Search Results for author:
Found 194 papers, 75 papers with code
Saliency Aggregation: A Data-Driven Approach
Our idea is to use data-driven approaches to saliency aggregation that appropriately consider the performance gaps among individual methods and the performance dependence of each method on individual images.
Offshore Wind Farm Layout Optimization Using Adapted Genetic Algorithm: A different perspective
In this paper we study the problem of optimal layout of an offshore wind farm to minimize the wake effect impacts.
Parallax-tolerant Image Stitching
We then pre-align input images using the optimal homography and further use content-preserving warping to locally refine the alignment.
Depth Enhancement via Low-rank Matrix Completion
Based on this subspace constraint, our method formulates depth map enhancement as a low-rank matrix completion problem.
Quantitative Analysis of Whether Machine Intelligence Can Surpass Human Intelligence
On the basis of traditional IQ, this article presents the Universal IQ test method suitable for both the machine intelligence and the human intelligence.
Casual Stereoscopic Panorama Stitching
The stitching of the right views is formulated as a labeling problem that is constrained by the stitching of the left views to make the left- and right-view panorama consistent to avoid retinal rivalry.
Kernel Fusion for Better Image Deblurring
This Gaussian Conditional Random Fields-based kernel fusion method not only models how individual kernels are fused at each kernel element but also the interaction of kernel fusion among multiple kernel elements.
On 3D Face Reconstruction via Cascaded Regression in Shape Space
Cascaded regression has been recently applied to reconstructing 3D faces from single 2D images directly in shape space, and achieved state-of-the-art performance.
A Study on Artificial Intelligence IQ and Standard Intelligent Model
Currently, potential threats of artificial intelligence (AI) to human have triggered a large controversy in society, behind which, the nature of the issue is whether the artificial intelligence (AI) system can be evaluated quantitatively.
Sketch Me That Shoe
We investigate the problem of fine-grained sketch-based image retrieval (SBIR), where free-hand human sketches are used as queries to perform instance-level retrieval of images.
Ranked #3 on
Sketch-Based Image Retrieval
on Chairs
Composition-Preserving Deep Photo Aesthetics Assessment
Deep convolutional neural network (ConvNet) methods have recently shown promising results for aesthetics assessment.
Ranked #6 on
Aesthetics Quality Assessment
on AVA
Semantic Regularisation for Recurrent Image Annotation
We propose a simple modification to the design pattern that makes learning more effective and efficient.
Heterogeneous domain adaptation: An unsupervised approach
To contribute to the research in this emerging field, this paper presents: (1) an unsupervised knowledge transfer theorem that guarantees the correctness of transferring knowledge; and (2) a principal angle-based metric to measure the distance between two pairs of domains: one pair comprises the original source and target domains and the other pair comprises two homogeneous representations of two domains.
Video Frame Interpolation via Adaptive Convolution
Video frame interpolation typically involves two steps: motion estimation and pixel synthesis.
Actor-Critic Sequence Training for Image Captioning
Generating natural language descriptions of images is an important capability for a robot or other visual-intelligence driven AI agent that may need to communicate with human users about what it is seeing.
Spatial-Semantic Image Search by Visual Feature Synthesis
We train a convolutional neural network to synthesize appropriate visual features that captures the spatial-semantic constraints from the user canvas query.
Video Frame Interpolation via Adaptive Separable Convolution
Our method develops a deep fully convolutional neural network that takes two input frames and estimates pairs of 1D kernels for all pixels simultaneously.
Ranked #8 on
Video Frame Interpolation
on Middlebury
Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition
Extensive experiments show that the proposed method can achieve the state-of-the-art accuracy in both face alignment and 3D face reconstruction, and benefit face recognition owing to its reconstructed PEN 3D face.
Intelligence Quotient and Intelligence Grade of Artificial Intelligence
Although artificial intelligence is currently one of the most interesting areas in scientific research, the potential threats posed by emerging AI systems remain a source of persistent controversy.
iVQA: Inverse Visual Question Answering
The iVQA task is to generate a question that corresponds to a given image and answer pair.
Three IQs of AI Systems and their Testing Methods
The rapid development of artificial intelligence has brought the artificial intelligence threat theory as well as the problem about how to evaluate the intelligence level of intelligent products.
Cross-City Transfer Learning for Deep Spatio-Temporal Prediction
RegionTrans aims to effectively transfer knowledge from a data-rich source city to a data-scarce target city.
Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool
The iVQA task is to generate a question that corresponds to a given image and answer pair.
Learning Environmental Sounds with Multi-scale Convolutional Neural Network
For leveraging the waveform-based features and spectrogram-based features in a single model, we introduce two-phase method to fuse the different features.
Sound Audio and Speech Processing
Context-aware Synthesis for Video Frame Interpolation
Finally, unlike common approaches that blend the pre-warped frames, our method feeds them and their context maps to a video frame synthesis neural network to produce the interpolated frame in a context-aware fashion.
Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition
This paper proposes an encoder-decoder network to disentangle shape features during 3D face reconstruction from single 2D images, such that the tasks of reconstructing accurate 3D face shapes and learning discriminative shape features for face recognition can be accomplished simultaneously.
Research on Artificial Intelligence Ethics Based on the Evolution of Population Knowledge Base
The unclear development direction of human society is a deep reason for that it is difficult to form a uniform ethical standard for human society and artificial intelligence.
Deciphering gene regulation from gene expression dynamics using deep neural network
Furthermore, the regulation network it uncovers is strikingly similar to the one inferred from experiments.
Interactive Boundary Prediction for Object Selection
Instead of relying on pre-defined low-level image features, our method adaptively predicts object boundaries according to image content and user interactions.
Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling
The DRR framework treats recommendation as a sequential decision making procedure and adopts an "Actor-Critic" reinforcement learning scheme to model the interactions between the users and recommender systems, which can consider both the dynamic adaptation and long-term rewards.
On Computation and Generalization of GANs with Spectrum Control
Specifically, we propose a new reparameterization approach for the weight matrices of the discriminator in GANs, which allows us to directly manipulate the spectra of the weight matrices through various regularizers and constraints, without intensively computing singular value decompositions.
3D Face Modeling From Diverse Raw Scan Data
Traditional 3D face models learn a latent representation of faces using linear subspaces from limited scans of a single database.
Continuous Integration of Machine Learning Models with ease.ml/ci: Towards a Rigorous Yet Practical Treatment
Continuous integration is an indispensable step of modern software engineering practices to systematically manage the life cycles of system development.
Towards High-fidelity Nonlinear 3D Face Morphable Model
By improving the nonlinear 3D morphable model in both learning objective and network architecture, we present a model which is superior in capturing higher level of details than the linear or its precedent nonlinear counterparts.
Ranked #23 on
3D Face Reconstruction
on REALY
On Computation and Generalization of Generative Adversarial Networks under Spectrum Control
Generative Adversarial Networks (GANs), though powerful, is hard to train.
Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation
Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD -- we name it wildly UDA (WUDA).
Unsupervised Domain Adaptation
Wildly Unsupervised Domain Adaptation
Evidence for $Z_{c}^{\pm}$ decays into the $ρ^{\pm} η_{c}$ final state
We study $e^{+}e^{-}$ collisions with a $\pi^{+}\pi^{-}\pi^{0}\eta_{c}$ final state using data samples collected with the BESIII detector at center-of-mass energies $\sqrt{s}=4. 226$, $4. 258$, $4. 358$, $4. 416$, and $4. 600$ GeV.
High Energy Physics - Experiment
Probabilistic Structure Learning for EEG/MEG Source Imaging with Hierarchical Graph Prior
Traditional EEG/MEG Source Imaging (ESI) methods usually assume that either source activity at different time points is unrelated, or that similar spatiotemporal patterns exist across an entire study period.
Open Set Domain Adaptation: Theoretical Bound and Algorithm
The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled (source) domain to improve a model's learning performance with an unlabeled (target) domain -- the basic strategy being to mitigate the effects of discrepancies between the two distributions.
Ranked #20 on
Domain Adaptation
on Office-Home
MemeFaceGenerator: Adversarial Synthesis of Chinese Meme-face from Natural Sentences
Chinese meme-face is a special kind of internet subculture widely spread in Chinese Social Community Networks.
Meta Learning with Relational Information for Short Sequences
This paper proposes a new meta-learning method -- named HARMLESS (HAwkes Relational Meta LEarning method for Short Sequences) for learning heterogeneous point process models from short event sequence data along with a relational network.
On Learning Disentangled Representations for Gait Recognition
The LSTM integrates pose features over time as a dynamic gait feature while canonical features are averaged as a static gait feature.
3D Ken Burns Effect from a Single Image
According to this depth estimate, our framework then maps the input image to a point cloud and synthesizes the resulting video frames by rendering the point cloud from the corresponding camera positions.
Ranked #4 on
Depth Estimation
on NYU-Depth V2
Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation
Our method employs two encoder networks to extract essential information for matting.
Ranked #11 on
Image Matting
on Composition-1K
Wildly Unsupervised Domain Adaptation and Its Powerful and Efficient Solution
Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD---we name it wildly UDA (WUDA).
Unsupervised Domain Adaptation
Wildly Unsupervised Domain Adaptation
On the Detection of Digital Face Manipulation
Instead of simply using multi-task learning to simultaneously detect manipulated images and predict the manipulated mask (regions), we propose to utilize an attention mechanism to process and improve the feature maps for the classification task.
Frosting Weights for Better Continual Training
Training a neural network model can be a lifelong learning process and is a computationally intensive one.
A Zero-Shot based Fingerprint Presentation Attack Detection System
Therefore, we propose a novel Zero-Shot Presentation Attack Detection Model to guarantee the generalization of the PAD model.
Learning Deep Kernels for Non-Parametric Two-Sample Tests
We propose a class of kernel-based two-sample tests, which aim to determine whether two sets of samples are drawn from the same distribution.
Ranked #1 on
Two-sample testing
on HIGGS Data Set
Segmentation-based Method combined with Dynamic Programming for Brain Midline Delineation
The midline related pathological image features are crucial for evaluating the severity of brain compression caused by stroke or traumatic brain injury (TBI).
Softmax Splatting for Video Frame Interpolation
In contrast, how to perform forward warping has seen less attention, partly due to additional challenges such as resolving the conflict of mapping multiple pixels to the same target location in a differentiable way.
Ranked #2 on
Video Frame Interpolation
on Middlebury
Local Facial Makeup Transfer via Disentangled Representation
In this paper, we propose a novel unified adversarial disentangling network to further decompose face images into four independent components, i. e., personal identity, lips makeup style, eyes makeup style and face makeup style.
Deep Homography Estimation for Dynamic Scenes
We then develop a multi-scale neural network and show that when properly trained using our new dataset, this neural network can already handle dynamic scenes to some extent.
xQSM-Quantitative Susceptibility Mapping with Octave Convolutional Neural Networks
Quantitative susceptibility mapping (QSM) is a valuable magnetic resonance imaging (MRI) contrast mechanism that has demonstrated broad clinical applications.
Image and Video Processing
Inter-sequence Enhanced Framework for Personalized Sequential Recommendation
Then, based on the inter-sequence correlation encoder, we build GRU network and attention network in the intra-sequence correlation encoder to model the item sequential correlation within each individual sequence and temporal dynamics for predicting users' preferences over candidate items.
Event Arguments Extraction via Dilate Gated Convolutional Neural Network with Enhanced Local Features
However, the F-Score of event arguments extraction is much lower than that of event trigger extraction, i. e. in the most recent work, event trigger extraction achieves 80. 7%, while event arguments extraction achieves only 58%.
Assessing the Impact of COVID-19 on the Objective and Analysis of Oncology Clinical Trials -- Application of the Estimand Framework
We identify key intercurrent events that may occur due to COVID-19 in oncology clinical trials with a focus on time-to-event endpoints and discuss considerations pertaining to the other estimand attributes introduced in the ICH E9 addendum.
Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation
To achieve this aim, a previous study has proven an upper bound of the target-domain risk, and the open set difference, as an important term in the upper bound, is used to measure the risk on unknown target data.
Domain Contrast for Domain Adaptive Object Detection
We present Domain Contrast (DC), a simple yet effective approach inspired by contrastive learning for training domain adaptive detectors.
Global optimization using mixed integer quadratic programming on non-convex two-way interaction truncated linear multivariate adaptive regression splines
The use of MARS maintains the flexibility of modeling within TITL-MARS-OPT while also taking advantage of the linear modeling structure of MARS to enable global optimality.
Optimization and Control
Model independent determination of the spin of the $Ω^{-}$ and its polarization alignment in $ψ(3686)\rightarrowΩ^{-}\barΩ^{+}$
We present an analysis of the process $\psi(3686) \to \Omega^- \bar{\Omega}^+$ ($\Omega^-\to K^-\Lambda$, $\bar{\Omega}^+\to K^+\bar{\Lambda}$, $\Lambda\to p\pi^-$, $\bar{\Lambda}\to \bar{p}\pi^+$) based on a data set of $448\times 10^6$ $\psi(3686)$ decays collected with the BESIII detector at the BEPCII electron-positron collider.
High Energy Physics - Experiment
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA).
Learning from a Complementary-label Source Domain: Theory and Algorithms
We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA).
Learned Dual-View Reflection Removal
Traditional reflection removal algorithms either use a single image as input, which suffers from intrinsic ambiguities, or use multiple images from a moving camera, which is inconvenient for users.
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
However, it has been shown that the MMD test is unaware of adversarial attacks -- the MMD test failed to detect the discrepancy between natural and adversarial data.
Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence
The goal of this paper is to learn dense 3D shape correspondence for topology-varying objects in an unsupervised manner.
Synchronization Instability of Inverter-Based Generation During Asymmetrical Grid Faults
In contrast, both positive- and negative-sequence synchronizations should be of concern for inverter-based generation (IBG) under asymmetrical faults.
Search for the reaction $e^{+}e^{-} \rightarrow π^{+}π^{-} χ_{cJ}$ and a charmonium-like structure decaying to $χ_{cJ}π^{\pm}$ between 4.18 and 4.60 GeV
We search for the process $e^{+}e^{-}\rightarrow \pi ^{+}\pi ^{-} \chi_{cJ}$ ($J=0, 1, 2$) and for a charged charmonium-like state in the $\pi ^{\pm} \chi_{cJ}$ subsystem.
High Energy Physics - Experiment
Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation
Compared to the previous state-of-the-art learning algorithms for non-rigid registration of face scans, SMF only requires the raw data to be rigidly aligned (with scaling) with a pre-defined face template.
A State Representation Dueling Network for Deep Reinforcement Learning
In recent years there have been many successes in boosting the performance of Deep Q-Networks (DQN).
Measurements of the center-of-mass energies of $e^{+}e^{-}$ collisions at BESIII
During the 2016-17 and 2018-19 running periods, the BESIII experiment collected 7. 5~fb$^{-1}$ of $e^+e^-$ collision data at center-of-mass energies ranging from 4. 13 to 4. 44 GeV.
High Energy Physics - Experiment
How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?
Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy.
Robust Scheduling of Virtual Power Plant under Exogenous and Endogenous Uncertainties
Virtual power plant (VPP) provides a flexible solution to distributed energy resources integration by aggregating renewable generation units, conventional power plants, energy storages, and flexible demands.
Cross section measurement of $e^+e^- \to p\bar{p}η$ and $e^+e^- \to p\bar{p}ω$ at center-of-mass energies between 3.773 GeV and 4.6 GeV
Based on $14. 7~\textrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected with the BESIII detector at the BEPCII collider at 17 different center-of-mass energies between $3. 7730~\textrm{GeV}$ and $4. 5995~\textrm{GeV}$, Born cross sections of the two processes $e^+e^- \to p\bar{p}\eta$ and $e^+e^- \to p\bar{p}\omega$ are measured for the first time.
High Energy Physics - Experiment
Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
In this paper, we demystify assumptions behind NCD and find that high-level semantic features should be shared among the seen and unseen classes.
Measurement of the absolute branching fractions for purely leptonic $D_s^+$ decays
Constraining our measurement to the Standard Model expectation of lepton universality ($R=9. 75$), we find the more precise results $\cal B(D_s^+\to \tau^+\nu_\tau) = (5. 22\pm0. 10\pm 0. 14)\times10^{-2}$ and $A_{\it CP}(\tau^\pm\nu_\tau) = (-0. 1\pm1. 9\pm1. 0)\%$.
High Energy Physics - Experiment
Group-wise Inhibition based Feature Regularization for Robust Classification
The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e. g. corrupted and adversarial samples).
Ranked #39 on
Domain Generalization
on ImageNet-C
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
Few-shot object detection has made substantial progressby representing novel class objects using the feature representation learned upon a set of base class objects.
Ranked #14 on
Few-Shot Object Detection
on MS-COCO (10-shot)
Universal Undersampled MRI Reconstruction
Simply mixing images from multiple anatomies for training a single network does not lead to an ideal universal model due to the statistical shift among datasets of various anatomies, the need to retrain from scratch on all datasets with the addition of a new dataset, and the difficulty in dealing with imbalanced sampling when the new dataset is further of a smaller size.
Accelerating Quantitative Susceptibility Mapping using Compressed Sensing and Deep Neural Network
In this study, a learning-based Deep Complex Residual Network (DCRNet) is proposed to recover both the magnitude and phase images from incoherently undersampled data, enabling high acceleration of QSM acquisition.
Deep Simultaneous Optimisation of Sampling and Reconstruction for Multi-contrast MRI
MRI images of the same subject in different contrasts contain shared information, such as the anatomical structure.
Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction
That is, for a 2D image of a generic object, we decompose it into latent representations of category, shape and albedo, lighting and camera projection matrix, decode the representations to segmented 3D shape and albedo respectively, and fuse these components to render an image well approximating the input image.
SDNet: mutil-branch for single image deraining using swin
The former implements the basic rain pattern feature extraction, while the latter fuses different features to further extract and process the image features.
Deep grey matter quantitative susceptibility mapping from small spatial coverages using deep learning
Method: A recently proposed deep learning-based QSM method, namely xQSM, is investigated to assess the accuracy of dipole inversion on reduced brain coverages.
KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation
However, in an open world, the unlabeled test images probably contain unknown categories and have different distributions from the labeled images.
TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
To this end, we propose a target orientated hypothesis adaptation network (TOHAN) to solve the FHA problem, where we generate highly-compatible unlabeled data (i. e., an intermediate domain) to help train a target-domain classifier.
Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data
In realistic scenarios with very limited numbers of data samples, however, it can be challenging to identify a kernel powerful enough to distinguish complex distributions.
Probabilistic Margins for Instance Reweighting in Adversarial Training
Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights.
Augmented Synchronization of Power Systems
Here, we formulate the empirical wisdom by the concept of augmented synchronization and aim to bridge such a theory-practice gap.
Fast Monte Carlo Rendering via Multi-Resolution Sampling
Specifically, we formulate this fusion task as a super resolution problem that generates a high resolution rendering from a low resolution input (LRHS), assisted with the HRLS rendering.
Balancing Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning
Fairness in recommendation has attracted increasing attention due to bias and discrimination possibly caused by traditional recommenders.
Learning Bounds for Open-Set Learning
In this paper, we target a more challenging and realistic setting: open-set learning (OSL), where there exist test samples from the classes that are unseen during training.
Local Reweighting for Adversarial Training
However, when tested on attacks different from the given attack simulated in training, the robustness may drop significantly (e. g., even worse than no reweighting).
StereoRel: Relational Triple Extraction from a Stereoscopic Perspective
Relational triple extraction is critical to understanding massive text corpora and constructing large-scale knowledge graph, which has attracted increasing research interest.
Escaping the Gradient Vanishing: Periodic Alternatives of Softmax in Attention Mechanism
Softmax is widely used in neural networks for multiclass classification, gate structure and attention mechanisms.
View Synthesis of Dynamic Scenes based on Deep 3D Mask Volume
Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations.
Taming Self-Supervised Learning for Presentation Attack Detection: De-Folding and De-Mixing
Even though there are numerous Presentation Attack Detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem.
Manifold-preserved GANs
Generative Adversarial Networks (GANs) have been widely adopted in various fields.
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.
Fingerprints of Super Resolution Networks
Compared to previously studied models, SISR networks are a uniquely challenging class of image generation model from which to extract and analyze fingerprints, as they can often generate images that closely match the corresponding ground truth and thus likely leave little flexibility to embed signatures.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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)
+2
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.
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.
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.
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 #3 on
Few-Shot Object Detection
on MS-COCO (30-shot)
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.
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.
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.
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.
SNeRF: Stylized Neural Implicit Representations for 3D Scenes
This paper presents a stylized novel view synthesis method.
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.
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.
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
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 #3 on
Image Classification
on Clothing1M
(using extra training data)
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.
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.
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.
A Perceptual Quality Metric for Video Frame Interpolation
In this paper, we present a dedicated perceptual quality metric for measuring video frame interpolation results.
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.
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)
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.
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 #20 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
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.
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.
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.
Continuous Semi-Supervised Nonnegative Matrix Factorization
Nonnegative matrix factorization can be used to automatically detect topics within a corpus in an unsupervised fashion.
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.
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 #7 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.
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.
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.
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.
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.
Ranked #12 on
Out-of-Distribution Detection
on ImageNet-1k vs Textures
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.
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.
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.
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
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.
Attacking Perceptual Similarity Metrics
In our study, we systematically examine the robustness of these metrics to imperceptible adversarial perturbations.
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.
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.
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.
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.
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.
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).
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.
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.
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.
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.
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.
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.
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.
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.
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.
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
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.
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.
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.
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.
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.
Fast View Synthesis of Casual Videos
Specifically, we build a global static scene model using an extended plane-based scene representation to synthesize temporally coherent novel video.
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.
Scale invariance in early embryonic development
The body plan of the fruit fly is determined by the expression of just a handful of genes.
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.
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
Privacy-Preserving Low-Rank Adaptation for Latent Diffusion Models
To mitigate this issue, we propose Stable PrivateLoRA that adapts the LDM by minimizing the ratio of the adaptation loss to the MI gain, which implicitly rescales the gradient and thus stabilizes the optimization.
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.
Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models
With the emergence of text-to-video (T2V) diffusion models, its temporal counterpart, motion customization, has not yet been well investigated.
Identification of Craving Maps among Marijuana Users via the Analysis of Functional Brain Networks with High-Order Attention Graph Neural Networks
The excessive consumption of marijuana can induce substantial psychological and social consequences.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
