Search Results for author:
Found 297 papers, 115 papers with code
BCRNet: Enhancing Landmark Detection in Laparoscopic Liver Surgery via Bezier Curve Refinement
In this paper, we propose BCRNet (Bezier Curve Refinement Net), a novel framework that significantly enhances landmark detection in laparoscopic liver surgery primarily via the Bezier curve refinement strategy.
CALM: Consensus-Aware Localized Merging for Multi-Task Learning
Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities.
SUSEP-Net: Simulation-Supervised and Contrastive Learning-based Deep Neural Networks for Susceptibility Source Separation
Comprehensive experiments were carried out on both simulated and in vivo data, including healthy subjects and patients with pathological conditions, to compare SUSEP-Net with three state-of-the-art susceptibility source separation methods (i. e., APART-QSM, \c{hi}-separation, and \c{hi}-sepnet).
Compositional and Equilibrium-Free Conditions for Power System Stability -- Part II: Method and Application
In Part I, we have established the stability theory and proposed stability conditions based on the delta dissipativity.
Compositional and Equilibrium-Free Conditions for Power System Stability -- Part I: Theory
This two-part paper proposes a compositional and equilibrium-free approach to analyzing power system stability.
Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction
As large-scale pre-trained foundation models continue to expand in size and capability, efficiently adapting them to specific downstream tasks has become increasingly critical.
OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data
Existing benchmarks for Earth science multimodal learning exhibit critical limitations in systematic coverage of geosystem components and cross-sphere interactions, often constrained to isolated subsystems (only in Human-activities sphere or atmosphere) with limited evaluation dimensions (less than 16 tasks).
EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse
However, in infilling tasks, the KV cache reuse is often hindered by the structure of the prompt format, which typically consists of a prefix and suffix relative to the insertion point.
Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems
Then it further utilizes a self-adaptive curriculum scheduler to enable LLMs to gradually learn from simpler data (self-distilled data) to more challenging data (real RS data).
Flow Matching based Sequential Recommender Model
Generative models, particularly diffusion model, have emerged as powerful tools for sequential recommendation.
No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery
Deep learning models trained on extensive Electronic Health Records (EHR) data have achieved high accuracy in diagnosis prediction, offering the potential to assist clinicians in decision-making and treatment planning.
Temporal and Spatial Feature Fusion Framework for Dynamic Micro Expression Recognition
In this paper, we propose a novel Temporal and Spatial feature Fusion framework for DMER (TSFmicro).
Field Matters: A lightweight LLM-enhanced Method for CTR Prediction
Click-through rate (CTR) prediction is a fundamental task in modern recommender systems.
Structure-Aware Corpus Construction and User-Perception-Aligned Metrics for Large-Language-Model Code Completion
Code completion technology based on large language model has significantly improved the development efficiency of programmers.
Temporal-Spectral-Spatial Unified Remote Sensing Dense Prediction
Consequently, variations in data dimensionality or task requirements often lead to significant performance degradation or model incompatibility, necessitating costly retraining or fine-tuning efforts for different application scenarios.
Highly Undersampled MRI Reconstruction via a Single Posterior Sampling of Diffusion Models
Incoherent k-space under-sampling and deep learning-based reconstruction methods have shown great success in accelerating MRI.
ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models
Current diffusion-based text-to-video methods are limited to producing short video clips of a single shot and lack the capability to generate multi-shot videos with discrete transitions where the same character performs distinct activities across the same or different backgrounds.
TACFN: Transformer-based Adaptive Cross-modal Fusion Network for Multimodal Emotion Recognition
Specifically, for the redundant features, we make one modality perform intra-modal feature selection through a self-attention mechanism, so that the selected features can adaptively and efficiently interact with another modality.
Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait
To this end, we propose FarSight, a unified end-to-end system for person recognition that integrates complementary biometric cues across face, gait, and body shape modalities.
Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions
Unmanned Aerial Vehicles (UAVs) are indispensable for infrastructure inspection, surveillance, and related tasks, yet they also introduce critical security challenges.
MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender
Large language models (LLMs), known for their comprehension capabilities and extensive knowledge, have been increasingly applied to recommendation systems (RS).
Could AI Trace and Explain the Origins of AI-Generated Images and Text?
AI-generated content is becoming increasingly prevalent in the real world, leading to serious ethical and societal concerns.
Flexible and Explainable Graph Analysis for EEG-based Alzheimer's Disease Classification
Alzheimer's Disease is a progressive neurological disorder that is one of the most common forms of dementia.
Ancestral Mamba: Enhancing Selective Discriminant Space Model with Online Visual Prototype Learning for Efficient and Robust Discriminant Approach
In the realm of computer graphics, the ability to learn continuously from non-stationary data streams while adapting to new visual patterns and mitigating catastrophic forgetting is of paramount importance.
Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation
However, the conventional next-token prediction paradigm in AR models does not align with the human creative process in music composition, potentially compromising the musicality of generated samples.
Hierarchical Adaptive Expert for Multimodal Sentiment Analysis
HAEMSA employs a hierarchical structure of adaptive experts to capture both global and local modality representations, enabling more nuanced sentiment analysis.
MedPlan:A Two-Stage RAG-Based System for Personalized Medical Plan Generation
Despite recent success in applying large language models (LLMs) to electronic health records (EHR), most systems focus primarily on assessment rather than treatment planning.
OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning
Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs across various applications.
Visual Persona: Foundation Model for Full-Body Human Customization
We introduce Visual Persona, a foundation model for text-to-image full-body human customization that, given a single in-the-wild human image, generates diverse images of the individual guided by text descriptions.
Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Space
Experimental results on the Valence-Arousal (VA) Estimation task of the 8th competition on Affective Behavior Analysis in-the-wild (ABAW) demonstrate that the proposed model achieves valence and arousal scores of 0. 5362 (0. 5036) and 0. 4310 (0. 4119) on the validation (test) set, respectively, outperforming the baseline.
GRU: Mitigating the Trade-off between Unlearning and Retention for Large Language Models
Specifically, GRU derives a closed-form solution to project the unlearning gradient onto the orthogonal space of that gradient harmful for retention, ensuring minimal deviation from its original direction under the condition that overall performance is retained.
MF-VITON: High-Fidelity Mask-Free Virtual Try-On with Minimal Input
To address this, we propose a Mask-Free VITON (MF-VITON) framework that achieves realistic VITON using only a single person image and a target garment, eliminating the requirement for auxiliary masks.
AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification
The relatively lower performance of all state-of-the-art approaches, including our proposed approach, on our new dataset highlights its challenging nature.
Transforming Weather Data from Pixel to Latent Space
The downstream task further demonstrates that task models can apply to multiple PVS with low data costs in latent space and achieve superior performance compared to models in pixel space.
One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
MMD-OPT first serves as a guiding signal to minimize the distributional discrepancy between CEs and AEs to train a denoiser.
SeisMoLLM: Advancing Seismic Monitoring via Cross-modal Transfer with Pre-trained Large Language Model
Recent advances in deep learning have revolutionized seismic monitoring, yet developing a foundation model that performs well across multiple complex tasks remains challenging, particularly when dealing with degraded signals or data scarcity.
NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders
Mental disorders are among the most widespread diseases globally.
Robust Dynamic Facial Expression Recognition
Moreover, to identify the principal expression in a video and enhance the model's capacity for representation learning, comprising a key expression re-sampling framework and a dual-stream hierarchical network is proposed, namely Robust Dynamic Facial Expression Recognition (RDFER).
Dynamic Facial Expression Recognition
Facial Expression Recognition
MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation
This paper presents a method that allows users to design cinematic video shots in the context of image-to-video generation.
Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning
Large Language Models (LLMs) have attained human-level accuracy on medical question-answer (QA) benchmarks.
Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding
Using STE, we systematically compare implicit and explicit temporal modeling across dimensions such as overall performance, token compression effectiveness, and temporal-specific understanding.
Attribute-based Visual Reprogramming for Image Classification with CLIP
Besides, as images of the same class may reflect different attributes after VR, AttrVR iteratively refines patterns using the $k$-nearest DesAttrs and DistAttrs for each image sample, enabling more dynamic and sample-specific optimization.
Lossy Compression with Pretrained Diffusion Models
We apply the DiffC algorithm (Theis et al. 2022) to Stable Diffusion 1. 5, 2. 1, XL, and Flux-dev, and demonstrate that these pretrained models are remarkably capable lossy image compressors.
Progressive Growing of Video Tokenizers for Highly Compressed Latent Spaces
Evaluation of video benchmarks shows that our method significantly improves reconstruction quality while increasing temporal compression compared to direct extensions of existing video tokenizers.
DispFormer: Pretrained Transformer for Flexible Dispersion Curve Inversion from Global Synthesis to Regional Applications
Surface wave dispersion curve inversion is essential for estimating subsurface Shear-wave velocity ($v_s$), yet traditional methods often struggle to balance computational efficiency with inversion accuracy.
DynamicLip: Shape-Independent Continuous Authentication via Lip Articulator Dynamics
We study the dynamic characteristics of lip biometrics based on articulator motion.
SapiensID: Foundation for Human Recognition
Existing human recognition systems often rely on separate, specialized models for face and body analysis, limiting their effectiveness in real-world scenarios where pose, visibility, and context vary widely.
DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution
During inference, DynRefer performs selectively multimodal referring by sampling proper region representations for tasks from the set of views based on image and task priors.
FloNa: Floor Plan Guided Embodied Visual Navigation
To eliminate this gap, we introduce a novel navigation task: Floor Plan Visual Navigation (FloNa), the first attempt to incorporate floor plan into embodied visual navigation.
Move-in-2D: 2D-Conditioned Human Motion Generation
Generating realistic human videos remains a challenging task, with the most effective methods currently relying on a human motion sequence as a control signal.
Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds
Leveraging this insight, we propose Consistency Model-based Adversarial Purification (CMAP), which optimizes vectors within the latent space of a pre-trained consistency model to generate samples for restoring clean data.
GAF-FusionNet: Multimodal ECG Analysis via Gramian Angular Fields and Split Attention
Electrocardiogram (ECG) analysis plays a crucial role in diagnosing cardiovascular diseases, but accurate interpretation of these complex signals remains challenging.
STEAM-EEG: Spatiotemporal EEG Analysis with Markov Transfer Fields and Attentive CNNs
Electroencephalogram (EEG) signals play a pivotal role in biomedical research and clinical applications, including epilepsy diagnosis, sleep disorder analysis, and brain-computer interfaces.
Semantic Retrieval at Walmart
In this paper, we present a hybrid system for e-commerce search deployed at Walmart that combines traditional inverted index and embedding-based neural retrieval to better answer user tail queries.
NLPrompt: Noise-Label Prompt Learning for Vision-Language Models
This matrix effectively partitions datasets into clean and noisy subsets, allowing for the application of cross-entropy loss to the clean subset and MAE loss to the noisy subset.
Automatic Differentiation-based Full Waveform Inversion with Flexible Workflows
The AD-based framework not only includes forword modeling and associated gradient computations for wave equations in various types of media from isotropic acoustic to vertically or horizontally transverse isotropic elastic, but also incorporates a suite of objective functions, regularization techniques, and optimization algorithms.
A Unified Data Representation Learning for Non-parametric Two-sample Testing
Common approaches will first split data into training and test sets and then learn data representations purely on the training set.
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising.
DualCast: Disentangling Aperiodic Events from Traffic Series with a Dual-Branch Model
Traffic forecasting is an important problem in the operation and optimisation of transportation systems.
TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On
Recent advancements in Virtual Try-On (VTO) have demonstrated exceptional efficacy in generating realistic images and preserving garment details, largely attributed to the robust generative capabilities of text-to-image (T2I) diffusion backbones.
EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation
Video generation has emerged as a promising tool for world simulation, leveraging visual data to replicate real-world environments.
World Models: The Safety Perspective
With the proliferation of the Large Language Model (LLM), the concept of World Models (WM) has recently attracted a great deal of attention in the AI research community, especially in the context of AI agents.
Adaptive Conditional Expert Selection Network for Multi-domain Recommendation
However, such MOE-based method typically employs all experts for each instance, leading to scalability issue and low-discriminability between domains and experts.
'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialogue
Out-of-distribution (OOD) detection in multimodal contexts is essential for identifying deviations in combined inputs from different modalities, particularly in applications like open-domain dialogue systems or real-life dialogue interactions.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Bayesian-guided Label Mapping for Visual Reprogramming
When adapting the output interface, label mapping methods transform the pretrained labels to downstream labels by establishing a gradient-free one-to-one correspondence between the two sets of labels.
Predicting the Encoding Error of SIRENs
Towards this goal, we present a method which predicts the encoding error that a popular INR network (SIREN) will reach, given its network hyperparameters and the signal to encode.
Fingerprints of Super Resolution Networks
Several recent studies have demonstrated that deep-learning based image generation models, such as GANs, can be uniquely identified, and possibly even reverse-engineered, by the fingerprints they leave on their output images.
Enhancing Learned Image Compression via Cross Window-based Attention
Therefore, to leverage global features along with local redundancy, we propose a CNN-based solution integrated with a feature encoding module.
Enhancing Multimodal Medical Image Classification using Cross-Graph Modal Contrastive Learning
However, traditional approaches typically focus on unimodal medical image data, neglecting the integration of diverse non-image patient data.
DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control
In this paper, we present DreamVideo-2, a zero-shot video customization framework capable of generating videos with a specific subject and motion trajectory, guided by a single image and a bounding box sequence, respectively, and without the need for test-time fine-tuning.
Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
However, in this paper, we find that there naturally exists a gap, which resembles the modality gap, between the prototype and image instance embeddings extracted from the frozen pre-trained backbone, and simply applying the same transformation during the adaptation phase constrains exploring the optimal representations and shrinks the gap between prototype and image representations.
Progressive Autoregressive Video Diffusion Models
In this work, we introduce a more natural formulation of autoregressive long video generation by revisiting the noise level assumption in video diffusion models.
HARIVO: Harnessing Text-to-Image Models for Video Generation
We present a method to create diffusion-based video models from pretrained Text-to-Image (T2I) models.
Optimal Control in Both Steady State and Transient Process with Unknown Disturbances
The scheme of online optimization as a feedback controller is widely used to steer the states of a physical system to the optimal solution of a predefined optimization problem.
AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs
Jailbreak vulnerabilities in Large Language Models (LLMs) refer to methods that extract malicious content from the model by carefully crafting prompts or suffixes, which has garnered significant attention from the research community.
Learning Deep Kernels for Non-Parametric Independence Testing
The Hilbert-Schmidt Independence Criterion (HSIC) is a powerful tool for nonparametric detection of dependence between random variables.
An End-to-End Approach for Chord-Conditioned Song Generation
The Song Generation task aims to synthesize music composed of vocals and accompaniment from given lyrics.
SongCreator: Lyrics-based Universal Song Generation
While various aspects of song generation have been explored by previous works, such as singing voice, vocal composition and instrumental arrangement, etc., generating songs with both vocals and accompaniment given lyrics remains a significant challenge, hindering the application of music generation models in the real world.
LLM4DSR: Leveraing Large Language Model for Denoising Sequential Recommendation
However, employing LLMs for denoising in sequential recommendation presents notable challenges: 1) Direct application of pretrained LLMs may not be competent for the denoising task, frequently generating nonsensical responses; 2) Even after fine-tuning, the reliability of LLM outputs remains questionable, especially given the complexity of the denoising task and the inherent hallucinatory issue of LLMs.
Fast Information Streaming Handler (FisH): A Unified Seismic Neural Network for Single Station Real-Time Earthquake Early Warning
FisH is designed to process real-time streaming seismic data and generate simultaneous results for phase picking, location estimation, and magnitude estimation in an end-to-end fashion.
Relevance Filtering for Embedding-based Retrieval
This issue is prominent in product search, where the number of relevant products is often small.
Mamba-Spike: Enhancing the Mamba Architecture with a Spiking Front-End for Efficient Temporal Data Processing
This paper introduces Mamba-Spike, a novel neuromorphic architecture that integrates a spiking front-end with the Mamba backbone to achieve efficient and robust temporal data processing.
Open-Set Biometrics: Beyond Good Closed-Set Models
Biometric recognition has primarily addressed closed-set identification, assuming all probe subjects are in the gallery.
MEDFuse: Multimodal EHR Data Fusion with Masked Lab-Test Modeling and Large Language Models
Electronic health records (EHRs) are multimodal by nature, consisting of structured tabular features like lab tests and unstructured clinical notes.
Optimal Kernel Choice for Score Function-based Causal Discovery
In this paper, we propose a kernel selection method within the generalized score function that automatically selects the optimal kernel that best fits the data.
Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features
What's more, we are the first to prove the effectiveness of emotional features, and provide a new idea for measuring the distance between skeletal motions.
Exclusive Style Removal for Cross Domain Novel Class Discovery
In this paper, we explore and establish the solvability of NCD in cross domain setting with the necessary condition that style information must be removed.
EHR-Based Mobile and Web Platform for Chronic Disease Risk Prediction Using Large Language Multimodal Models
Traditional diagnosis of chronic diseases involves in-person consultations with physicians to identify the disease.
IR2QSM: Quantitative Susceptibility Mapping via Deep Neural Networks with Iterative Reverse Concatenations and Recurrent Modules
Quantitative susceptibility mapping (QSM) is an MRI phase-based post-processing technique to extract the distribution of tissue susceptibilities, demonstrating significant potential in studying neurological diseases.
Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
To alleviate this issue, we propose a Candidate Pseudolabel Learning method, termed CPL, to fine-tune VLMs with suitable candidate pseudolabels of unlabeled data in downstream tasks.
Capacity Credit Evaluation of Generalized Energy Storage Considering Strategic Capacity Withholding and Decision-Dependent Uncertainty
This paper proposes a novel capacity credit evaluation framework to accurately quantify the contribution of generalized energy storage (GES) to resource adequacy, considering both strategic capacity withholding and decision-dependent uncertainty (DDU).
Sample-specific Masks for Visual Reprogramming-based Prompting
Since we generate different masks for individual samples, SMM is theoretically shown to reduce approximation error for the target tasks compared with existing state-of-the-art VR methods.
Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
The local visual areas are then cross-aligned with the finer descriptions by creating a similarity matrix using the pre-trained VLM.
Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
However, in this paper, we discover that not all pixels contribute equally to the accuracy on AEs (i. e., robustness) and accuracy on natural images (i. e., accuracy).
MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence
In cross-domain few-shot classification, \emph{nearest centroid classifier} (NCC) aims to learn representations to construct a metric space where few-shot classification can be performed by measuring the similarities between samples and the prototype of each class.
DynRefer: Delving into Region-level Multi-modality Tasks via Dynamic Resolution
Unfortunately, most of existing methods using fixed visual inputs remain lacking the resolution adaptability to find out precise language descriptions.
BDetCLIP: Multimodal Prompting Contrastive Test-Time Backdoor Detection
In this paper, we provide the first attempt at a computationally efficient backdoor detection method to defend against backdoored CLIP in the inference stage.
Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language Model
Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance.
VideoGigaGAN: Towards Detail-rich Video Super-Resolution
We introduce VideoGigaGAN, a new generative VSR model that can produce videos with high-frequency details and temporal consistency.
Ranked #16 on
Video Super-Resolution
on Vid4 - 4x upscaling
(PSNR metric)
On the Learnability of Out-of-distribution Detection
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game
In this paper, we propose a multi-agent attacker-disguiser game approach to achieve a weak defense mechanism that allows the large model to both safely reply to the attacker and hide the defense intent.
Negative Label Guided OOD Detection with Pretrained Vision-Language Models
In this paper, we propose a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extensive corpus databases.
Benchmarking Video Frame Interpolation
Video frame interpolation, the task of synthesizing new frames in between two or more given ones, is becoming an increasingly popular research target.
KeyPoint Relative Position Encoding for Face Recognition
By anchoring the significance of pixels around keypoints, the model can more effectively retain spatial relationships, even when those relationships are disrupted by affine transformations.
QSMDiff: Unsupervised 3D Diffusion Models for Quantitative Susceptibility Mapping
In this work, we developed a 3D image patch-based diffusion model, namely QSMDiff, for robust QSM reconstruction across different scan parameters, alongside simultaneous super-resolution and image-denoising tasks.
IIDM: Image-to-Image Diffusion Model for Semantic Image Synthesis
Semantic image synthesis aims to generate high-quality images given semantic conditions, i. e. segmentation masks and style reference images.
Learning-Aided Control of Robotic Tether-Net with Maneuverable Nodes to Capture Large Space Debris
System performance is assessed in terms of capture success and overall fuel consumption by the MUs.
Large Language Multimodal Models for 5-Year Chronic Disease Cohort Prediction Using EHR Data
In our experiments, we observe that clinicalBERT and PubMed-BERT, when combined with attention fusion, can achieve an accuracy of 73% in multiclass chronic diseases and diabetes prediction.
Spatial Craving Patterns in Marijuana Users: Insights from fMRI Brain Connectivity Analysis with High-Order Graph Attention Neural Networks
The excessive consumption of marijuana can induce substantial psychological and social consequences.
Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models
To address the challenge of one-shot video motion customization, we propose Customize-A-Video that models the motion from a single reference video and adapts it to new subjects and scenes with both spatial and temporal varieties.
Fingerprint Presentation Attack Detector Using Global-Local Model
While by using the texture in-painting-based local module, a local spoofness score predicted from fingerprint patches is obtained.
Privacy-Preserving Low-Rank Adaptation against Membership Inference Attacks for Latent Diffusion Models
To mitigate this issue, we further propose a Stable Membership-Privacy-preserving LoRA (SMP-LoRA) that adapts the LDM by minimizing the ratio of the adaptation loss to the MI gain.
Multiview Contrastive Learning for Unsupervised Domain Adaptation in Brain–Computer Interfaces
Domain adaptation has gained significant attention to address the nonstationarity problem in electroencephalography (EEG) data in motor imagery (MI) classification.
Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection
Multi-view 3D object detection systems often struggle with generating precise predictions due to the challenges in estimating depth from images, increasing redundant and incorrect detections.
Ranked #2 on
3D Object Detection
on nuScenes Camera Only
From Data to Insights: A Comprehensive Survey on Advanced Applications in Thyroid Cancer Research
Thyroid cancer, the most prevalent endocrine cancer, has gained significant global attention due to its impact on public health.
SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model
Our method employs a supernet training paradigm that targets various model cost and resolution options using a weight-sharing method.
Distilling CLIP with Dual Guidance for Learning Discriminative Human Body Shape Representation
Person Re-Identification (ReID) holds critical importance in computer vision with pivotal applications in public safety and crime prevention.
Scale invariance in early embryonic development
The body plan of the fruit fly is determined by the expression of just a handful of genes.
INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fields
We propose INFAMOUS-NeRF, an implicit morphable face model that introduces hypernetworks to NeRF to improve the representation power in the presence of many training subjects.
Fast View Synthesis of Casual Videos with Soup-of-Planes
Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video.
Parkinson's Disease Classification Using Contrastive Graph Cross-View Learning with Multimodal Fusion of SPECT Images and Clinical Features
This work proposes a multimodal approach encompassing both image and non-image features, leveraging contrastive cross-view graph fusion for PD classification.
Single Image Compressed Sensing MRI via a Self-Supervised Deep Denoising Approach
Popular methods in compressed sensing (CS) are dependent on deep learning (DL), where large amounts of data are used to train non-linear reconstruction models.
Fast Controllable Diffusion Models for Undersampled MRI Reconstruction
Supervised deep learning methods have shown promise in undersampled Magnetic Resonance Imaging (MRI) reconstruction, but their requirement for paired data limits their generalizability to the diverse MRI acquisition parameters.
Plug-and-Play Latent Feature Editing for Orientation-Adaptive Quantitative Susceptibility Mapping Neural Networks
The proposed OA-LFE-empowered iQSM, which we refer to as iQSM+, is trained in a self-supervised manner on a specially-designed simulation brain dataset.
LRM: Large Reconstruction Model for Single Image to 3D
We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds.
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
To this end, we suggest that generated data (with mistaken OOD generation) can be used to devise an auxiliary OOD detection task to facilitate real OOD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
Learning to Augment Distributions for Out-of-Distribution Detection
Accordingly, we propose Distributional-Augmented OOD Learning (DAL), alleviating the OOD distribution discrepancy by crafting an OOD distribution set that contains all distributions in a Wasserstein ball centered on the auxiliary OOD distribution.
Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis
Based on this fact, we introduce a simple partition mechanism to boost the performance of two INR methods for image reconstruction: one for learning INRs, and the other for learning-to-learn INRs.
Auxiliary Features-Guided Super Resolution for Monte Carlo Rendering
This paper investigates super resolution to reduce the number of pixels to render and thus speed up Monte Carlo rendering algorithms.
PINF: Continuous Normalizing Flows for Physics-Constrained Deep Learning
The normalization constraint on probability density poses a significant challenge for solving the Fokker-Planck equation.
Baichuan 2: Open Large-scale Language Models
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
BG-GAN: Generative AI Enable Representing Brain Structure-Function Connections for Alzheimer's Disease
The experimental findings suggest that the relationship between brain structure and function is not a complete one-to-one correspondence.
Multi-Stage Expansion Planning for Decarbonizing Thermal Generation Supported Renewable Power Systems Using Hydrogen and Ammonia Storage
Large-scale centralized development of wind and solar energy and peer-to-grid transmission of renewable energy source (RES) via high voltage direct current (HVDC) has been regarded as one of the most promising ways to achieve goals of peak carbon and carbon neutrality in China.
Slimmed optical neural networks with multiplexed neuron sets and a corresponding backpropagation training algorithm
However, inter-channel crosstalk has obstructed WDM technologies to be deployed in nonlinear activation in ONNs.
Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification
Long-Term Person Re-Identification (LT-ReID) has become increasingly crucial in computer vision and biometrics.
Ranked #2 on
Person Re-Identification
on CCVID
Quantitative Susceptibility Mapping through Model-based Deep Image Prior (MoDIP)
The data-driven approach of supervised learning methods has limited applicability in solving dipole inversion in Quantitative Susceptibility Mapping (QSM) with varying scan parameters across different objects.
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
In this paper, we propose a diversity-enhancing generative network (DEG-Net) for the FHA problem, which can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC).
Learning Constrained Corner Node Trajectories of a Tether Net System for Space Debris Capture
The earth's orbit is becoming increasingly crowded with debris that poses significant safety risks to the operation of existing and new spacecraft and satellites.
FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude
Whole-body biometric recognition is an important area of research due to its vast applications in law enforcement, border security, and surveillance.
CoverHunter: Cover Song Identification with Refined Attention and Alignments
Abstract: Cover song identification (CSI) focuses on finding the same music with different versions in reference anchors given a query track.
Ranked #1 on
Cover song identification
on SHS100K-TEST
Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score
Last, we propose an EPS-based adversarial detection (EPS-AD) method, in which we develop EPS-based maximum mean discrepancy (MMD) as a metric to measure the discrepancy between the test sample and natural samples.
DADIN: Domain Adversarial Deep Interest Network for Cross Domain Recommender Systems
Click-Through Rate (CTR) prediction is one of the main tasks of the recommendation system, which is conducted by a user for different items to give the recommendation results.
Attacking Perceptual Similarity Metrics
In our study, we systematically examine the robustness of these metrics to imperceptible adversarial perturbations.
Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization
To improve transferability, the existing work introduced the standard invariant regularization (SIR) to impose style-independence property to SCL, which can exempt the impact of nuisance style factors in the standard representation.
Detecting Out-of-distribution Data through In-distribution Class Prior
In this paper, we show that this assumption makes the above methods incapable when the ID model is trained with class-imbalanced data. Fortunately, by analyzing the causal relations between ID/OOD classes and features, we identify several common scenarios where the OOD-to-ID probabilities should be the ID-class-prior distribution and propose two strategies to modify existing inference-time detection methods: 1) replace the uniform distribution with the ID-class-prior distribution if they explicitly use the uniform distribution; 2) otherwise, reweight their scores according to the similarity between the ID-class-prior distribution and the softmax outputs of the pre-trained model.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
DCFace: Synthetic Face Generation with Dual Condition Diffusion Model
Our novel Patch-wise style extractor and Time-step dependent ID loss enables DCFace to consistently produce face images of the same subject under different styles with precise control.
AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representation
To apply optical flow in practice, it is often necessary to resize the input to smaller dimensions in order to reduce computational costs.
Optimal Sizing of Isolated Renewable Power Systems with Ammonia Synthesis: Model and Solution Approach
However, multi-timescale electricity, hydrogen, and ammonia storages, minimum power supply for system safety, and the multi-year uncertainty of renewable generation lead to difficulties in planning.
Out-of-distribution Detection with Implicit Outlier Transformation
It leads to a min-max learning scheme -- searching to synthesize OOD data that leads to worst judgments and learning from such OOD data for uniform performance in OOD detection.
Multi-timescale Trading Strategy for Renewable Power to Ammonia Virtual Power Plant in the Electricity, Hydrogen, and Ammonia Markets
Hence, we develop a multi-timescale trading strategy for the RePtA VPP in the electricity, hydrogen, and ammonia markets.
AliasNet: Alias Artefact Suppression Network for Accelerated Phase-Encode MRI
Sparse reconstruction is an important aspect of MRI, helping to reduce acquisition time and improve spatial-temporal resolution.
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
Adversarial contrastive learning (ACL) does not require expensive data annotations but outputs a robust representation that withstands adversarial attacks and also generalizes to a wide range of downstream tasks.
Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition
Dynamic Facial Expression Recognition (DFER) is a rapidly developing field that focuses on recognizing facial expressions in video format.
Ranked #12 on
Dynamic Facial Expression Recognition
on FERV39k
Dynamic Facial Expression Recognition
Facial Expression Recognition
Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition
Recent studies have shown the vulnerability of CNNs under perturbation noises, which is partially caused by the reason that the well-trained CNNs are too biased toward the object texture, i. e., they make predictions mainly based on texture cues.
Learning Implicit Functions for Dense 3D Shape Correspondence of Generic Objects
The objective of this paper is to learn dense 3D shape correspondence for topology-varying generic objects in an unsupervised manner.
Continuous Semi-Supervised Nonnegative Matrix Factorization
Nonnegative matrix factorization can be used to automatically detect topics within a corpus in an unsupervised fashion.
Optimal Sizing and Pricing of Renewable Power to Ammonia Systems Considering the Limited Flexibility of Ammonia Synthesis
This paper proposes an optimal sizing and pricing method for RePtA system planning.
3D-EPI Blip-Up/Down Acquisition (BUDA) with CAIPI and Joint Hankel Structured Low-Rank Reconstruction for Rapid Distortion-Free High-Resolution T2* Mapping
Purpose: This work aims to develop a novel distortion-free 3D-EPI acquisition and image reconstruction technique for fast and robust, high-resolution, whole-brain imaging as well as quantitative T2* mapping.
Affine Transformation Edited and Refined Deep Neural Network for Quantitative Susceptibility Mapping
We propose an end-to-end AFfine Transformation Edited and Refined (AFTER) deep neural network for QSM, which is robust against arbitrary acquisition orientation and spatial resolution up to 0. 6 mm isotropic at the finest.
Watermarking for Out-of-distribution Detection
Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models.
Ranked #21 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
Is Out-of-Distribution Detection Learnable?
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
Cluster and Aggregate: Face Recognition with Large Probe Set
Advances in attention and recurrent modules have led to feature fusion that can model the relationship among the images in the input set.
Ranked #1 on
Face Verification
on IJB-B
(TAR @ FAR=0.001 metric)
Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization
Domain generalization (DG) enables generalizing a learning machine from multiple seen source domains to an unseen target one.
A Perceptual Quality Metric for Video Frame Interpolation
In this paper, we present a dedicated perceptual quality metric for measuring video frame interpolation results.
A Uniform Representation Learning Method for OCT-based Fingerprint Presentation Attack Detection and Reconstruction
For reconstruction performance, our method achieves the best performance with 0. 834 mIOU and 0. 937 PA. By comparing with the recognition performance on surface 2D fingerprints, the effectiveness of our proposed method on high quality subsurface fingerprint reconstruction is further proved.
Two-Stage Submodular Optimization of Dynamic Thermal Rating for Risk Mitigation Considering Placement and Operation Schedule
From the perspectives of service life and Braess paradox, it is important and challenging to jointly optimize the DTR placement and operation schedule for changing system state, which is a two-stage combinatorial problem with only discrete variables, suffering from no approximation guarantee and dimension curse only based on traditional models.
Neighborhood Collective Estimation for Noisy Label Identification and Correction
Specifically, our method is divided into two steps: 1) Neighborhood Collective Noise Verification to separate all training samples into a clean or noisy subset, 2) Neighborhood Collective Label Correction to relabel noisy samples, and then auxiliary techniques are used to assist further model optimization.
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels
In this paper, we propose a two-stage clean samples identification method to address the aforementioned challenge.
Ranked #4 on
Image Classification
on Clothing1M
(using extra training data)
Shift-tolerant Perceptual Similarity Metric
This paper studies the effect of small misalignment, specifically a small shift between the input and reference image, on existing metrics, and accordingly develops a shift-tolerant similarity metric.
Ranked #24 on
Video Quality Assessment
on MSU SR-QA Dataset
Controllable and Guided Face Synthesis for Unconstrained Face Recognition
To address this problem, we propose a controllable face synthesis model (CFSM) that can mimic the distribution of target datasets in a style latent space.
Ranked #1 on
Face Verification
on IJB-S
2D GANs Meet Unsupervised Single-view 3D Reconstruction
In light of this, we propose a novel image-conditioned neural implicit field, which can leverage 2D supervisions from GAN-generated multi-view images and perform the single-view reconstruction of generic objects.
A simple normalization technique using window statistics to improve the out-of-distribution generalization on medical images
In this study, we present a novel normalization technique called window normalization (WIN) to improve the model generalization on heterogeneous medical images, which is a simple yet effective alternative to existing normalization methods.
SNeRF: Stylized Neural Implicit Representations for 3D Scenes
This paper presents a stylized novel view synthesis method.
Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
The AutoAttack (AA) has been the most reliable method to evaluate adversarial robustness when considerable computational resources are available.
Bilateral Dependency Optimization: Defending Against Model-inversion Attacks
To defend against MI attacks, previous work utilizes a unilateral dependency optimization strategy, i. e., minimizing the dependency between inputs (i. e., features) and outputs (i. e., labels) during training the classifier.
Multi-class Classification with Fuzzy-feature Observations: Theory and Algorithms
Hence, in this paper, we propose a novel framework to address a new realistic problem called multi-class classification with imprecise observations (MCIMO), where we need to train a classifier with fuzzy-feature observations.
Incentive Mechanism Design for Emergency Frequency Control in Multi-Infeed Hybrid AC-DC System
In multi-infeed hybrid AC-DC (MIDC) systems, the emergency frequency control (EFC) with LCC-HVDC systems participating is of vital importance for system frequency stability.
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models.
Ranked #5 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Robust Representation via Dynamic Feature Aggregation
With the regularization and orthogonal classifier, a more compact embedding space can be obtained, which accordingly improves the model robustness against adversarial attacks.
A novel stereo matching pipeline with robustness and unfixed disparity search range
The new stereo matching pipeline have the following advantages: It 1) has better generalization performance than most of the current stereo matching methods; 2) relaxes the limitation of a fixed disparity search range; 3) can handle the scenes that involve both positive and negative disparities, which has more potential applications, such as view synthesis in 3D multimedia and VR/AR.
BFRnet: A deep learning-based MR background field removal method for QSM of the brain containing significant pathological susceptibility sources
The BFRnet method is compared with three conventional BFR methods and one previous deep learning method using simulated and in vivo brains from 4 healthy and 2 hemorrhagic subjects.
Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion
In this paper, we proposed an any-to-one VC method using hybrid bottleneck features extracted from CTC-BNFs and CE-BNFs to complement each other advantages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Undersampled MRI Reconstruction with Side Information-Guided Normalisation
In this paper, we investigate the use of such side information as normalisation parameters in a convolutional neural network (CNN) to improve undersampled MRI reconstruction.
Multi-channel deep convolutional neural networks for multi-classifying thyroid disease
Therefore, this study proposed a novel multi-channel convolutional neural network (CNN) architecture to address the multi-class classification task of thyroid disease.
Adversarial Attack and Defense for Non-Parametric Two-Sample Tests
Furthermore, we theoretically find that the adversary can also degrade the lower bound of a TST's test power, which enables us to iteratively minimize the test criterion in order to search for adversarial pairs.
Balanced Graph Structure Learning for Multivariate Time Series Forecasting
However, current models do not incorporate the trade-off between efficiency and flexibility and lack the guidance of domain knowledge in the design of graph structure learning algorithms.
The State of Aerial Surveillance: A Survey
The rapid emergence of airborne platforms and imaging sensors are enabling new forms of aerial surveillance due to their unprecedented advantages in scale, mobility, deployment and covert observation capabilities.
Motion-Adjustable Neural Implicit Video Representation
The model is trained end-to-end on a video to jointly determine the phase-shift values at each time with the mapping from the phase-shifted sinusoidal functions to the corresponding frame, enabling an implicit video representation.
LMR-CBT: Learning Modality-fused Representations with CB-Transformer for Multimodal Emotion Recognition from Unaligned Multimodal Sequences
Learning modality-fused representations and processing unaligned multimodal sequences are meaningful and challenging in multimodal emotion recognition.
Achieving an Accurate Random Process Model for PV Power using Cheap Data: Leveraging the SDE and Public Weather Reports
To fill this gap, this article finds that an accurate SDE model for PV power can be constructed by only using the cheap data from low-resolution public weather reports.
FRT-PAD: Effective Presentation Attack Detection Driven by Face Related Task
The proposed method, first introduces task specific features from other face related task, then, we design a Cross-Modal Adapter using a Graph Attention Network (GAT) to re-map such features to adapt to PAD task.
Fingerprint Presentation Attack Detection by Channel-wise Feature Denoising
The proposed method learns important features of fingerprint images by weighing the importance of each channel and identifying discriminative channels and "noise" channels.
Instant tissue field and magnetic susceptibility mapping from MR raw phase using Laplacian enabled deep neural networks
In addition, experiments on patients with intracranial hemorrhage and multiple sclerosis were also performed to test the generalization of the novel neural networks.
Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image
With complementary supervision from both 3D detection and reconstruction, one enables the 3D voxel features to be geometry and context preserving, benefiting both tasks. The effectiveness of our approach is demonstrated through 3D detection and reconstruction in single object and multiple object scenarios.
A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition
Firstly, we perform representation learning for audio and video modalities to obtain the semantic features of the two modalities by efficient ResNeXt and 1D CNN, respectively.
EvoGAN: An Evolutionary Computation Assisted GAN
Quantitative and Qualitative results are presented on several compound expressions, and the experimental results demonstrate the feasibility and the potential of EvoGAN.
Approaching the Transient Stability Boundary of a Power System: Theory and Applications
Estimating the stability boundary is a fundamental and challenging problem in transient stability studies.
Manifold-preserved GANs
Generative Adversarial Networks (GANs) have been widely adopted in various fields.
