even when no exact training sample is available to the attacker.
An Efficient Subpopulation-based Membership Inference Attack
The intuition is that the model response should not be significantly different between the target sample and its subpopulation if it was not a training sample.
Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention
We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds.
Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach
Penetration Testing plays a critical role in evaluating the security of a target network by emulating real active adversaries.
Multi-Objective Reinforcement Learning
reinforcement-learning
Survey on Graph Neural Network Acceleration: An Algorithmic Perspective
Next, we provide comparisons from aspects of the efficiency and characteristics of these methods.
MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing
Camera-based contactless photoplethysmography refers to a set of popular techniques for contactless physiological measurement.
Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function
In this paper, we focus on the decentralized optimization problem over the Stiefel manifold, which is defined on a connected network of $d$ agents.
Diaformer: Automatic Diagnosis via Symptoms Sequence Generation
Detailed analysis on symptom inquiry prediction demonstrates that the potential of applying symptoms sequence generation for automatic diagnosis.
Graph Convolutional Networks with Dual Message Passing for Subgraph Isomorphism Counting and Matching
Based on this observation, we propose dual message passing neural networks (DMPNNs) to enhance the substructure representation learning in an asynchronous way for subgraph isomorphism counting and matching as well as unsupervised node classification.
KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation
Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently.
Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
RDIM and region fitting do not require extra running time and these three steps can be well integrated into other attacks.
Leaping Through Time with Gradient-based Adaptation for Recommendation
Different from the popular recurrent modeling approach, we propose a new solution named LeapRec to the temporal dynamic problem by using trajectory-based meta-learning to model time dependencies.
MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification
We propose MASTAF, a Model-Agnostic Spatio-Temporal Attention Fusion network for few-shot video classification.
Consistency Regularization for Deep Face Anti-Spoofing
Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems.
CLARA: A Constrained Reinforcement Learning Based Resource Allocation Framework for Network Slicing
Network slicing is proposed as a promising solution for resource utilization in 5G and future networks to address this dire need.
Simplifying approach to Node Classification in Graph Neural Networks
In this work, we decouple the node feature aggregation step and depth of graph neural network, and empirically analyze how different aggregated features play a role in prediction performance.
RGB Camera-based Physiological Sensing: Challenges and Future Directions
Numerous real-world applications have been driven by the recent algorithmic advancement of artificial intelligence (AI).
Natural Image Reconstruction from fMRI using Deep Learning: A Survey
With the advent of brain imaging techniques and machine learning tools, much effort has been devoted to building computational models to capture the encoding of visual information in the human brain.
Synthetic Data for Multi-Parameter Camera-Based Physiological Sensing
We present systematic experiments showing how physiologically-grounded synthetic data can be used in training camera-based multi-parameter cardiopulmonary sensing.
EfficientPhys: Enabling Simple, Fast and Accurate Camera-Based Vitals Measurement
Camera-based physiological measurement is a growing field with neural models providing state-the-art-performance.
Face Detection
Photoplethysmography (PPG) heart rate estimation
Spectroscopy Approaches for Food Safety Applications: Improving Data Efficiency Using Active Learning and Semi-Supervised Learning
The past decade witnesses a rapid development in the measurement and monitoring technologies for food science.
Learning Higher-Order Dynamics in Video-Based Cardiac Measurement
Recent developments in camera-based vital sign measurement have shown that cardiac measurements can be recovered with impressive accuracy from videos; however, most of the research has focused on extracting summary statistics such as heart rate.
FedTune: Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective
Federated learning (FL) hyper-parameters significantly affect the training overheads in terms of computation time, transmission time, computation load, and transmission load.
Spatio-Temporal-Categorical Graph Neural Networks for Fine-Grained Multi-Incident Co-Prediction
Forecasting incident occurrences (e. g. crime, EMS, traffic accident) is a crucial task for emergency service providers and transportation agencies in performing response time optimization and dynamic fleet management.
EfficientPhys: Enabling Simple, Fast, and Accurate Camera-Based Vitals Measurement
Camera-based physiological measurement is a growing field with neural models providing state-the-art-performance.
Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective
Federated Learning (FL) is a distributed model training paradigm that preserves clients' data privacy.
Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph
To address this challenge, we propose dictionary-based heterogeneous graph neural network (DHGNet) that effectively handles the heterogeneity of DHG by two-step aggregations, which are word-level and language-level aggregations.
GNNSampler: Bridging the Gap between Sampling Algorithms of GNN and Hardware
Extensive experiments show that our method is universal to mainstream sampling algorithms and helps significantly reduce the training time, especially in large-scale graphs.
AGNet: Weighing Black Holes with Deep Learning
We find a 1$\sigma$ scatter of 0. 37 dex between the predicted SMBH mass and the fiducial virial mass estimate based on SDSS single-epoch spectra, which is comparable to the systematic uncertainty in the virial mass estimate.
MMChat: Multi-Modal Chat Dataset on Social Media
To better investigate this issue, we manually annotate 100K dialogues from MMChat and further filter the corpus accordingly, which yields MMChat-hf.
Provable Convergence of Nesterov's Accelerated Gradient Method for Over-Parameterized Neural Networks
Despite the fact that the objective function is non-convex and non-smooth, we show that NAG converges to a global minimum at a non-asymptotic linear rate $(1-\Theta(1/\sqrt{\kappa}))^t$, where $\kappa > 1$ is the condition number of a gram matrix and $t$ is the number of the iterations.
iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis
We introduce a new dataset for the emotional artificial intelligence research: identity-free video dataset for Micro-Gesture Understanding and Emotion analysis (iMiGUE).
Early Mobility Recognition for Intensive Care Unit Patients Using Accelerometers
In this paper, we target a new healthcare application of human activity recognition, early mobility recognition for Intensive Care Unit(ICU) patients.
Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation
A well-known limitation in pretrain-finetune paradigm lies in its inflexibility caused by the one-size-fits-all vocabulary.
Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning
In this study, we define the spectral graph convolutional network with the high-order dynamic Chebyshev approximation (HDGCN), which augments the multi-hop graph reasoning by fusing messages aggregated from direct and long-term dependencies into one convolutional layer.
A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes
This paper presents the first model-free, simulator-free reinforcement learning algorithm for Constrained Markov Decision Processes (CMDPs) with sublinear regret and zero constraint violation.
Exploring Discourse Structures for Argument Impact Classification
Discourse relations among arguments reveal logical structures of a debate conversation.
Improving Graph Neural Networks with Simple Architecture Design
Combining these techniques, we present a simple and shallow model, Feature Selection Graph Neural Network (FSGNN), and show empirically that the proposed model outperforms other state of the art GNN models and achieves up to 64% improvements in accuracy on node classification tasks.
Ranked #2 on
Node Classification
on Cornell
FDDH: Fast Discriminative Discrete Hashing for Large-Scale Cross-Modal Retrieval
To tackle these issues, we formulate the learning of similarity-preserving hash codes in terms of orthogonally rotating the semantic data so as to minimize the quantization loss of mapping such data to hamming space, and propose an efficient Fast Discriminative Discrete Hashing (FDDH) approach for large-scale cross-modal retrieval.
Gait Characterization in Duchenne Muscular Dystrophy (DMD) Using a Single-Sensor Accelerometer: Classical Machine Learning and Deep Learning Approaches
We extracted temporospatial gait clinical features (CFs) and applied multiple machine learning (ML) approaches to differentiate between DMD and TD children using extracted temporospatial gait CFs and raw data.
Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective
We analyze the impact of various factors in deep ensembles and demonstrate the root cause of the trade-off.
FastAdaBelief: Improving Convergence Rate for Belief-based Adaptive Optimizers by Exploiting Strong Convexity
%on how to exploit strong convexity to further improve the convergence rate of AdaBelief.
Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy
A practical long-term tracker typically contains three key properties, i. e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism.
A Survey on Federated Learning and its Applications for Accelerating Industrial Internet of Things
Federated learning (FL) brings collaborative intelligence into industries without centralized training data to accelerate the process of Industry 4. 0 on the edge computing level.
ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities
After conceptualization with Probase, a selectional preference based concept-instance relational knowledge base, our concept graph contains 15 million conceptualized eventualities and 224 million edges between them.
Learning to Filter: Siamese Relation Network for Robust Tracking
RD performs in a meta-learning way to obtain a learning ability to filter the distractors from the background while RM aims to effectively integrate the proposed RD into the Siamese framework to generate accurate tracking result.
Forecasting Ambulance Demand with Profiled Human Mobility via Heterogeneous Multi-Graph Neural Networks
Forecasting regional ambulance demand plays a fundamental part in dynamic fleet allocation and redeployment.
An Overview of Human Activity Recognition Using Wearable Sensors: Healthcare and Artificial Intelligence
With the rapid development of the internet of things (IoT) and artificial intelligence (AI) technologies, human activity recognition (HAR) has been applied in a variety of domains such as security and surveillance, human-robot interaction, and entertainment.
No frame left behind: Full Video Action Recognition
A common heuristic is uniformly sampling a small number of video frames and using these to recognize the action.
Balanced softmax cross-entropy for incremental learning with and without memory
When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old classes while learning the new ones.
Sampling methods for efficient training of graph convolutional networks: A survey
Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations.
Deep Manifold Learning for Dynamic MR Imaging
The nonlinear manifold is designed to characterize the temporal correlation of dynamic signals.
Higher-order topological superconductors based on weak topological insulators
High-order topological phases host robust boundary states at the boundary of the boundary, which can be interpreted from their boundary topology.
Superconductivity Mesoscale and Nanoscale Physics Materials Science
DST: Data Selection and joint Training for Learning with Noisy Labels
In this paper, we propose a Data Selection and joint Training (DST) method to automatically select training samples with accurate annotations.
An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints
Thus, the overall computational complexity of our algorithm is similar to that of the linear UCB for unconstrained stochastic linear bandits.
Learning adaptive differential evolution algorithm from optimization experiences by policy gradient
A reinforcement learning algorithm, named policy gradient, is applied to learn an agent (i. e. parameter controller) that can provide the control parameters of a proposed differential evolution adaptively during the search procedure.
Spectrum Sharing for 6G Integrated Satellite-Terrestrial Communication Networks Based on NOMA and Cognitive Radio
ISTCN aims to provide high speed and pervasive network services by integrating broadband terrestrial mobile networks with satellite communication networks.
SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices
In this work, we demonstrate state-of-the-art latency and accuracy for on-device super-resolution using a novel hybrid architecture called SplitSR and a novel lightweight residual block called SplitSRBlock.
Generalized Image Reconstruction over T-Algebra
We also show in our experiments that the performance of TPCA increases when the order of compounded pixels increases.
Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans
The experimental results show that our automatically searched models (CovidNet3D) outperform the baseline human-designed models on the three datasets with tens of times smaller model size and higher accuracy.
An Unsupervised Learning Method with Convolutional Auto-Encoder for Vessel Trajectory Similarity Computation
Based on the massive vessel trajectories collected, the CAE can learn the low-dimensional representations of informative trajectory images in an unsupervised manner.
OAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space
Specifically, we employ orthogonal low-rank embedding in the latent space to disentangle the features in the latent space using mutual class information.
Annotation-efficient deep learning for automatic medical image segmentation
Automatic medical image segmentation plays a critical role in scientific research and medical care.
Getting Ready for LISA: The Data, Support and Preparation Needed to Maximize US Participation in Space-Based Gravitational Wave Science
Among our findings: LISA science productivity is greatly enhanced by a full-featured US science center and an open access data model.
Instrumentation and Methods for Astrophysics High Energy Astrophysical Phenomena General Relativity and Quantum Cosmology
MedWriter: Knowledge-Aware Medical Text Generation
To exploit the domain knowledge to guarantee the correctness of generated text has been a hot topic in recent years, especially for high professional domains such as medical.
AGNet: Weighing Black Holes with Machine Learning
Supermassive black holes (SMBHs) are ubiquitously found at the centers of most galaxies.
Multi-task MR Imaging with Iterative Teacher Forcing and Re-weighted Deep Learning
Noises, artifacts, and loss of information caused by the magnetic resonance (MR) reconstruction may compromise the final performance of the downstream applications.
Soft-Median Choice: An Automatic Feature Smoothing Method for Sound Event Detection
In Sound Event Detection (SED) systems, the lengths of median filters for post-processing have never been optimized during training due to several problems.
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
