Search Results for author:
Found 243 papers, 73 papers with code
Binarized Neural Network for Single Image Super Resolution
Lighter model and faster inference are the focus of current single image super-resolution (SISR) research.
The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation
This paper describes the University of Maryland’s submissions to the WMT20 Shared Task on Chat Translation.
Multi-modal Anchor Gated Transformer with Knowledge Distillation for Emotion Recognition in Conversation
Furthermore, we introduce a multi-modal anchor gated transformer to effectively integrate utterance-level representations across modalities.
A Simple Contrastive Framework Of Item Tokenization For Generative Recommendation
Specifically, different from existing reconstruction-based strategies, SimCIT propose to use a learnable residual quantization module to align with the signals from different modalities of the items, which combines multi-modal knowledge alignment and semantic tokenization in a mutually beneficial contrastive learning framework.
Probing the Robustness of Large Language Models Safety to Latent Perturbations
Consequently, small shifts in hidden activations can re-trigger harmful behaviors embedded in the latent space.
FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution
State-of-the-art (SOTA) compressed video super-resolution (CVSR) models face persistent challenges, including prolonged inference time, complex training pipelines, and reliance on auxiliary information.
EyeSim-VQA: A Free-Energy-Guided Eye Simulation Framework for Video Quality Assessment
Free-energy-guided self-repair mechanisms have shown promising results in image quality assessment (IQA), but remain under-explored in video quality assessment (VQA), where temporal dynamics and model constraints pose unique challenges.
FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training
Recent advancements in text-to-image (T2I) generation have led to the emergence of highly expressive models such as diffusion transformers (DiTs), exemplified by FLUX.
Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?
As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress.
JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them increasingly susceptible to jailbreak attacks.
Towards Generalized Proactive Defense against Face Swapping with Contour-Hybrid Watermark
Face swapping, recognized as a privacy and security concern, has prompted considerable defensive research.
StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning
Together, StPR effectively leverages spatial semantics and temporal dynamics, achieving a unified, exemplar-free VCIL framework.
Flexible-weighted Chamfer Distance: Enhanced Objective Function for Point Cloud Completion
To address this issue, we propose a Flexible-Weighted Chamfer Distance (FCD) to guide point cloud generation.
Dim and Small Target Detection for Drone Broadcast Frames Based on Time-Frequency Analysis
As the sampling duration increases, the detection speed improves while the detection accuracy of broadcast frames termed as small targets decreases.
Pure Component Property Estimation Framework Using Explainable Machine Learning Methods
In this work, an enhanced framework for pure component property prediction by using explainable machine learning methods is proposed.
Reinforcement Learning (RL) Meets Urban Climate Modeling: Investigating the Efficacy and Impacts of RL-Based HVAC Control
This study proposes an integrated framework combining RL with an urban climate model that incorporates a building energy model, aiming to evaluate the efficacy of RL-based HVAC control across different background climates, impacts of RL strategies on indoor climate and local urban climate, and the transferability of RL strategies across cities.
ALFEE: Adaptive Large Foundation Model for EEG Representation
A channel encoder adaptively compresses variable channel information, a temporal encoder captures task-guided evolution, and a hybrid decoder reconstructs signals in both temporal and frequency domains.
Predicting Stress in Two-phase Random Materials and Super-Resolution Method for Stress Images by Embedding Physical Information
This enables a multiscale analysis of the stress concentration regions at phase boundaries.
Global Stress Generation and Spatiotemporal Super-Resolution Physics-Informed Operator under Dynamic Loading for Two-Phase Random Materials
In this study, we propose a framework for global stress generation and spatiotemporal super-resolution in TRMs under dynamic loading.
AlphaZero-Edu: Making AlphaZero Accessible to Everyone
Recent years have witnessed significant progress in reinforcement learning, especially with Zero-like paradigms, which have greatly boosted the generalization and reasoning abilities of large-scale language models.
GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM
While large language models (LLMs) have revolutionized text-to-speech (TTS) synthesis through discrete tokenization paradigms, current architectures exhibit fundamental tensions between three critical dimensions: 1) irreversible loss of acoustic characteristics caused by quantization of speech prompts; 2) stringent dependence on precisely aligned prompt speech-text pairs that limit real-world deployment; and 3) catastrophic forgetting of the LLM's native text comprehension during optimization for speech token generation.
Bridging the Gap between Continuous and Informative Discrete Representations by Random Product Quantization
Its quantization error is lower-bounded by the product of rho and epsilon-kms, where epsilon-kms denotes the quantization error of a single K-means quantizer.
WonderTurbo: Generating Interactive 3D World in 0.72 Seconds
Interactive 3D generation is gaining momentum and capturing extensive attention for its potential to create immersive virtual experiences.
HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation
However, human-object interaction (HOI) often cannot be precisely generated by current T2V models due to the lack of large-scale videos with accurate captions for HOI.
Drone Remote Identification Based on Zadoff-Chu Sequences and Time-Frequency Images
Cross-correlation is performed between locally generated ZC sequences and drone signals to derive ZC sequence-based features.
Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV Systems
Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications.
Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which innovatively integrates sparse semantic IDs and dense vectors through a cascading process.
Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning
The effectiveness of instruction fine-tuning for Large Language Models is fundamentally constrained by the quality and efficiency of training datasets.
A Single-Frame and Multi-Frame Cascaded Image Super-Resolution Method
In this paper, we propose a novel two-step image super resolution method concatenating multi-frame super-resolution (MFSR) with single-frame super-resolution (SFSR), to progressively upsample images to the desired resolution.
Inference-to-complete: A High-performance and Programmable Data-plane Co-processor for Neural-network-driven Traffic Analysis
The programmable run-to-completion accelerators are developed for flexible inference.
Performance-Driven QUBO for Recommender Systems on Quantum Annealers
We propose Counterfactual Analysis Quadratic Unconstrained Binary Optimization (CAQUBO) to solve QUBO problems for feature selection in recommender systems.
MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Construction
We propose MemFusionMap, a novel temporal fusion model with enhanced temporal reasoning capabilities for online HD map construction.
Infrared and Visible Image Fusion with Hierarchical Human Perception
Existing methods take pixel intensity, texture and high-level vision task information as the standards to determine preservation of information, lacking enhancement for human perception.
DiffFAS: Face Anti-Spoofing via Generative Diffusion Models
Based on our analysis, we propose DiffFAS framework, which quantifies quality as prior information input into the network to counter image quality shift, and performs diffusion-based high-fidelity cross-domain and cross-attack types generation to counter image style shift.
SDformer: Efficient End-to-End Transformer for Depth Completion
The network consists of an input module for the depth map and RGB image features extraction and concatenation, a U-shaped encoder-decoder Transformer for extracting deep features, and a refinement module.
AgileIR: Memory-Efficient Group Shifted Windows Attention for Agile Image Restoration
Thus, we introduce AgileIR, group shifted attention mechanism along with window attention, which sparsely simplifies the model in architecture.
Spectrum Prediction With Deep 3D Pyramid Vision Transformer Learning
Based on the Deep- SPred, we first propose a novel 3D spectrum prediction method combining a flow processing strategy with 3D vision Transformer (ViT, i. e., Swin) and a pyramid to serve possible applications such as spectrum monitoring task, named 3D-SwinSTB.
Towards Cross-View-Consistent Self-Supervised Surround Depth Estimation
This paper proposes an efficient and consistent pose estimation design and two loss functions to enhance cross-view consistency for SSSDE.
CRUISE on Quantum Computing for Feature Selection in Recommender Systems
In this paper, we use Quantum Annealers to address the feature selection problem in recommendation algorithms.
Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment
Our results show that these methods significantly improve refusal rates and reduce unsafe content, with cross-model distilling achieving refusal rates close to Claude3's 94. 51%.
Pulmonary Embolism Mortality Prediction Using Multimodal Learning Based on Computed Tomography Angiography and Clinical Data
Imaging features and/or clinical variables were then incorporated into DL models to predict survival outcomes.
An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition
Significant action recognition performance is achieved when evaluated on the challenging NTU RGB+D, NTU RGB+D 120, and PKU-MMD benchmarks and validate that multi-granularity semantic features facilitate the differentiation of action clusters with similar visual features.
Multi-Channel Multi-Step Spectrum Prediction Using Transformer and Stacked Bi-LSTM
The advantage of this fusion mode is that it can deeply capture the long-term dependence of multichannel spectrum data.
MindSemantix: Deciphering Brain Visual Experiences with a Brain-Language Model
MindSemantix generates high-quality captions that are deeply rooted in the visual and semantic information derived from brain activity.
Multi-modality Regional Alignment Network for Covid X-Ray Survival Prediction and Report Generation
In response to the worldwide COVID-19 pandemic, advanced automated technologies have emerged as valuable tools to aid healthcare professionals in managing an increased workload by improving radiology report generation and prognostic analysis.
High-dimensional multiple imputation (HDMI) for partially observed confounders including natural language processing-derived auxiliary covariates
HDMI approaches may decrease bias in studies with partially observed confounders where missingness depends on unobserved factors.
SAM3D: Zero-Shot Semi-Automatic Segmentation in 3D Medical Images with the Segment Anything Model
We introduce SAM3D, a new approach to semi-automatic zero-shot segmentation of 3D images building on the existing Segment Anything Model.
Region-specific Risk Quantification for Interpretable Prognosis of COVID-19
The COVID-19 pandemic has strained global public health, necessitating accurate diagnosis and intervention to control disease spread and reduce mortality rates.
Towards Balanced RGB-TSDF Fusion for Consistent Semantic Scene Completion by 3D RGB Feature Completion and a Classwise Entropy Loss Function
To address this RGB-TSDF distribution difference, we propose a two-stage network with a 3D RGB feature completion module that completes RGB features with meaningful values for occluded areas.
Policy Bifurcation in Safe Reinforcement Learning
Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems.
TBI Image/Text (TBI-IT): Comprehensive Text and Image Datasets for Traumatic Brain Injury Research
In this paper, we introduce a new dataset in the medical field of Traumatic Brain Injury (TBI), called TBI-IT, which includes both electronic medical records (EMRs) and head CT images.
LocalGCL: Local-aware Contrastive Learning for Graphs
Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings.
Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessment
Firstly, we devise a new diffusion restoration network that leverages the produced enhanced image and noise-containing images, incorporating nonlinear features obtained during the denoising process of the diffusion model, as high-level visual information.
Advancing GenAI Assisted Programming--A Comparative Study on Prompt Efficiency and Code Quality Between GPT-4 and GLM-4
Our GenAI Coding Workshop highlights the effectiveness and accessibility of the prompting methodology developed in this study.
Contrasting Adversarial Perturbations: The Space of Harmless Perturbations
However, in this work, we reveal the existence of a harmless perturbation space, in which perturbations drawn from this space, regardless of their magnitudes, leave the network output unchanged when applied to inputs.
A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
To address this research gap, we conducted an extensive empirical study on Multilingual Jailbreak attacks.
HICH Image/Text (HICH-IT): Comprehensive Text and Image Datasets for Hypertensive Intracerebral Hemorrhage Research
Index Terms-HICH, Deep learning, Intraparenchymal hemorrhage, named entity recognition, novel dataset
Progress and Prospects in 3D Generative AI: A Technical Overview including 3D human
Since the year 2023 an abundant amount of research papers has emerged in the domain of 3D generation.
DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query
In DeLR, the query is based on region-level, and we only annotate the object region that is queried; 2) Instead of directly providing both localization and recognition annotations, we separately query the two components, and thus reduce the recognition budget with the pseudo class labels provided by the model.
A Dual Domain Multi-exposure Image Fusion Network based on the Spatial-Frequency Integration
Specifically, we introduce a Spatial-Frequency Fusion Block to facilitate efficient interaction between dual domains and capture complementary information from input images with different exposures.
Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking
In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction, improving the graph neural network's feature representation capability.
A Multi-scale Information Integration Framework for Infrared and Visible Image Fusion
In this study, we propose a multi-scale dual attention (MDA) framework for infrared and visible image fusion, which is designed to measure and integrate complementary information in both structure and loss function at the image and patch level.
EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model
To further clarify the noise of expanded boundaries, we combine mutual learning with a tailored proposal-level contrastive objective to use a learnable approach to harmonize a balance between incomplete yet clean (initial) and comprehensive yet noisy (expanded) boundaries for more precise ones.
Viewport Prediction for Volumetric Video Streaming by Exploring Video Saliency and Trajectory Information
To our knowledge, this is the first comprehensive study of viewport prediction in volumetric video streaming.
Joint Design of ISAC Waveform under PAPR Constraints
In this paper, we formulate the precoding problem of integrated sensing and communication (ISAC) waveform as a non-convex quadratically constrainted quadratic program (QCQP), in which the weighted sum of communication multi-user interference (MUI) and the gap between dual-use waveform and ideal radar waveform is minimized with peak-to-average power ratio (PAPR) constraints.
Audio-visual Saliency for Omnidirectional Videos
Visual saliency prediction for omnidirectional videos (ODVs) has shown great significance and necessity for omnidirectional videos to help ODV coding, ODV transmission, ODV rendering, etc..
Robust and Communication-Efficient Federated Domain Adaptation via Random Features
As a result, there is a growing trend to leverage federated learning (FL) techniques to train large ML models in a distributed and collaborative manner.
Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps
We propose a novel framework to integrate SD maps into online map prediction and propose a Transformer-based encoder, SD Map Encoder Representations from transFormers, to leverage priors in SD maps for the lane-topology prediction task.
Optimization Landscape of Policy Gradient Methods for Discrete-time Static Output Feedback
Despite the absence of convexity, we leverage these properties to derive novel findings regarding convergence (and nearly dimension-free rate) to stationary points for three policy gradient methods, including the vanilla policy gradient method, the natural policy gradient method, and the Gauss-Newton method.
Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration
We also show that a modified version of regularized policy iteration, i. e., with finite-step policy evaluation, is equivalent to inexact Newton method where the Newton iteration formula is solved with truncated iterations.
User Experience Design Professionals' Perceptions of Generative Artificial Intelligence
They emphasized the unique human factors of "enjoyment" and "agency", where humans remain the arbiters of "AI alignment".
Learning Optimal Robust Control of Connected Vehicles in Mixed Traffic Flow
Connected and automated vehicles (CAVs) technologies promise to attenuate undesired traffic disturbances.
A boundary-aware point clustering approach in Euclidean and embedding spaces for roof plane segmentation
To solve this problem, we propose a boundary-aware point clustering approach in Euclidean and embedding spaces constructed by a multi-task deep network for roof plane segmentation.
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.
Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
Knowledge from animals and humans inspires robotic innovations.
HODN: Disentangling Human-Object Feature for HOI Detection
However, these methods ignore the relationship among humans, objects, and interactions: 1) human features are more contributive than object ones to interaction prediction; 2) interactive information disturbs the detection of objects but helps human detection.
ChinaTelecom System Description to VoxCeleb Speaker Recognition Challenge 2023
This technical report describes ChinaTelecom system for Track 1 (closed) of the VoxCeleb2023 Speaker Recognition Challenge (VoxSRC 2023).
Improving Human-Object Interaction Detection via Virtual Image Learning
Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects, which plays a curtail role in high-level semantic understanding tasks.
UniAP: Unifying Inter- and Intra-Layer Automatic Parallelism by Mixed Integer Quadratic Programming
To the best of our knowledge, UniAP is the first parallel method that can jointly optimize the two categories of parallel strategies to find an optimal solution.
A novel integrated method of detection-grasping for specific object based on the box coordinate matching
Furthermore, a detection-grasping integrated algorithm based on box coordinate matching (DG-BCM) is proposed to obtain the fusion model of object detection and grasp estimation.
MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection
Advanced manipulation techniques have provided criminals with opportunities to make social panic or gain illicit profits through the generation of deceptive media, such as forged face images.
Quantum-Enhanced Diamond Molecular Tension Microscopy for Quantifying Cellular Forces
The constant interplay and information exchange between cells and their micro-environment are essential to their survival and ability to execute biological functions.
SMC-UDA: Structure-Modal Constraint for Unsupervised Cross-Domain Renal Segmentation
Medical image segmentation based on deep learning often fails when deployed on images from a different domain.
Temporal Gradient Inversion Attacks with Robust Optimization
We investigate a Temporal Gradient Inversion Attack with a Robust Optimization framework, called TGIAs-RO, which recovers private data without any prior knowledge by leveraging multiple temporal gradients.
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
Also, humans have brain regions dedicated to understanding the minds of others and analyzing their intentions, such as the medial prefrontal cortex of the temporal lobe.
Ranked #3 on
Skeleton Based Action Recognition
on NTU RGB+D 120
(using extra training data)
Tracking through Containers and Occluders in the Wild
Tracking objects with persistence in cluttered and dynamic environments remains a difficult challenge for computer vision systems.
Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint
The proposed Bi-SCC firstly adopts a temporal context augmentation to generate an augmented video that breaks the correlation between positive actions and their co-scene actions in the inter-video; Then, a semantic consistency constraint (SCC) is used to enforce the predictions of the original video and augmented video to be consistent, hence suppressing the co-scene actions.
BS-GAT Behavior Similarity Based Graph Attention Network for Network Intrusion Detection
To address the above issue, this paper proposes a graph neural network algorithm based on behavior similarity (BS-GAT) using graph attention network.
What's in a Name? Beyond Class Indices for Image Recognition
In this paper, we reconsider the recognition problem and task a vision-language model with assigning class names to images given only a large (essentially unconstrained) vocabulary of categories as prior information.
MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification
Furthermore, to better disentangle the modality-relevant features and the modality-irrelevant features, we propose a novel Center-Quadruplet Causal (CQC) loss to encourage the network to effectively learn the modality-relevant features and the modality-irrelevant features.
Viewpoint Equivariance for Multi-View 3D Object Detection
We design view-conditioned queries at the output level, which enables the generation of multiple virtual frames during training to learn viewpoint equivariance by enforcing multi-view consistency.
Adaptive incentive for cross-silo federated learning: A multi-agent reinforcement learning approach
To overcome these limitations, we propose a novel adaptive mechanism for cross-silo FL, towards incentivizing organizations to contribute data to maximize their long-term payoffs in a real dynamic training environment.
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects.
Predicting Molecule-Target Interaction by Learning Biomedical Network and Molecule Representations
Most existing methodologies utilize either biomedical network information or molecule structural features to predict potential interaction link.
Multi-scale multi-modal micro-expression recognition algorithm based on transformer
A micro-expression is a spontaneous unconscious facial muscle movement that can reveal the true emotions people attempt to hide.
A Novel Improved Mask RCNN for Multiple Targets Detection in the Indoor Complex Scenes
However, indoor scenes are usually complex and there are many types of interference factors, leading to great challenges in the multiple targets detection.
Breaking the "Object" in Video Object Segmentation
Yet, this important phenomenon is largely absent from existing video object segmentation (VOS) benchmarks.
ShaSTA: Modeling Shape and Spatio-Temporal Affinities for 3D Multi-Object Tracking
To address these issues in a unified framework, we propose to learn shape and spatio-temporal affinities between tracks and detections in consecutive frames.
Automatic Change-Point Detection in Time Series via Deep Learning
We show how to automatically generate new offline detection methods based on training a neural network.
Reconstruction of compressed spectral imaging based on global structure and spectral correlation
To take full exploration of the constraints between spectra, the coefficients corresponding to the convolution kernel are constrained by the L_(2, 1)norm to improve spectral accuracy.
Depth Is All You Need for Monocular 3D Detection
Our methods leverage commonly available LiDAR or RGB videos during training time to fine-tune the depth representation, which leads to improved 3D detectors.
Seen to Unseen: When Fuzzy Inference System Predicts IoT Device Positioning Labels That Had Not Appeared in Training Phase
Situating at the core of Artificial Intelligence (AI), Machine Learning (ML), and more specifically, Deep Learning (DL) have embraced great success in the past two decades.
Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition
Experimental results show that the proposed model achieves competitive performance with 1/3 of the parameters of the encoder, compared with the full-parameter model.
Seeking Subjectivity in Visual Emotion Distribution Learning
In psychology, the \textit{Object-Appraisal-Emotion} model has demonstrated that each individual's emotion is affected by his/her subjective appraisal, which is further formed by the affective memory.
TransFA: Transformer-based Representation for Face Attribute Evaluation
The multiple branches transformer is employed to explore the inter-correlation between different attributes in similar semantic regions for attribute feature learning.
SpOT: Spatiotemporal Modeling for 3D Object Tracking
In this work, we develop a holistic representation of traffic scenes that leverages both spatial and temporal information of the actors in the scene.
Digital-twin-enhanced metal tube bending forming real-time prediction method based on Multi-source-input MTL
To address this issue, a digital-twin-enhanced (DT-enhanced) metal tube bending forming real-time prediction method based on multi-source-input multi-task learning (MTL) is proposed.
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?
Building 3D perception systems for autonomous vehicles that do not rely on high-density LiDAR is a critical research problem because of the expense of LiDAR systems compared to cameras and other sensors.
Autonomous Vehicles
Bird's-Eye View Semantic Segmentation
+1
An Indoor Environment Sensing and Localization System via mmWave Phased Array
At the end, we show that the reconstructed room layout can be utilized to locate a mobile device according to its AoA spectrum, even with single access point.
FairGAN: GANs-based Fairness-aware Learning for Recommendations with Implicit Feedback
To fill this gap, we propose a Generative Adversarial Networks (GANs) based learning algorithm FairGAN mapping the exposure fairness issue to the problem of negative preferences in implicit feedback data.
Object Permanence Emerges in a Random Walk along Memory
This paper proposes a self-supervised objective for learning representations that localize objects under occlusion - a property known as object permanence.
Passive Motion Detection via mmWave Communication System
Relying on the passive sensing system, a dataset of received signals, where three types of hand gestures are sensed, is collected by using Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) paths as the reference channel respectively.
On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach
Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations.
Spherical Convolution empowered FoV Prediction in 360-degree Video Multicast with Limited FoV Feedback
Most of the current prediction methods combining saliency detection and FoV information neither take into account that the distortion of projected 360-degree videos can invalidate the weight sharing of traditional convolutional networks, nor do they adequately consider the difficulty of obtaining complete multi-user FoV information, which degrades the prediction performance.
One-Bit Active Query With Contrastive Pairs
The Yes query is treated as positive pairs of the queried category for contrastive pulling, while the No query is treated as hard negative pairs for contrastive repelling.
Learning to Learn Transferable Attack
By treating the attack of both specific data and a modified model as a task, we expect the adversarial perturbations to adopt enough tasks for generalization.
Fully Attentional Network for Semantic Segmentation
Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation.
Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides
Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.
Image-specific Convolutional Kernel Modulation for Single Image Super-resolution
Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples.
Denoised Non-Local Neural Network for Semantic Segmentation
Without any external training data, our proposed Denoised NL can achieve the state-of-the-art performance of 83. 5\% and 46. 69\% mIoU on Cityscapes and ADE20K, respectively.
Bone Marrow Cell Recognition: Training Deep Object Detection with A New Loss Function
Therefore, it is crucial to study a robust bone marrow cell detection algorithm for a quantitative automatic analysis system.
Mining for Potent Inhibitors through Artificial Intelligence and Physics: A Unified Methodology for Ligand Based and Structure Based Drug Design
The viability of a new drug molecule is a time and resource intensive task that makes computer-aided assessments a vital approach to rapid drug discovery.
FedIPR: Ownership Verification for Federated Deep Neural Network Models
To address these risks, the ownership verification of federated learning models is a prerequisite that protects federated learning model intellectual property rights (IPR) i. e., FedIPR.
Geometry-Based Stochastic Line-of-Sight Probability Model for A2G Channels under Urban Scenarios
Line-of-sight (LoS) path is essential for the reliability of air-to-ground (A2G) communications, but the existence of LoS path is difficult to predict due to random obstacles on the ground.
Stimuli-Aware Visual Emotion Analysis
Then, we design three specific networks, i. e., Global-Net, Semantic-Net and Expression-Net, to extract distinct emotional features from different stimuli simultaneously.
An Integrated Framework for the Heterogeneous Spatio-Spectral-Temporal Fusion of Remote Sensing Images
Images from many remote sensing satellites, including MODIS, Landsat-8, Sentinel-1, and Sentinel-2, are utilized in the experiments.
LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision
Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets.
Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion
In this paper, we systematically investigate the coupling of model-driven and data-driven methods, which has rarely been considered in the remote sensing image restoration and fusion communities.
Is Pseudo-Lidar needed for Monocular 3D Object detection?
Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors.
Ranked #1 on
Monocular 3D Object Detection
on KITTI Pedestrian Moderate
(using extra training data)
A Dynamic 3D Spontaneous Micro-expression Database: Establishment and Evaluation
Micro-expressions are spontaneous, unconscious facial movements that show people's true inner emotions and have great potential in related fields of psychological testing.
Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
UGV-KPNet is computationally efficient with a small number of parameters and provides pixel-level accurate keypoints detection results in real-time.
Wideband photonic blind source separation with optical pulse sampling
The ultra-fast optical pulse functions as a tweezer that collects samples of the signals at very low sampling rates, and each sample is short enough to maintain the statistical properties of the signals.
Integrated Sensing and Communication from Learning Perspective: An SDP3 Approach
Characterizing the sensing and communication performance tradeoff in integrated sensing and communication (ISAC) systems is challenging in the applications of learning-based human motion recognition.
Fully Polarimetric SAR and Single-Polarization SAR Image Fusion Network
The data fusion technology aims to aggregate the characteristics of different data and obtain products with multiple data advantages.
IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement
3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level features.
A Circular-Structured Representation for Visual Emotion Distribution Learning
Visual Emotion Analysis (VEA) has attracted increasing attention recently with the prevalence of sharing images on social networks.
Learning the Non-Differentiable Optimization for Blind Super-Resolution
Instead of considering iterative strategy, we make the blur kernel predictor trainable in the whole blind SR model, in which AMNet is well-trained.
Inverse Simulation: Reconstructing Dynamic Geometry of Clothed Humans via Optimal Control
Inspired by the theory of optimal control, we optimize the body states such that the simulated cloth motion is matched to the point cloud measurements, and the analytic gradient of the simulator is back-propagated to update the body states.
Hierarchical Lovasz Embeddings for Proposal-Free Panoptic Segmentation
We use a hierarchical Lovasz hinge loss to learn a low-dimensional embedding space structured into a unified semantic and instance hierarchy without requiring separate network branches or object proposals.
GPLA-12: An Acoustic Signal Dataset of Gas Pipeline Leakage
In this paper, we introduce a new acoustic leakage dataset of gas pipelines, called as GPLA-12, which has 12 categories over 684 training/testing acoustic signals.
Hierarchical Lovász Embeddings for Proposal-free Panoptic Segmentation
We use a hierarchical Lov\'asz hinge loss to learn a low-dimensional embedding space structured into a unified semantic and instance hierarchy without requiring separate network branches or object proposals.
Semi-supervised Contrastive Learning with Similarity Co-calibration
Semi-supervised learning acts as an effective way to leverage massive unlabeled data.
Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack
We argue this is due to the lack of rich information in the probability prediction and the overfitting caused by hard labels.
Exploring Multi-dimensional Data via Subset Embedding
The core of the approach is a subset embedding network (SEN) that represents a group of subsets as uniformly-formatted embeddings.
Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model
Although wireless channel models can be adopted for dataset generation, current channel models are mostly designed for communication rather than sensing.
Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).
Geometric Unsupervised Domain Adaptation for Semantic Segmentation
Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation.
Transitional Learning: Exploring the Transition States of Degradation for Blind Super-resolution
Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally time-consuming and less effective, as the estimation of degradation proceeds from a blind initialization and lacks interpretable degradation priors.
Learning to Track with Object Permanence
In this work, we introduce an end-to-end trainable approach for joint object detection and tracking that is capable of such reasoning.
Approximate Optimal Filter for Linear Gaussian Time-invariant Systems
The equivalence holds given certain conditions about initial state distributions and policy formats, in which the system state is the estimation error, control input is the filter gain, and control objective function is the accumulated estimation error.
Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model
Formally, MPG is constructed as a weighted average of the data-driven and model-driven PGs, where the former is the derivative of the learned Q-value function, and the latter is that of the model-predictive return.
Real-time tracking of COVID-19 and coronavirus research updates through text mining
The novel coronavirus (SARS-CoV-2) which causes COVID-19 is an ongoing pandemic.
Enhance Information Propagation for Graph Neural Network by Heterogeneous Aggregations
Graph neural networks are emerging as continuation of deep learning success w. r. t.
DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds
In this paper, we put forward a novel density-oriented PointNet (DPointNet) for 3D object detection in point clouds, in which the density of points increases layer by layer.
Long time-series NDVI reconstruction in cloud-prone regions via spatio-temporal tensor completion
The applications of Normalized Difference Vegetation Index (NDVI) time-series data are inevitably hampered by cloud-induced gaps and noise.
Heterogeneous Graph based Deep Learning for Biomedical Network Link Prediction
Multi-scale biomedical knowledge networks are expanding with emerging experimental technologies that generates multi-scale biomedical big data.
Curvature-based Feature Selection with Application in Classifying Electronic Health Records
Disruptive technologies provides unparalleled opportunities to contribute to the identifications of many aspects in pervasive healthcare, from the adoption of the Internet of Things through to Machine Learning (ML) techniques.
Aha! Adaptive History-Driven Attack for Decision-Based Black-Box Models
A common practice is to start from a large perturbation and then iteratively reduce it with a deterministic direction and a random one while keeping it adversarial.
Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving
Second, we propose to learn a metric that combines the Mahalanobis and feature distances when comparing a track and a new detection in data association.
Ranked #3 on
3D Pedestrian Tracking
on nuScenes validation set
Skeleton-based Approaches based on Machine Vision: A Survey
Recently, skeleton-based approaches have achieved rapid progress on the basis of great success in skeleton representation.
Two-Dimensional Multifunctional Materials from Endohedral Fullerenes
A new multifunctional 2D material is theoretically predicted based on systematic ab-initio calculations and model simulations for the honeycomb lattice of endohedral fullerene W@C28 molecules.
Materials Science Computational Physics
Coherent mechanical noise cancellation and cooperativity competition in optomechanical arrays
Studying the interplay between multiple coupled mechanical resonators is a promising new direction in the field of optomechanics.
Optics Mesoscale and Nanoscale Physics
6 GHz hyperfast rotation of an optically levitated nanoparticle in vacuum
We measure a highest rotation frequency about 4. 3 GHz of the trapped nanoparticle without feedback cooling and a 6 GHz rotation with feedback cooling, which is the fastest mechanical rotation ever reported to date.
Optics Mesoscale and Nanoscale Physics Quantum Physics
Anatomy of Multipath BGP Deployment in a Large ISP Network
Our work provides insights into the latest deployment of M-BGP in a major ISP network and it highlights the characteristics and effectiveness of M-BGP as a means to realize load sharing.
Networking and Internet Architecture
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input.
Ranked #4 on
3D Semantic Scene Completion
on SemanticKITTI
3D Semantic Scene Completion from a single RGB image
3D Semantic Segmentation
+3
Association: Remind Your GAN not to Forget
Neural networks are susceptible to catastrophic forgetting.
Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution
Hyperspectral images are crucial for many research works.
Generative and Discriminative Learning for Distorted Image Restoration
Due to the uncertainty in the distortion variation, restoring distorted images caused by liquify filter is a challenging task.
The Occurrence of Rocky Habitable Zone Planets Around Solar-Like Stars from Kepler Data
We present occurrence rates for rocky planets in the habitable zones (HZ) of main-sequence dwarf stars based on the Kepler DR25 planet candidate catalog and Gaia-based stellar properties.
Earth and Planetary Astrophysics Solar and Stellar Astrophysics
Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution
To solve them, we propose a purposeful and interpretable detail-fidelity attention network to progressively process these smoothes and details in divide-and-conquer manner, which is a novel and specific prospect of image super-resolution for the purpose on improving the detail fidelity, instead of blindly designing or employing the deep CNNs architectures for merely feature representation in local receptive fields.
A Framework of Randomized Selection Based Certified Defenses Against Data Poisoning Attacks
Random selection based defenses can achieve certified robustness by averaging the classifiers' predictions on the sub-datasets sampled from the training set.
A Density-Aware PointRCNN for 3D Object Detection in Point Clouds
We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds.
Extending Label Smoothing Regularization with Self-Knowledge Distillation
The experiment results confirm that the TC can help LsrKD and MrKD to boost training, especially on the networks they are failed.
A Light-Weight Object Detection Framework with FPA Module for Optical Remote Sensing Imagery
On the DOTA dataset, CenterFPANet mAP is 64. 00%, and FPS is 22. 2, which is close to the accuracy of the anchor-based methods currently used and much faster than them.
Align Deep Features for Oriented Object Detection
However most of existing methods rely on heuristically defined anchors with different scales, angles and aspect ratios and usually suffer from severe misalignment between anchor boxes and axis-aligned convolutional features, which leads to the common inconsistency between the classification score and localization accuracy.
Ranked #26 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
PillarFlow: End-to-end Birds-eye-view Flow Estimation for Autonomous Driving
In autonomous driving, accurately estimating the state of surrounding obstacles is critical for safe and robust path planning.
Giant magnetic anisotropy energy and long coherence time of uranium substitution on defected Al2O3(0001)
Nanomagnets with giant magnetic anisotropy energy and long coherence time are desired for various technological innovations such as quantum information procession and storage.
Materials Science Computational Physics
Ternary Policy Iteration Algorithm for Nonlinear Robust Control
The simulation results show that the TPI algorithm can converge to the optimal solution for the linear plant, and has high resistance to disturbances for the nonlinear plant.
Balanced Symmetric Cross Entropy for Large Scale Imbalanced and Noisy Data
Deep convolution neural network has attracted many attentions in large-scale visual classification task, and achieves significant performance improvement compared to traditional visual analysis methods.
Weakly Supervised Temporal Action Localization with Segment-Level Labels
Specifically, we devise a partial segment loss regarded as a loss sampling to learn integral action parts from labeled segments.
Collaborative Boundary-aware Context Encoding Networks for Error Map Prediction
Further, we propose a context encoding module to utilize the global predictor from the error map to enhance the feature representation and regularize the networks.
Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition
Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios.
Projection & Probability-Driven Black-Box Attack
For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.
Anisotropic Convolutional Networks for 3D Semantic Scene Completion
In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely.
A Big Data Enabled Channel Model for 5G Wireless Communication Systems
This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling.
Semantically-Guided Representation Learning for Self-Supervised Monocular Depth
Instead of using semantic labels and proxy losses in a multi-task approach, we propose a new architecture leveraging fixed pretrained semantic segmentation networks to guide self-supervised representation learning via pixel-adaptive convolutions.
3D Gated Recurrent Fusion for Semantic Scene Completion
This paper tackles the problem of data fusion in the semantic scene completion (SSC) task, which can simultaneously deal with semantic labeling and scene completion.
Ranked #15 on
3D Semantic Scene Completion
on NYUv2
Facial Attribute Capsules for Noise Face Super Resolution
In the SR processing, we first generated a group of FACs from the input LR face, and then reconstructed the HR face from this group of FACs.
Video Face Super-Resolution with Motion-Adaptive Feedback Cell
Current state-of-the-art CNN methods usually treat the VSR problem as a large number of separate multi-frame super-resolution tasks, at which a batch of low resolution (LR) frames is utilized to generate a single high resolution (HR) frame, and running a slide window to select LR frames over the entire video would obtain a series of HR frames.
Image Fine-grained Inpainting
Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones.
Depth Based Semantic Scene Completion with Position Importance Aware Loss
We propose PALNet, a novel hybrid network for SSC based on single depth.
Probabilistic 3D Multi-Object Tracking for Autonomous Driving
Our method estimates the object states by adopting a Kalman Filter.
Cloud Removal with Fusion of High Resolution Optical and SAR Images Using Generative Adversarial Networks
The approach can be roughly divided into two steps: in the first step, a specially designed convolutional neural network (CNN) translates the synthetic aperture radar (SAR) images into simulated optical images in an object-to-object manner; in the second step, the simulated optical image, together with the SAR image and the optical image corrupted by clouds, is fused to reconstruct the corrupted area by a generative adversarial network (GAN) with a particular loss function.
Ranked #8 on
Cloud Removal
on SEN12MS-CR
Speaker-aware speech-transformer
We investigate different factors of SAM.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Direct and indirect reinforcement learning
Reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks.
Real-Time Panoptic Segmentation from Dense Detections
Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution.
HighEr-Resolution Network for Image Demosaicing and Enhancing
However, plenty of studies have shown that global information is crucial for image restoration tasks like image demosaicing and enhancing.
AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results
For training, only one set of source input images is therefore provided in the challenge.
Trident Segmentation CNN: A Spatiotemporal Transformation CNN for Punctate White Matter Lesions Segmentation in Preterm Neonates
In this paper, a novel spatiotemporal transformation deep learning method called Trident Segmentation CNN (TS-CNN) is proposed to segment PWML in MR images.
Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances
Dense depth estimation from a single image is a key problem in computer vision, with exciting applications in a multitude of robotic tasks.
