Search Results for author:
Found 113 papers, 41 papers with code
L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation
Third, we propose a Dual-Density Memory Encoding Module that uses two crowd memories to learn scene-specific patterns from low- and simulated high-density scenes, respectively.
Efficient Membership Inference Attacks by Bayesian Neural Network
Membership Inference Attacks (MIAs) aim to estimate whether a specific data point was used in the training of a given model.
Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows
We curate a dataset of apo and multiple holo states of protein-ligand complexes, simulated by molecular dynamics, and propose a full-atom flow model (and a stochastic version), named DynamicFlow, that learns to transform apo pockets and noisy ligands into holo pockets and corresponding 3D ligand molecules.
Enhancing Gradient-based Discrete Sampling via Parallel Tempering
While gradient-based discrete samplers are effective in sampling from complex distributions, they are susceptible to getting trapped in local minima, particularly in high-dimensional, multimodal discrete distributions, owing to the discontinuities inherent in these landscapes.
An ocean front detection and tracking algorithm
This paper foucuses on large-scale ocean fronts and proposes an automatic front detection and tracking algorithm based on Bayesian decision and metric space.
Language-TPP: Integrating Temporal Point Processes with Language Models for Event Analysis
Temporal Point Processes (TPPs) have been widely used for event sequence modeling, but they often struggle to incorporate rich textual event descriptions effectively.
Advances in Temporal Point Processes: Bayesian, Deep, and LLM Approaches
Temporal point processes (TPPs) are stochastic process models used to characterize event sequences occurring in continuous time.
Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild
To facilitate future research, we create a multimodal mini-dataset named CapQA, which includes 1k images of fine-grained activities, for visual instruction tuning and evaluation, our proposed SQ method leads to a 31. 2% improvement in the hallucination score.
Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA
In this work, we propose a low-cost method for pruning MHA models into GQA models with any compression ratio of key-value heads.
Navigating Towards Fairness with Data Selection
Machine learning algorithms often struggle to eliminate inherent data biases, particularly those arising from unreliable labels, which poses a significant challenge in ensuring fairness.
Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regression
This work addresses a key limitation in current federated learning approaches, which predominantly focus on homogeneous tasks, neglecting the task diversity on local devices.
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
Position-aware Guided Point Cloud Completion with CLIP Model
Current methods either solely rely on the 3D coordinates of the point cloud to complete it or incorporate additional images with well-calibrated intrinsic parameters to guide the geometric estimation of the missing parts.
Human Motion Instruction Tuning
This paper presents LLaMo (Large Language and Human Motion Assistant), a multimodal framework for human motion instruction tuning.
Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Method
Recently, road graph extraction has garnered increasing attention due to its crucial role in autonomous driving, navigation, etc.
Series-to-Series Diffusion Bridge Model
Diffusion models have risen to prominence in time series forecasting, showcasing their robust capability to model complex data distributions.
Investigating the Capabilities of Deep Learning for Processing and Interpreting One-Shot Multi-offset GPR Data: A Numerical Case Study for Lunar and Martian Environments
The one-shot multi-offset configuration is investigated via a coherent numerical case study, showcasing the potential of deep learning for A) reconstructing the dielectric distribution of the the near surface of Terrestrial planets, and B) filling missing or bad-quality traces.
IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks
Implicit graph neural networks (IGNNs), which exhibit strong expressive power with a single layer, have recently demonstrated remarkable performance in capturing long-range dependencies (LRD) in underlying graphs while effectively mitigating the over-smoothing problem.
Federated Neural Nonparametric Point Processes
Temporal point processes (TPPs) are effective for modeling event occurrences over time, but they struggle with sparse and uncertain events in federated systems, where privacy is a major concern.
Is Score Matching Suitable for Estimating Point Processes?
Score matching estimators have gained widespread attention in recent years partly because they are free from calculating the integral of normalizing constant, thereby addressing the computational challenges in maximum likelihood estimation (MLE).
Nonstationary Sparse Spectral Permanental Process
Existing permanental processes often impose constraints on kernel types or stationarity, limiting the model's expressiveness.
SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images
To tackle this issue, we propose a simple and general upsampler, SimFeatUp, to restore lost spatial information in deep features in a training-free style.
Ranked #2 on
Open Vocabulary Semantic Segmentation
on iSAID
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+1
Conjugate Bayesian Two-step Change Point Detection for Hawkes Process
The Bayesian two-step change point detection method is popular for the Hawkes process due to its simplicity and intuitiveness.
HSIGene: A Foundation Model For Hyperspectral Image Generation
Some studies propose to incorporate multi-modal data to enhance spatial diversity, but the spectral fidelity cannot be ensured.
Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation
To make the patch inconspicuous to human observers, we introduce a two-stage opacity optimization mechanism, in which opacity is fine-tuned after texture optimization.
Distillation Learning Guided by Image Reconstruction for One-Shot Medical Image Segmentation
A registration-based data augmentation network creates realistic, labeled samples, while a feature distillation module helps the student network learn segmentation from these samples, guided by the teacher network.
ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality
Thus, we propose ActivityCLIP, a plug-and-play method for mining the text information contained in the action labels to supplement the image information for enhancing group activity recognition.
TransFeat-TPP: An Interpretable Deep Covariate Temporal Point Processes
The classical temporal point process (TPP) constructs an intensity function by taking the occurrence times into account.
BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation
The BiLD loss filters out the long-tail noise by utilizing only top-$k$ teacher and student logits, and leverages the internal logits ranking information by constructing logits differences.
Accelerating Convergence in Bayesian Few-Shot Classification
Bayesian few-shot classification has been a focal point in the field of few-shot learning.
OMEGAS: Object Mesh Extraction from Large Scenes Guided by Gaussian Segmentation
Moreover, to reconstruct the unseen portions of the target, we propose a novel target replenishment technique driven by large-scale generative diffusion priors.
An Evidential-enhanced Tri-Branch Consistency Learning Method for Semi-supervised Medical Image Segmentation
Additionally, the evidential fusion branch capitalizes on the complementary attributes of the first two branches and leverages an evidence-based Dempster-Shafer fusion strategy, supervised by more reliable and accurate pseudo-labels of unlabeled data.
Controllable Generation with Text-to-Image Diffusion Models: A Survey
In the rapidly advancing realm of visual generation, diffusion models have revolutionized the landscape, marking a significant shift in capabilities with their impressive text-guided generative functions.
Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiency
Fine-tuning pre-trained models is a widely employed technique in numerous real-world applications.
Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures
Deep equilibrium models (DEQs), as a typical implicit neural network, have demonstrated remarkable success on various tasks.
Bayesian Exploration of Pre-trained Models for Low-shot Image Classification
Low-shot image classification is a fundamental task in computer vision and the emergence of large-scale vision-language models such as CLIP has greatly advanced the forefront of research in this field.
Lifting by Image -- Leveraging Image Cues for Accurate 3D Human Pose Estimation
In the second stage, we allow the keypoints to further emphasize the retained critical image features.
Mitigating Label Bias in Machine Learning: Fairness through Confident Learning
In this paper, we demonstrate that despite only having access to the biased labels, it is possible to eliminate bias by filtering the fairest instances within the framework of confident learning.
Image is All You Need to Empower Large-scale Diffusion Models for In-Domain Generation
We decouple domain-related guidance from the conditional guidance used in classifier-free guidance mechanisms to preserve open-world control guidance and unconditional guidance from the pre-trained model.
Revisiting Logistic-softmax Likelihood in Bayesian Meta-Learning for Few-Shot Classification
In this context, the logistic-softmax likelihood is often employed as an alternative to the softmax likelihood in multi-class Gaussian process classification due to its conditional conjugacy property.
A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check
In recent years, Chinese Spelling Check (CSC) has been greatly improved by designing task-specific pre-training methods or introducing auxiliary tasks, which mostly solve this task in an end-to-end fashion.
IRCNN$^{+}$: An Enhanced Iterative Residual Convolutional Neural Network for Non-stationary Signal Decomposition
To address this challenge, a series of nonlinear and adaptive methods, pioneered by the empirical mode decomposition method, have been proposed.
From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
Experiments in various situations demonstrate the advantages of our method compared to strong baselines on this task.
Ranked #11 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
(using extra training data)
Textual and Visual Prompt Fusion for Image Editing via Step-Wise Alignment
The use of denoising diffusion models is becoming increasingly popular in the field of image editing.
Heterogeneous Multi-Task Gaussian Cox Processes
This paper presents a novel extension of multi-task Gaussian Cox processes for modeling multiple heterogeneous correlated tasks jointly, e. g., classification and regression, via multi-output Gaussian processes (MOGP).
Enhancing Phrase Representation by Information Bottleneck Guided Text Diffusion Process for Keyphrase Extraction
Keyphrase extraction (KPE) is an important task in Natural Language Processing for many scenarios, which aims to extract keyphrases that are present in a given document.
On the (In)Effectiveness of Large Language Models for Chinese Text Correction
Recently, the development and progress of Large Language Models (LLMs) have amazed the entire Artificial Intelligence community.
RRCNN: A novel signal decomposition approach based on recurrent residue convolutional neural network
Inspired by the successful applications of deep learning in fields like image processing and natural language processing, and given the lack in the literature of works in which deep learning techniques are used directly to decompose non-stationary signals into simple oscillatory components, we use the convolutional neural network, residual structure and nonlinear activation function to compute in an innovative way the local average of the signal, and study a new non-stationary signal decomposition method under the framework of deep learning.
An Improved Baseline Framework for Pose Estimation Challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop
This technical report describes our first-place solution to the pose estimation challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop.
Improving Crowded Object Detection via Copy-Paste
Crowdedness caused by overlapping among similar objects is a ubiquitous challenge in the field of 2D visual object detection.
IFDID: Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG
Some Natural Language Generation (NLG) tasks require both faithfulness and diversity.
Accelerated Linearized Laplace Approximation for Bayesian Deep Learning
Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of pretrained deep neural networks to Bayesian neural networks.
Design a Sustainable Micro-mobility Future: Trends and Challenges in the United States and European Union Using Natural Language Processing Techniques
To better design such a sustainable future, it is necessary to understand the trends and challenges.
De-biased Representation Learning for Fairness with Unreliable Labels
In other words, the fair pre-processing methods ignore the discrimination encoded in the labels either during the learning procedure or the evaluation stage.
Cause-and-Effect Analysis of ADAS: A Comparison Study between Literature Review and Complaint Data
Advanced driver assistance systems (ADAS) are designed to improve vehicle safety.
Towards Privacy-Preserving, Real-Time and Lossless Feature Matching
Given limited public projects in this field, codes of our method and implemented baselines are made open-source in https://github. com/IrvingMeng/SecureVector.
Deep Ensemble as a Gaussian Process Approximate Posterior
In this way, we relate DE to Bayesian inference to enjoy reliable Bayesian uncertainty.
Fully-integrated multipurpose microwave frequency identification system on a single chip
We demonstrate a fully-integrated multipurpose microwave frequency identification system on silicon-on-insulator platform.
Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters
The growing public concerns on data privacy in face recognition can be greatly addressed by the federated learning (FL) paradigm.
Basket-based Softmax
Experimentally, we demonstrate the efficiency and superiority of the BBS on the tasks of face recognition and re-identification, with both simulated and real-world datasets.
Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer
Bayesian neural networks (BNNs) have become a principal approach to alleviate overconfident predictions in deep learning, but they often suffer from scaling issues due to a large number of distribution parameters.
Continuous-time edge modelling using non-parametric point processes
The mutually-exciting Hawkes process (ME-HP) is a natural choice to model reciprocity, which is an important attribute of continuous-time edge (dyadic) data.
Disengagement Cause-and-Effect Relationships Extraction Using an NLP Pipeline
The advancement in machine learning and artificial intelligence is promoting the testing and deployment of autonomous vehicles (AVs) on public roads.
Deep Ensemble as a Gaussian Process Posterior
Deep Ensemble (DE) is a flexible, feasible, and effective alternative to Bayesian neural networks (BNNs) for uncertainty estimation in deep learning.
Additive Poisson Process: Learning Intensity of Higher-Order Interaction in Poisson Processes
We present the Additive Poisson Process (APP), a novel framework that can model the higher-order interaction effects of the intensity functions in Poisson processes using projections into lower-dimensional space.
Learning Compatible Embeddings
Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems.
PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition
Despite the great success achieved by deep learning methods in face recognition, severe performance drops are observed for large pose variations in unconstrained environments (e. g., in cases of surveillance and photo-tagging).
Predicting Driver Takeover Time in Conditionally Automated Driving
Their main effects and interaction effects on takeover time were examined.
Bias-Tolerant Fair Classification
Therefore, we propose a Bias-TolerantFAirRegularizedLoss (B-FARL), which tries to regain the benefits using data affected by label bias and selection bias.
Nonlinear Hawkes Processes in Time-Varying System
Hawkes processes are a class of point processes that have the ability to model the self- and mutual-exciting phenomena.
Robust Lightweight Facial Expression Recognition Network with Label Distribution Training
This paper presents an efficiently robust facial expression recognition (FER) network, named EfficientFace, which holds much fewer parameters but more robust to the FER in the wild.
Ranked #1 on
Facial Expression Recognition (FER)
on CAER
Unsupervised Classification for Polarimetric SAR Data Using Variational Bayesian Wishart Mixture Model with Inverse Gamma-Gamma Prior
Although various clustering methods have been successfully applied to polarimetric synthetic aperture radar (PolSAR) image clustering tasks, most of the available approaches fail to realize automatic determination of cluster number, nor have they derived an exact distribution for the number of looks.
MagFace: A Universal Representation for Face Recognition and Quality Assessment
This paper proposes MagFace, a category of losses that learn a universal feature embedding whose magnitude can measure the quality of the given face.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
Predicting Driver Fatigue in Automated Driving with Explainability
Research indicates that monotonous automated driving increases the incidence of fatigued driving.
Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models
By augmenting the data using back-translation, we doubled the sample size of the dataset and the DistilBERT model was able to obtain good performance (accuracy: 0. 972; areas under the curve: 0. 993) in detecting misinformation about COVID-19.
Coexistience of phononic six-fold, four-fold and three-fold excitations in ternary antimonide Zr3Ni3Sb4
However, these materials are uncommon because these excitations in electronic systems are usually broken by spin-orbit coupling (SOC) and normally far from the Fermi level.
Materials Science
Searching for Alignment in Face Recognition
A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing.
Body-Face Joint Detection via Embedding and Head Hook
Detecting pedestrians and their associated faces jointly is a challenging task. On one hand, body or face could be absent because of occlusion or non-frontal human pose. On the other hand, the association becomes difficult or even miss-leading in crowded scenes due to the lack of strong correlational evidence.
Learning Joint Intensity in a Multivariate Poisson Process on Statistical Manifolds
Learning of the model is achieved via convex optimization, thanks to the dually flat statistical manifold generated by the log-linear model.
Matching Guided Distillation
However, this introduces two problems: a) The adaptation module brings more parameters into training.
Visible Feature Guidance for Crowd Pedestrian Detection
Then we perform NMS only on visible bounding boxes to achieve the best fitting full box in inference.
Do not forget interaction: Predicting fatality of COVID-19 patients using logistic regression
Amid the ongoing COVID-19 pandemic, whether COVID-19 patients with high risks can be recovered or not depends, to a large extent, on how early they will be treated appropriately before irreversible consequences are caused to the patients by the virus.
Efficient Inference of Flexible Interaction in Spiking-neuron Networks
Hawkes process provides an effective statistical framework for analyzing the time-dependent interaction of neuronal spiking activities.
Additive Poisson Process: Learning Intensity of Higher-Order Interaction in Stochastic Processes
We present the Additive Poisson Process (APP), a novel framework that can model the higher-order interaction effects of the intensity functions in stochastic processes using lower dimensional projections.
Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing
Depth supervised learning has been proven as one of the most effective methods for face anti-spoofing.
Searching Central Difference Convolutional Networks for Face Anti-Spoofing
Here we propose a novel frame level FAS method based on Central Difference Convolution (CDC), which is able to capture intrinsic detailed patterns via aggregating both intensity and gradient information.
Ranked #4 on
Face Anti-Spoofing
on OULU-NPU
Deep Variational Luenberger-type Observer for Stochastic Video Prediction
Our model builds upon an variational encoder which transforms the input video into a latent feature space and a Luenberger-type observer which captures the dynamic evolution of the latent features.
Examining the Effects of Emotional Valence and Arousal on Takeover Performance in Conditionally Automated Driving
Participants with different levels of emotional valence and arousal were required to take over control from automated driving, and their takeover time and quality were analyzed.
Scalable Inference for Nonparametric Hawkes Process Using Pólya-Gamma Augmentation
In this paper, we consider the sigmoid Gaussian Hawkes process model: the baseline intensity and triggering kernel of Hawkes process are both modeled as the sigmoid transformation of random trajectories drawn from Gaussian processes (GP).
Recognizing Part Attributes with Insufficient Data
Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications.
Efficient EM-Variational Inference for Hawkes Process
In classical Hawkes process, the baseline intensity and triggering kernel are assumed to be a constant and parametric function respectively, which limits the model flexibility.
Learning Meta Model for Zero- and Few-shot Face Anti-spoofing
Therefore, we define face anti-spoofing as a zero- and few-shot learning problem.
Compact Generalized Non-local Network
The non-local module is designed for capturing long-range spatio-temporal dependencies in images and videos.
Fine-grained Video Categorization with Redundancy Reduction Attention
Specifically, it firstly summarizes the video by weight-summing all feature vectors in the feature maps of selected frames with a spatio-temporal soft attention, and then predicts which channels to suppress or to enhance according to this summary with a learned non-linear transform.
Ranked #12 on
Action Recognition
on ActivityNet
Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories
Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information.
Hyperspectral image classification using spectral-spatial LSTMs
Specifically, for each pixel, we feed its spectral values in different channels into Spectral LSTM one by one to learn the spectral feature.
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition
Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them.
Ranked #67 on
Fine-Grained Image Classification
on Stanford Cars
3D Pose Estimation for Fine-Grained Object Categories
The new dataset is available at www. umiacs. umd. edu/~wym/3dpose. html
Fine-Grained Facial Expression Analysis Using Dimensional Emotion Model
Specifically, we first mapped facial expressions into dimensional measures so that we transformed facial expression analysis from a classification problem to a regression one.
Deep Metric Learning with Angular Loss
The modern image search system requires semantic understanding of image, and a key yet under-addressed problem is to learn a good metric for measuring the similarity between images.
Kernel Pooling for Convolutional Neural Networks
We demonstrate how to approximate kernels such as Gaussian RBF up to a given order using compact explicit feature maps in a parameter-free manner.
Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network
This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework.
Ranked #13 on
Hyperspectral Image Classification
on Indian Pines
(Overall Accuracy metric, using extra
training data)
Dynamic Computational Time for Visual Attention
We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM).
Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification
In the network, the issue of spectral feature extraction is considered as a sequence learning problem, and a recurrent connection operator across the spectral domain is used to address it.
Deep Deformation Network for Object Landmark Localization
We propose a novel cascaded framework, namely deep deformation network (DDN), for localizing landmarks in non-rigid objects.
Fully Convolutional Attention Networks for Fine-Grained Recognition
Fine-grained recognition is challenging due to its subtle local inter-class differences versus large intra-class variations such as poses.
Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop
To demonstrate the effectiveness of the proposed framework, we bootstrap a fine-grained flower dataset with 620 categories from Instagram images.
Embedding Label Structures for Fine-Grained Feature Representation
However, previous studies have rarely focused on learning a fined-grained and structured feature representation that is able to locate similar images at different levels of relevance, e. g., discovering cars from the same make or the same model, both of which require high precision.
Fine-grained Image Classification by Exploring Bipartite-Graph Labels
To facilitate the study, we construct a new food benchmark dataset, which consists of 37, 885 food images collected from 6 restaurants and totally 975 menus.
Time-Mapping Using Space-Time Saliency
We describe a new approach for generating regular-speed, low-frame-rate (LFR) video from a high-frame-rate (HFR) input while preserving the important moments in the original.
Ranked #6 on
Video Salient Object Detection
on DAVSOD-Difficult20
(using extra training data)
Deformable Graph Matching
This paper proposes deformable graph matching (DGM), an extension of GM for matching graphs subject to global rigid and non-rigid geometric constraints.
Canonical Time Warping for Alignment of Human Behavior
Alignment of time series is an important problem to solve in many scientific disciplines.
