Search Results for author:
Found 230 papers, 61 papers with code
Cold Start Problem For Automated Live Video Comments
These comments have become a determining factor in the popularity of the videos.
A Meta-framework for Spatiotemporal Quantity Extraction from Text
News events are often associated with quantities (e. g., the number of COVID-19 patients or the number of arrests in a protest), and it is often important to extract their type, time, and location from unstructured text in order to analyze these quantity events.
A Double-Norm Aggregated Tensor Latent Factorization Model for Temporal-Aware Traffic Speed Imputation
In intelligent transportation systems (ITS), traffic management departments rely on sensors, cameras, and GPS devices to collect real-time traffic data.
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
MetaDSE: A Few-shot Meta-learning Framework for Cross-workload CPU Design Space Exploration
Cross-workload design space exploration (DSE) is crucial in CPU architecture design.
Latent Tensor Factorization with Nonlinear PID Control for Missing Data Recovery in Non-Intrusive Load Monitoring
Non-Intrusive Load Monitoring (NILM) has emerged as a key smart grid technology, identifying electrical device and providing detailed energy consumption data for precise demand response management.
NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains.
Cross-Domain Few-Shot
Cross-Domain Few-Shot Object Detection
+3
Academic Network Representation via Prediction-Sampling Incorporated Tensor Factorization
Accurate representation to an academic network is of great significance to academic relationship mining like predicting scientific impact.
3DBonsai: Structure-Aware Bonsai Modeling Using Conditioned 3D Gaussian Splatting
Recent advancements in text-to-3D generation have shown remarkable results by leveraging 3D priors in combination with 2D diffusion.
ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation
Source-Free Domain Adaptation (SFDA) aims to train a target model without source data, and the key is to generate pseudo-labels using a pre-trained source model.
Adaptive Stochastic Gradient Descents on Manifolds with an Application on Weighted Low-Rank Approximation
We prove a convergence theorem for stochastic gradient descents on manifolds with adaptive learning rate and apply it to the weighted low-rank approximation problem.
Water Quality Data Imputation via A Fast Latent Factorization of Tensors with PID-based Optimizer
Water quality data can supply a substantial decision support for water resources utilization and pollution prevention.
SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic
This framework aligns with the feature extraction paradigm in RGB-based methods, enabling direct evaluation of RGB-based models on skeleton-based benchmarks.
Group Activity Recognition
Temporal Group Activity Localization
StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition
With the rise of real-world human-AI interaction applications, such as AI assistants, the need for Streaming Video Dialogue is critical.
SpecServe: Efficient and SLO-Aware Large Language Model Serving with Adaptive Speculative Decoding
Large Language Model (LLM) services often face challenges in achieving low inference latency and meeting Service Level Objectives (SLOs) under dynamic request patterns.
Learning-Augmented Frequent Directions
Our first contribution is a learning-augmented variant of the Misra-Gries algorithm which improves upon the error of learned CountMin and learned CountSketch and achieves the state-of-the-art performance of randomized algorithms (Aamand et al., NeurIPS'23) with a simpler, deterministic algorithm.
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation
The cross-modal 3D retrieval task aims to achieve mutual matching between text descriptions and 3D shapes.
Flow-based Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems
Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems is a fundamental yet challenging problem in many fields of science and engineering.
Weighted Low-rank Approximation via Stochastic Gradient Descent on Manifolds
We solve a regularized weighted low-rank approximation problem by a stochastic gradient descent on a manifold.
Dense Object Detection Based on De-homogenized Queries
This paper focuses on the challenging task of dense object detection.
Multiscale style transfer based on a Laplacian pyramid for traditional Chinese painting
Style transfer is adopted to synthesize appealing stylized images that preserve the structure of a content image but carry the pattern of a style image.
OneForecast: A Universal Framework for Global and Regional Weather Forecasting
Accurate weather forecasts are important for disaster prevention, agricultural planning, and water resource management.
Retrievals Can Be Detrimental: A Contrastive Backdoor Attack Paradigm on Retrieval-Augmented Diffusion Models
Subsequently, a malicious variant of contrastive learning is adopted to inject backdoors into the retriever, which builds shortcuts from triggers to the toxicity surrogates.
Benchmarking Large Language Models via Random Variables
LLMs must fully understand the problem-solving process for the original problem to correctly answer RV questions with various combinations of variable values.
CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness
This paper first defines two communication delay settings in MARL and emphasizes their harm to collaboration.
Improved Forecasts of Global Extreme Marine Heatwaves Through a Physics-guided Data-driven Approach
Our framework significantly improves the forecast ability of extreme MHWs through two specially designed modules inspired by numerical models: a coupler and a probabilistic data argumentation.
AEPHORA: AI/ML-Based Energy-Efficient Proactive Handover and Resource Allocation
Future Vehicle-to-Everything (V2X) scenarios require high-speed, low-latency, and ultra-reliable communication services, particularly for applications such as autonomous driving and in-vehicle infotainment.
Know Unreported Roadway Incidents in Real-time: A Deep Learning Framework for Early Traffic Anomaly Detection
Our framework does not focus on stacking or tweaking various deep learning models; instead, it focuses on model design and training strategies to improve early detection performance.
Optimal Bounds for Private Minimum Spanning Trees via Input Perturbation
Given a graph $G = (V, E, \vec{W})$ where $V$ is a set of $n$ vertices, $E$ is a set of $m$ undirected edges, and $ \vec{W} \in \mathbb{R}^{|E|} $ is an edge-weight vector, our goal is to publish an approximate MST under edge-weight differential privacy, as introduced by Sealfon in PODS 2016, where $V$ and $E$ are considered public and the weight vector is private.
DIR: Retrieval-Augmented Image Captioning with Comprehensive Understanding
However, current methods face two key challenges: (1) image features used for retrieval are often optimized based on ground-truth (GT) captions, which represent the image from a specific perspective and are influenced by annotator biases, and (2) they underutilize the full potential of retrieved text, typically relying on raw captions or parsed objects, which fail to capture the full semantic richness of the data.
Fast High-Quality Enhanced Imaging Algorithm for Layered Dielectric Targets Based on MMW MIMO-SAR System
Millimeter-wave (MMW) multiple-input multiple-output synthetic aperture radar (MIMO-SAR) system is a technology that can achieve high resolution, high frame rate, and all-weather imaging and has received extensive attention in the non-destructive testing and internal imaging applications of layered dielectric targets.
DeepContext: A Context-aware, Cross-platform, and Cross-framework Tool for Performance Profiling and Analysis of Deep Learning Workloads
This paper introduces DeepContext, a novel profiler that links program contexts across high-level Python code, deep learning frameworks, underlying libraries written in C/C++, as well as device code executed on GPUs.
Reliable and Compact Graph Fine-tuning via GraphSparse Prompting
To address this issue, we propose exploiting sparse representation theory for graph prompting and present Graph Sparse Prompting (GSP).
Privacy-Preserving Federated Learning via Dataset Distillation
We hold that users are only willing and need to share the essential knowledge to the training task to obtain the FL model with high accuracy.
Multi-objective Optimization in CPU Design Space Exploration: Attention is All You Need
This approach enhances both the prediction accuracy and interpretability of the performance model.
Making Every Frame Matter: Continuous Video Understanding for Large Models via Adaptive State Modeling
Video understanding has become increasingly important with the rise of multi-modality applications.
Learning Graph Quantized Tokenizers
Graph Transformers (GTs) have recently emerged as leading models in geometric deep learning, outperforming Graph Neural Networks (GNNs) in various graph learning tasks.
Diversified and Adaptive Negative Sampling on Knowledge Graphs
In reality, since knowledge graphs are sparse and incomplete, negative triplets often lack explicit labels, and thus they are often obtained from various sampling strategies (eg: randomly replacing an entity in a positive triplet).
LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management
The expanding context windows in large language models (LLMs) have greatly enhanced their capabilities in various applications, but they also introduce significant challenges in maintaining low latency, particularly in Time to First Token (TTFT).
Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
To this end, we establish a causal framework for ST predictions, termed CaPaint, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process.
Training Data Attribution: Was Your Model Secretly Trained On Data Created By Mine?
Our experiments demonstrate that our method achieves an accuracy of over 80\% in identifying the source of a suspicious model's training data, without interfering the original training or generation process of the source model.
CoAst: Validation-Free Contribution Assessment for Federated Learning based on Cross-Round Valuation
Existing validation-free methods assess the contribution based on the parameters and gradients of local models and the global model in a single training round, which is easily compromised by the stochasticity of model training.
Flow Matching for Optimal Reaction Coordinates of Biomolecular System
We present flow matching for reaction coordinates (FMRC), a novel deep learning algorithm designed to identify optimal reaction coordinates (RC) in biomolecular reversible dynamics.
Web Service QoS Prediction via Extended Canonical Polyadic-based Tensor Network
Experiments are conducted on two public dynamic QoS data, and the results show that compared with state-of-the-art QoS prediction models, the ECTN obtains higher prediction accuracy.
Gradient-free variational learning with conditional mixture networks
Previous work shows that fast variational methods can reduce the compute requirements of Bayesian methods by eliminating the need for gradient computation or sampling, but are often limited to simple models.
High-Dimensional Sparse Data Low-rank Representation via Accelerated Asynchronous Parallel Stochastic Gradient Descent
Data characterized by high dimensionality and sparsity are commonly used to describe real-world node interactions.
Optical Semantic Communication through Multimode Fiber: From Symbol Transmission to Sentiment Analysis
By encoding semantically similar symbols to adjacent frequencies, the system's noise tolerance is effectively improved, facilitating accurate sentiment analysis.
FunEditor: Achieving Complex Image Edits via Function Aggregation with Diffusion Models
This approach enables complex editing tasks, such as object movement, by aggregating multiple functions and applying them simultaneously to specific areas.
Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm
Unexpected stimuli induce "error" or "surprise" signals in the brain.
Dual-Channel Latent Factor Analysis Enhanced Graph Contrastive Learning for Recommendation
Graph Neural Networks (GNNs) are powerful learning methods for recommender systems owing to their robustness in handling complicated user-item interactions.
Real-time Event Recognition of Long-distance Distributed Vibration Sensing with Knowledge Distillation and Hardware Acceleration
The proposed method greatly enhances the efficiency of vibration pattern recognition, promoting the use of DVS as a smart IoT system.
Spatial-temporal Graph Convolutional Networks with Diversified Transformation for Dynamic Graph Representation Learning
Dynamic graphs (DG) are often used to describe evolving interactions between nodes in real-world applications.
A Probabilistic Approach for Queue Length Estimation Using License Plate Recognition Data: Considering Overtaking in Multi-lane Scenarios
Eventually, to leverage the LPR data sufficiently, we extend our approach to multi-lane scenarios, where the problem can be converted to a weighted general exact coverage problem and solved by a backtracking algorithm with heuristics.
Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning
Forensic pathology is critical in determining the cause and manner of death through post-mortem examinations, both macroscopic and microscopic.
CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks
Transferable targeted adversarial attacks aim to mislead models into outputting adversary-specified predictions in black-box scenarios.
$\text{Memory}^3$: Language Modeling with Explicit Memory
The model is named $\text{Memory}^3$, since explicit memory is the third form of memory in LLMs after implicit memory (model parameters) and working memory (context key-values).
A Unified Graph Selective Prompt Learning for Graph Neural Networks
The proposed GSPF integrates the prompt learning on both graph node and edge together, which thus provides a unified prompt model for the graph data.
One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
In this paper, we reveal that VLP models are also vulnerable to the instance-agnostic universal adversarial perturbation (UAP).
GLADformer: A Mixed Perspective for Graph-level Anomaly Detection
However, current methods are constrained by their receptive fields, struggling to learn global features within the graphs.
GI-NAS: Boosting Gradient Inversion Attacks through Adaptive Neural Architecture Search
In this paper, we further exploit such implicit prior knowledge by proposing Gradient Inversion via Neural Architecture Search (GI-NAS), which adaptively searches the network and captures the implicit priors behind neural architectures.
ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks
The challenge of effectively learning inter-series correlations for multivariate time series forecasting remains a substantial and unresolved problem.
Ranked #51 on
Time Series Forecasting
on ETTh1 (336) Multivariate
BeamVQ: Aligning Space-Time Forecasting Model via Self-training on Physics-aware Metrics
Data-driven deep learning has emerged as the new paradigm to model complex physical space-time systems.
Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
First, we raise the scaling law between batch sizes and optimal learning rates in the sign of gradient case, in which we prove that the optimal learning rate first rises and then falls as the batch size increases.
All Nodes are created Not Equal: Node-Specific Layer Aggregation and Filtration for GNN
This assumption often poses challenges for many GNNs working with heterophilic graphs.
COM3D: Leveraging Cross-View Correspondence and Cross-Modal Mining for 3D Retrieval
To address this issue, we propose COM3D, making the first attempt to exploit the cross-view correspondence and cross-modal mining to enhance the retrieval performance.
Towards Consistent Object Detection via LiDAR-Camera Synergy
The study also explored how the proposed consistency detection method performs on images when the calibration parameters between images and point clouds are disturbed, compared to existing post-processing methods.
emrQA-msquad: A Medical Dataset Structured with the SQuAD V2.0 Framework, Enriched with emrQA Medical Information
Machine Reading Comprehension (MRC) holds a pivotal role in shaping Medical Question Answering Systems (QAS) and transforming the landscape of accessing and applying medical information.
Fast Gradient Computation for Gromov-Wasserstein Distance
In this way, the original computational bottleneck is broken and the new entropic solution can be obtained with total quadratic time, which is almost optimal complexity.
DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement
We present Dive Into the BoundarieS (DIBS), a novel pretraining framework for dense video captioning (DVC), that elaborates on improving the quality of the generated event captions and their associated pseudo event boundaries from unlabeled videos.
SLFNet: Generating Semantic Logic Forms from Natural Language Using Semantic Probability Graphs
Building natural language interfaces typically uses a semantic parser to parse the user's natural language and convert it into structured \textbf{S}emantic \textbf{L}ogic \textbf{F}orms (SLFs).
VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections
Therefore, mini-batch training for graph transformers is a promising direction, but limited samples in each mini-batch can not support effective dense attention to encode informative representations.
LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images
Most importantly, the LUWA dataset provides an underexplored opportunity for vision and learning communities and complements existing image classification problems on common objects.
Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance
This paper proposes a two-stage framework named ST-PAD for spatio-temporal fluid dynamics modeling in the field of earth sciences, aiming to achieve high-precision simulation and prediction of fluid dynamics through spatio-temporal physics awareness and parameter diffusion guidance.
Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference
Finally, we employ the diffusion model to train and infer various gestures.
Learning Hierarchical Color Guidance for Depth Map Super-Resolution
On the one hand, the low-level detail embedding module is designed to supplement high-frequency color information of depth features in a residual mask manner at the low-level stages.
A Survey of Learned Indexes for the Multi-dimensional Space
We present a taxonomy that classifies and categorizes each learned multi-dimensional index, and survey the existing literature on learned multi-dimensional indexes according to this taxonomy.
DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting
In this paper, we introduce for the first time the concept of spatio-temporal data dynamic sparse training and are committed to adaptively, dynamically filtering important sensor distributions.
CaT-GNN: Enhancing Credit Card Fraud Detection via Causal Temporal Graph Neural Networks
Credit card fraud poses a significant threat to the economy.
NeuralDiffuser: Neuroscience-inspired Diffusion Guidance for fMRI Visual Reconstruction
Reconstructing visual stimuli from functional Magnetic Resonance Imaging fMRI enables fine-grained retrieval of brain activity.
Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts
In this paper, we address the issue of modeling and estimating changes in the state of the spatio-temporal dynamical systems based on a sequence of observations like video frames.
Coronary CTA and Quantitative Cardiac CT Perfusion (CCTP) in Coronary Artery Disease
CCTA in conjunction with a new automated quantitative CCTP approach can augment the interpretation of CAD, enabling the distinction of ischemia due to obstructive lesions and MVD.
CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
For each of these CRUD categories, we have developed comprehensive datasets to evaluate the performance of RAG systems.
AI prediction of cardiovascular events using opportunistic epicardial adipose tissue assessments from CT calcium score
Background: Recent studies have used basic epicardial adipose tissue (EAT) assessments (e. g., volume and mean HU) to predict risk of atherosclerosis-related, major adverse cardiovascular events (MACE).
PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology
To address this, we introduce PathMMU, the largest and highest-quality expert-validated pathology benchmark for Large Multimodal Models (LMMs).
Pericoronary adipose tissue feature analysis in CT calcium score images with comparison to coronary CTA
Preliminarily, PCAT features can be assessed from three main coronary arteries in non-contrast CTCS images with performance characteristics that are at the very least comparable to CCTA.
EEG Based Generative Depression Discriminator
In the test, a segment of EEG signal was put into the two generators separately, if the relationship between the EEG signal and brain activity conforms to the characteristics of a certain category, then the signal generated by the generator of the corresponding category is more consistent with the original signal.
Energy based diffusion generator for efficient sampling of Boltzmann distributions
Sampling from Boltzmann distributions, particularly those tied to high-dimensional and complex energy functions, poses a significant challenge in many fields.
On Completeness of SDP-Based Barrier Certificate Synthesis over Unbounded Domains
Furthermore, motivated by this formulation, we introduce the definition of homogenized systems and propose a complete characterization of a family of non-polynomial barrier certificates with more expressive power.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Visual Question Answering (VQA)
on InfographicVQA
UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation
In response to this, we introduce UCMCTrack, a novel motion model-based tracker robust to camera movements.
Ranked #3 on
Multi-Object Tracking
on MOT17
Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community.
Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum
This detector includes a hybrid filtering module and a local environmental constraint module, the two modules are utilized to solve heterophily and label utilization problem respectively.
Multi-Scale and Multi-Modal Contrastive Learning Network for Biomedical Time Series
Multi-modal biomedical time series (MBTS) data offers a holistic view of the physiological state, holding significant importance in various bio-medical applications.
LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancement
In this paper, we proposed a novel fusion model for MOS prediction that combines supervised and unsupervised approaches.
A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations
After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0. 130 to 0. 903 and 0. 116 to 0. 877.
Efficient Pyramid Channel Attention Network for Pathological Myopia Recognition
Moreover, motivated by the recent pretraining-and-finetuning paradigm, we attempt to adapt pre-trained natural image models for PM recognition by freezing them and treating the EPCA and other attention modules as adapters.
Reaction coordinate flows for model reduction of molecular kinetics
In this work, we introduce a flow based machine learning approach, called reaction coordinate (RC) flow, for discovery of low-dimensional kinetic models of molecular systems.
Enhancing cardiovascular risk prediction through AI-enabled calcium-omics
We used a Cox model with elastic-net regularization on 2457 CT calcium score (CTCS) enriched for MACE events obtained from a large no-cost CLARIFY program (ClinicalTri-als. gov Identifier: NCT04075162).
RIS-assisted High-Speed Railway Integrated Sensing and Communication System
One technology that has the potential to improve wireless communications in years to come is integrated sensing and communication (ISAC).
MM-GEF: Multi-modal representation meet collaborative filtering
In modern e-commerce, item content features in various modalities offer accurate yet comprehensive information to recommender systems.
Real-time FPGA Implementation of CNN-based Distributed Fiber Optic Vibration Event Recognition Method
Utilizing optical fibers to detect and pinpoint vibrations, Distributed Optical Fiber Vibration Sensing (DVS) technology provides real-time monitoring and surveillance of wide-reaching areas.
AI-GOMS: Large AI-Driven Global Ocean Modeling System
Here, we present AI-GOMS, a large AI-driven global ocean modeling system, for accurate and efficient global ocean daily prediction.
An Intelligent Remote Sensing Image Quality Inspection System
Due to the inevitable presence of quality problems, quality inspection of remote sensing images is indeed an indispensable step between the acquisition and the application of them.
Cardiac CT perfusion imaging of pericoronary adipose tissue (PCAT) highlights potential confounds in coronary CTA
HU, blood flow, and radiomics were assessed over time.
Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback
Generating and editing a 3D scene guided by natural language poses a challenge, primarily due to the complexity of specifying the positional relations and volumetric changes within the 3D space.
PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction
In this paper, we investigate the challenge of spatio-temporal video prediction task, which involves generating future video frames based on historical spatio-temporal observation streams.
A Constrained BA Algorithm for Rate-Distortion and Distortion-Rate Functions
The Blahut-Arimoto (BA) algorithm has played a fundamental role in the numerical computation of rate-distortion (RD) functions.
Efficient Bayesian inference using physics-informed invertible neural networks for inverse problems
Simultaneously, the INN is designed to partition the parameter vector linked to the input physical field into two distinct components: the expansion coefficients representing the forward problem solution and the Gaussian latent noise.
Immune Defense: A Novel Adversarial Defense Mechanism for Preventing the Generation of Adversarial Examples
Therefore, we propose a novel adversarial defense mechanism, which is referred to as immune defense and is the example-based pre-defense.
Do We Really Need Complicated Model Architectures For Temporal Networks?
Recurrent neural network (RNN) and self-attention mechanism (SAM) are the de facto methods to extract spatial-temporal information for temporal graph learning.
IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning
We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks, including deep neural network (DNN) regression and neural operator learning (DeepONet).
A Closer Look at Few-shot Classification Again
Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples.
Vision Learners Meet Web Image-Text Pairs
In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data.
A Simple Framework for Text-Supervised Semantic Segmentation
LoDA and SimSeg jointly ameliorate a vanilla CLIP to produce impressive semantic segmentation results.
MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning
Learning effective motion features is an essential pursuit of video representation learning.
Online Handbook of Argumentation for AI: Volume 3
This volume contains revised versions of the papers selected for the third volume of the Online Handbook of Argumentation for AI (OHAAI).
An ADMM-Incorporated Latent Factorization of Tensors Method for QoS Prediction
We maintain the non-negativity of the model by constructing an augmented Lagrangian function with the ADMM optimization framework.
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs.
Track Targets by Dense Spatio-Temporal Position Encoding
Experiments on video multi-object tracking (MOT) and multi-object tracking and segmentation (MOTS) datasets demonstrate the effectiveness of the proposed DST position encoding.
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+2
Enhancing Spatiotemporal Prediction Model using Modular Design and Beyond
In this paper, a modular design is proposed, which decomposes spatiotemporal sequence model into two modules: a spatial encoder-decoder and a predictor.
FP8 Formats for Deep Learning
FP8 is a natural progression for accelerating deep learning training inference beyond the 16-bit formats common in modern processors.
A detail-enhanced sampling strategy in Hadamard single-pixel imaging
Hadamard single-pixel imaging (HSI) is an appealing imaging technique due to its features of low hardware complexity and industrial cost.
Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction
Limited labeled data increase the risk of distribution shift between test data and training data.
\b{eta}-Divergence-Based Latent Factorization of Tensors model for QoS prediction
A nonnegative latent factorization of tensors (NLFT) model can well model the temporal pattern hidden in nonnegative quality-of-service (QoS) data for predicting the unobserved ones with high accuracy.
Distinctive Image Captioning via CLIP Guided Group Optimization
Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions.
Dual Power Spectrum Manifold and Toeplitz HPD Manifold: Enhancement and Analysis for Matrix CFAR Detection
These advantages benefit from the geometry of the Toeplitz Hermitian positive definite (HPD) manifold $\mathcal{M}_{\mathcal{T}H_{++}}$, but the sophisticated geometry also results in some challenges for geometric detectors, such as the implementation of the enhanced detector to improve the SCR (signal-to-clutter ratio) and the analysis of the detection performance.
Priors in Deep Image Restoration and Enhancement: A Survey
Image restoration and enhancement is a process of improving the image quality by removing degradations, such as noise, blur, and resolution degradation.
Resilience in Industrial Internet of Things Systems: A Communication Perspective
Industrial Internet of Things is an ultra-large-scale system that is much more sophisticated and fragile than conventional industrial platforms.
Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles
Driven by the ever-increasing requirements of autonomous vehicles, such as traffic monitoring and driving assistant, deep learning-based object detection (DL-OD) has been increasingly attractive in intelligent transportation systems.
A New Outlier Removal Strategy Based on Reliability of Correspondence Graph for Fast Point Cloud Registration
We use a simple and intuitive method to describe the 6-DOF (degree of freedom) curtailment process in point cloud registration and propose an outlier removal strategy based on the reliability of the correspondence graph.
CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training
Specifically, we first extract multiple code views using compiler tools, and learn the complementary information among them under a contrastive learning framework.
Towards Practical and Efficient Long Video Summary
Recently, video summarization (VS) techniques are widely used to alleviate huge processing pressure brought by numerous long videos.
Digging into Primary Financial Market: Challenges and Opportunities of Adopting Blockchain
Since the emergence of blockchain technology, its application in the financial market has always been an area of focus and exploration by all parties.
GMSS: Graph-Based Multi-Task Self-Supervised Learning for EEG Emotion Recognition
GMSS has the ability to learn more general representations by integrating multiple self-supervised tasks, including spatial and frequency jigsaw puzzle tasks, and contrastive learning tasks.
Monte Carlo PINNs: deep learning approach for forward and inverse problems involving high dimensional fractional partial differential equations
We introduce a sampling based machine learning approach, Monte Carlo physics informed neural networks (MC-PINNs), for solving forward and inverse fractional partial differential equations (FPDEs).
Beyond the Limitation of Pulse Width in Optical Time-domain Reflectometry
Here, we propose and experimentally demonstrate an OTDR deconvolution neural network based on deep convolutional neural networks.
Compilable Neural Code Generation with Compiler Feedback
Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics and automated software engineering.
Contrastive Vision-Language Pre-training with Limited Resources
However, these works require a tremendous amount of data and computational resources (e. g., billion-level web data and hundreds of GPUs), which prevent researchers with limited resources from reproduction and further exploration.
Deeptime: a Python library for machine learning dynamical models from time series data
Generation and analysis of time-series data is relevant to many quantitative fields ranging from economics to fluid mechanics.
FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling
However, like other modern SSL algorithms, FixMatch uses a pre-defined constant threshold for all classes to select unlabeled data that contribute to the training, thus failing to consider different learning status and learning difficulties of different classes.
Positional-Spectral-Temporal Attention in 3D Convolutional Neural Networks for EEG Emotion Recognition
The proposed module, denoted by PST-Attention, consists of Positional, Spectral and Temporal Attention modules to explore more discriminative EEG features.
Aspect-driven User Preference and News Representation Learning for News Recommendation
News recommender systems are essential for helping users to efficiently and effectively find out those interesting news from a large amount of news.
Enabling variable high spatial resolution retrieval from a long pulse BOTDA sensor
We propose a convolutional neural network (CNN) to process the data of conventional Brillouin optical time domain analysis (BOTDA) sensors, which achieves unprecedented performance improvement that allows to directly retrieve higher spatial resolution (SR) from the sensing system that use long pump pulses.
Normalizing field flows: Solving forward and inverse stochastic differential equations using physics-informed flow models
We introduce in this work the normalizing field flows (NFF) for learning random fields from scattered measurements.
Cooperative Learning for Noisy Supervision
Learning with noisy labels has gained the enormous interest in the robust deep learning area.
SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation
Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence.
Conjugate Energy-Based Models
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables.
Nested Variational Inference
We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an forward or reverse KL divergence at each level of nesting.
Boosting Offline Reinforcement Learning with Residual Generative Modeling
While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.
Mathematical Modeling of Chemotaxis Guided Amoeboid Cell Swimming
Cells and microorganisms adopt various strategies to migrate in response to different environmental stimuli.
Collaborative Label Correction via Entropy Thresholding
Deep neural networks (DNNs) have the capacity to fit extremely noisy labels nonetheless they tend to learn data with clean labels first and then memorize those with noisy labels.
XRJL-HKUST at SemEval-2021 Task 4: WordNet-Enhanced Dual Multi-head Co-Attention for Reading Comprehension of Abstract Meaning
This paper presents our submitted system to SemEval 2021 Task 4: Reading Comprehension of Abstract Meaning.
LiGCN: Label-interpretable Graph Convolutional Networks for Multi-label Text Classification
Besides, the model allows better interpretability for predicted labels as the token-label edges are exposed.
Minimization of ion micromotion with artificial neural network
Minimizing the micromotion of the single trapped ion in a linear Paul trap is a tedious and time-consuming work, but is of great importance in cooling the ion into the motional ground state as well as maintaining long coherence time, which is crucial for quantum information processing and quantum computation.
Atomic Physics Quantum Physics
Learning Proposals for Probabilistic Programs with Inference Combinators
Proposals in these samplers can be parameterized using neural networks, which in turn can be trained by optimizing variational objectives.
A Convergent Semi-Proximal Alternating Direction Method of Multipliers for Recovering Internet Traffics from Link Measurements
Our model can be divided into a series of subproblems, which only relate to the traffics in a certain individual time interval.
Optimization and Control
LEAP: TrustZone Based Developer-Friendly TEE for Intelligent Mobile Apps
ARM TrustZone is widely deployed on commercial-off-the-shelf mobile devices for secure execution.
Cryptography and Security
Coalition Game Based Full-duplex Popular Content Distribution in mmWave Vehicular Networks
We evaluate the proposed scheme by extensive simulations in mmWave vehicular networks.
Fairness
Information Theory
Networking and Internet Architecture
Information Theory
Adaptive Tree Wasserstein Minimization for Hierarchical Generative Modeling
In this work, we consider OT over tree metrics, which is more general than the sliced Wasserstein and includes the sliced Wasserstein as a special case, and we propose a fast minimization algorithm in $O(n)$ for the optimal Wasserstein-1 transport plan between two distributions in the tree structure.
Warren at SemEval-2020 Task 4: ALBERT and Multi-Task Learning for Commonsense Validation
This paper describes our system in subtask A of SemEval 2020 Shared Task 4.
Learning the Best Pooling Strategy for Visual Semantic Embedding
Visual Semantic Embedding (VSE) is a dominant approach for vision-language retrieval, which aims at learning a deep embedding space such that visual data are embedded close to their semantic text labels or descriptions.
Memory Group Sampling Based Online Action Recognition Using Kinetic Skeleton Features
First, we combine the spatial and temporal skeleton features to depict the actions, which include not only the geometrical features, but also multi-scale motion features, such that both the spatial and temporal information of the action are covered.
A Relaxed Matching Procedure for Unsupervised BLI
Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest.
Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction
In this paper, we propose a new semi-supervised BLI framework to encourage the interaction between the supervised signal and unsupervised alignment.
Easy, Reproducible and Quality-Controlled Data Collection with CROWDAQ
High-quality and large-scale data are key to success for AI systems.
Improving the spatial resolution of a BOTDA sensor using deconvolution algorithm
The frequency dependency of Brillouin gain temporal envelope is investigated by simulation, and its impact on the recovered results of deconvolution algorithm is thoroughly analyzed.
DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors
Recently, two attention methods are proposed via combining with Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) network, which can capture the dependencies of sensing signals in both spatial and temporal domains simultaneously.
Learning Based Distributed Tracking
Inspired by the great success of machine learning in the past decade, people have been thinking about the possibility of improving the theoretical results by exploring data distribution.
Data Structures and Algorithms
Real-time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices
For deep learning, improvements in performance have to heavily rely on increasing model size or capacity to scale to larger and larger datasets, which inevitably leads to the increase of operations.
Response to LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts
Recently the Chinese video sharing platform Bilibili, has popularised a novel captioning system where user comments are displayed as streams of moving subtitles overlaid on the video playback screen and broadcast to all viewers in real-time.
Modeling nanoconfinement effects using active learning
At this scale, the fluid properties are affected by nanoconfinement effects due to the increased fluid-solid interactions.
TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions
A critical part of reading is being able to understand the temporal relationships between events described in a passage of text, even when those relationships are not explicitly stated.
Ranked #2 on
Question Answering
on Torque
Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation
Quantization techniques can reduce the size of Deep Neural Networks and improve inference latency and throughput by taking advantage of high throughput integer instructions.
Masked Face Recognition Dataset and Application
These datasets are freely available to industry and academia, based on which various applications on masked faces can be developed.
Fully Convolutional Networks for Automatically Generating Image Masks to Train Mask R-CNN
This paper proposes a novel automatically generating image masks method for the state-of-the-art Mask R-CNN deep learning method.
DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories
We propose a deep convolutional neural network called DeepDualMapper which fuses the aerial image and trajectory data in a more seamless manner to extract the digital map.
Ranked #5 on
Semantic Segmentation
on TLCGIS
Stochastic Normalizing Flows
The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics.
Structural-Aware Sentence Similarity with Recursive Optimal Transport
Moreover, we further develop Recursive Optimal Similarity (ROTS) for sentences with the valuable semantic insights from the connections between cosine similarity of weighted average of word vectors and optimal transport.
Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games.
Deep learning Markov and Koopman models with physical constraints
Here we develop theory and methods for deep learning Markov and Koopman models that can bear such physical constraints.
Computational Physics
Structured Multi-Hashing for Model Compression
Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory.
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frames structured variational inference as adaptive importance sampling.
Continuous Convolutional Neural Network forNonuniform Time Series
Convolutional neural network (CNN) for time series data implicitly assumes that the data are uniformly sampled, whereas many event-based and multi-modal data are nonuniform or have heterogeneous sampling rates.
Learning Latent Parameters without Human Response Patterns: Item Response Theory with Artificial Crowds
We demonstrate a use-case for latent difficulty item parameters, namely training set filtering, and show that using difficulty to sample training data outperforms baseline methods.
An encoding framework with brain inner state for natural image identification
The framework comprises two parts: forward encoding model that deals with visual stimuli and inner state model that captures influence from intrinsic connections in the brain.
Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes
However, these methods require fully annotated object bounding boxes for training, which are incredibly hard to scale up due to the high annotation cost.
Learning to Reconstruct and Understand Indoor Scenes from Sparse Views
This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes.
Joint Reasoning for Temporal and Causal Relations
Understanding temporal and causal relations between events is a fundamental natural language understanding task.
A Variational Approach for Learning from Positive and Unlabeled Data
Learning binary classifiers only from positive and unlabeled (PU) data is an important and challenging task in many real-world applications, including web text classification, disease gene identification and fraud detection, where negative samples are difficult to verify experimentally.
Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations
We propose the Unified Visual-Semantic Embeddings (Unified VSE) for learning a joint space of visual representation and textual semantics.
ZQM at SemEval-2019 Task9: A Single Layer CNN Based on Pre-trained Model for Suggestion Mining
In our system, the input of convolutional neural network is the embedding vectors which are drawn from the pre-trained BERT model.
Adaptive Learning Material Recommendation in Online Language Education
Recommending personalized learning materials for online language learning is challenging because we typically lack data about the student's ability and the relative difficulty of learning materials.
Uneven illumination surface defects inspection based on convolutional neural network
Surface defect inspection based on machine vision is often affected by uneven illumination.
Free Component Analysis: Theory, Algorithms & Applications
We describe a method for unmixing mixtures of freely independent random variables in a manner analogous to the independent component analysis (ICA) based method for unmixing independent random variables from their additive mixtures.
Wasserstein-Fisher-Rao Document Distance
As a fundamental problem of natural language processing, it is important to measure the distance between different documents.
UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations
We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts.
Boltzmann Generators -- Sampling Equilibrium States of Many-Body Systems with Deep Learning
Computing equilibrium states in condensed-matter many-body systems, such as solvated proteins, is a long-standing challenge.
Variational Selection of Features for Molecular Kinetics
The modeling of atomistic biomolecular simulations using kinetic models such as Markov state models (MSMs) has had many notable algorithmic advances in recent years.
Composing Modeling and Inference Operations with Probabilistic Program Combinators
We assume that models are dynamic, but that model composition is static, in the sense that combinator application takes place prior to evaluating the model on data.
