Search Results for author:
Found 33 papers, 12 papers with code
Towards deployment-centric multimodal AI beyond vision and language
Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering.
LL4G: Self-Supervised Dynamic Optimization for Graph-Based Personality Detection
Graph-based personality detection constructs graph structures from textual data, particularly social media posts.
STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1.
A Data Balancing and Ensemble Learning Approach for Credit Card Fraud Detection
This research introduces an innovative method for identifying credit card fraud by combining the SMOTE-KMEANS technique with an ensemble machine learning model.
Traversing Distortion-Perception Tradeoff using a Single Score-Based Generative Model
The distortion-perception (DP) tradeoff reveals a fundamental conflict between distortion metrics (e. g., MSE and PSNR) and perceptual quality.
Causal invariant geographic network representations with feature and structural distribution shifts
We propose a feature-structure mixed invariant representation learning (FSM-IRL) model that accounts for both feature distribution shifts and structural distribution shifts.
Hoi2Anomaly: An Explainable Anomaly Detection Approach Guided by Human-Object Interaction
This deficiency often leads to the detection of anomalous entities or actions that are susceptible to machine illusions and lack sufficient explanation.
MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
In this paper, we explore human multiview diffusion models at the megapixel level and introduce a solution called mesh attention to enable training at 1024x1024 resolution.
Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks.
IMM-MOT: A Novel 3D Multi-object Tracking Framework with Interacting Multiple Model Filter
3D Multi-Object Tracking (MOT) provides the trajectories of surrounding objects, assisting robots or vehicles in smarter path planning and obstacle avoidance.
A Deep Learning Framework Integrating CNN and BiLSTM for Financial Systemic Risk Analysis and Prediction
This study proposes a deep learning model based on the combination of convolutional neural network (CNN) and bidirectional long short-term memory network (BiLSTM) for discriminant analysis of financial systemic risk.
Simultaneous Beamforming and Anti-Jamming With Intelligent Omni-Surfaces
In this paper, we consider an IOS-aided multi-user anti-jamming communication system, aiming to improve desired signals and nullify jamming by optimizing IOS phase shifts and transmit beamforming.
Leveraging Convolutional Neural Network-Transformer Synergy for Predictive Modeling in Risk-Based Applications
To this end, this paper proposes a deep learning model based on the combination of convolutional neural networks (CNN) and Transformer for credit user default prediction.
RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understanding
Under the new LaGD paradigm, the old datasets, which have led to advances in RSI intelligence understanding in the last decade, are no longer suitable for fire-new tasks.
Unveiling Incomplete Modality Brain Tumor Segmentation: Leveraging Masked Predicted Auto-Encoder and Divergence Learning
Brain tumor segmentation remains a significant challenge, particularly in the context of multi-modal magnetic resonance imaging (MRI) where missing modality images are common in clinical settings, leading to reduced segmentation accuracy.
G-VOILA: Gaze-Facilitated Information Querying in Daily Scenarios
Modern information querying systems are progressively incorporating multimodal inputs like vision and audio.
Lasso Ridge based XGBoost and Deep_LSTM Help Tennis Players Perform better
Understanding the dynamics of momentum and game fluctuation in tennis matches is cru-cial for predicting match outcomes and enhancing player performance.
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.
LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
Accurate traffic forecasting is a fundamental problem in intelligent transportation systems and learning long-range traffic representations with key information through spatiotemporal graph neural networks (STGNNs) is a basic assumption of current traffic flow prediction models.
Towards Dense and Accurate Radar Perception Via Efficient Cross-Modal Diffusion Model
Millimeter wave (mmWave) radars have attracted significant attention from both academia and industry due to their capability to operate in extreme weather conditions.
Development of a Reliable and Accessible Caregiving Language Model (CaLM)
The RAG framework improved the performance of all FMs used in this study across all measures.
Symbol as Points: Panoptic Symbol Spotting via Point-based Representation
Finally, we propose a KNN interpolation mechanism for the mask attention module of the spotting head to better handle primitive mask downsampling, which is primitive-level in contrast to pixel-level for the image.
Neural Video Fields Editing
Specifically, we construct a neural video field, powered by tri-plane and sparse grid, to enable encoding long videos with hundreds of frames in a memory-efficient manner.
MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention
We first conducted a Wizard-of-Oz study (N=12) and an interview study (N=10) to summarize the mental states behind problematic smartphone use: boredom, stress, and inertia.
StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation
In this paper, we introduce a novel motion generator design that uses a learning-based inversion network for GAN.
Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
To obtain high-quality positron emission tomography (PET) scans while reducing radiation exposure to the human body, various approaches have been proposed to reconstruct standard-dose PET (SPET) images from low-dose PET (LPET) images.
DiffLLE: Diffusion-guided Domain Calibration for Unsupervised Low-light Image Enhancement
Specifically, we adopt a naive unsupervised enhancement algorithm to realize preliminary restoration and design two zero-shot plug-and-play modules based on diffusion model to improve generalization and effectiveness.
3D RegNet: Deep Learning Model for COVID-19 Diagnosis on Chest CT Image
In this paper, a 3D-RegNet-based neural network is proposed for diagnosing the physical condition of patients with coronavirus (Covid-19) infection.
HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
In this work, we propose a high fidelity face swapping method, called HifiFace, which can well preserve the face shape of the source face and generate photo-realistic results.
Ranked #7 on
Face Swapping
on FaceForensics++
Efficient Two-Step Networks for Temporal Action Segmentation
Due to boundary ambiguity and over-segmentation issues, identifying all the frames in long untrimmed videos is still challenging.
Ranked #14 on
Action Segmentation
on GTEA
In situ Performance of the Low Frequency Arrayfor Advanced ACTPol
The Advanced Atacama Cosmology Telescope Polarimeter (AdvACT) \cite{thornton} is an upgrade for the Atacama Cosmology Telescope using Transition Edge Sensor (TES) detector arrays to measure cosmic microwave background (CMB) temperature and polarization anisotropies in multiple frequencies.
Instrumentation and Methods for Astrophysics
Effective and Sparse Count-Sketch via k-means clustering
This data-oblivious matrix sketching method could produce a bad sketched matrix which will result in low accuracy for subsequent machine learning tasks (e. g. classification); (2) For highly sparse input data, count-sketch could produce a dense sketched data matrix.
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability.
Ranked #13 on
Face Verification
on IJB-C
(TAR @ FAR=1e-4 metric)
