Papers
Wed 9 Aug 2023
197 papers
- Leveraging the Edge and Cloud for V2X-Based Real-Time Object Detection in Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
- PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like InteractionsDiffusion models → Image generation, text-to-image and editing
- LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
- Bayesian Inverse Transition Learning for Offline SettingsOffline RL and imitation learning from data → Offline RL algorithms
- Neural Field Movement Primitives for Joint Modelling of Scenes and MotionsOffline RL and imitation learning from data → Robot learning from demonstration
- On Error Propagation of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action RecognitionKnowledge distillation → General knowledge distillation methods
- A Bipartite Graph is All We Need for Enhancing Emotional Reasoning with Commonsense KnowledgeLLM reasoning → Reasoning benchmarks and evaluation
- JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion ModelsDiffusion models → Audio, speech and music
- Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense RetrievalLLM reasoning → Knowledge- and tool-augmented reasoning
- Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QALLM reasoning → Prompting and chain-of-thought reasoning +1
- Which Tokens to Use? Investigating Token Reduction in Vision TransformersEfficient LLM inference and serving → Token pruning and merging for ViTs
- Where's the Liability in Harmful AI Speech?LLM safety and security → Prompt injection and agent security
- Towards AI enabled automated tracking of multiple boxers
- 1st Place in ICCV 2023 Workshop Challenge Track 1 on Resource Efficient Deep Learning for Computer Vision: Budgeted Model Training Challenge
- Evaluating the diversity and utility of materials proposed by generative models
- On the Unexpected Abilities of Large Language Models
- Conceptualizing Machine Learning for Dynamic Information Retrieval of Electronic Health Record Notes
- TBIN: Modeling Long Textual Behavior Data for CTR Prediction
- Variations on the Reinforcement Learning performance of Blackjack
- An Interpretable and Attention-based Method for Gaze Estimation Using Electroencephalography
- EEG-based Emotion Style Transfer Network for Cross-dataset Emotion Recognition
- Unleashing the Power of Extra-Tree Feature Selection and Random Forest Classifier for Improved Survival Prediction in Heart Failure Patients
- Unlocking the diagnostic potential of electrocardiograms through information transfer from cardiac magnetic resonance imaging
- AI4GCC -- Track 3: Consumption and the Challenges of Multi-Agent RL
- Developing a Hybrid Convolutional Neural Network for Automatic Aphid Counting in Sugar Beet Fields
- Data-driven Intra-Autonomous Systems Graph Generator
- Vector quantization loss analysis in VQGANs: a single-GPU ablation study for image-to-image synthesis
- Enhancing Architecture Frameworks by Including Modern Stakeholders and their Views/Viewpoints
- Financial Fraud Detection: A Comparative Study of Quantum Machine Learning Models
- Spatial Gated Multi-Layer Perceptron for Land Use and Land Cover Mapping
- SegMatch: A semi-supervised learning method for surgical instrument segmentation
- Training neural networks with end-to-end optical backpropagation
- Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI
- Decoding Layer Saliency in Language Transformers
- Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audio
- "Generate" the Future of Work through AI: Empirical Evidence from Online Labor Markets
- Evaluating Pedestrian Trajectory Prediction Methods with Respect to Autonomous Driving
- Hierarchical Representations for Spatio-Temporal Visual Attention Modeling and Understanding
- FPGA Resource-aware Structured Pruning for Real-Time Neural Networks
- A Unified Interactive Model Evaluation for Classification, Object Detection, and Instance Segmentation in Computer Vision
- Deep Learning for Morphological Identification of Extended Radio Galaxies using Weak Labels
- Sound propagation in realistic interactive 3D scenes with parameterized sources using deep neural operators
- Robust Object Modeling for Visual Tracking
- Discrepancy-based Active Learning for Weakly Supervised Bleeding Segmentation in Wireless Capsule Endoscopy Images
- Analyzing the Effect of Data Impurity on the Detection Performances of Mental Disorders
- Are Sex-based Physiological Differences the Cause of Gender Bias for Chest X-ray Diagnosis?
- High-Level Parallelism and Nested Features for Dynamic Inference Cost and Top-Down Attention
- Data-Free Model Extraction Attacks in the Context of Object Detection
- Two Novel Approaches to Detect Community: A Case Study of Omicron Lineage Variants PPI Network
- Scene-Generalizable Interactive Segmentation of Radiance Fields
- Improved Multi-Shot Diffusion-Weighted MRI with Zero-Shot Self-Supervised Learning Reconstruction
- DOST -- Domain Obedient Self-supervised Training for Multi Label Classification with Noisy Labels
- A degree of image identification at sub-human scales could be possible with more advanced clusters
- Organizational Bulk Email Systems: Their Role and Performance in Remote Work
- Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling
- Drones4Good: Supporting Disaster Relief Through Remote Sensing and AI
- Volumetric Fast Fourier Convolution for Detecting Ink on the Carbonized Herculaneum Papyri
- Geometric Learning-Based Transformer Network for Estimation of Segmentation Errors
- Competitions in AI -- Robustly Ranking Solvers Using Statistical Resampling
- Fine-Tune Language Models as Multi-Modal Differential Equation Solvers
- A Novel Method for improving accuracy in neural network by reinstating traditional back propagation technique
- PAT: Position-Aware Transformer for Dense Multi-Label Action Detection
- RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extraction
- Separate Anything You Describe
- Collaborative Wideband Spectrum Sensing and Scheduling for Networked UAVs in UTM Systems
- Expert load matters: operating networks at high accuracy and low manual effort
- Kairos: Practical Intrusion Detection and Investigation using Whole-system Provenance
- Density Crop-guided Semi-supervised Object Detection in Aerial Images
- An End-to-End Framework of Road User Detection, Tracking, and Prediction from Monocular Images
- Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution
- When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
- A Comprehensive Empirical Study of Bugs in Open-Source Federated Learning Frameworks
- MetRoBERTa: Leveraging Traditional Customer Relationship Management Data to Develop a Transit-Topic-Aware Language Model
- Multi-Class Deep SVDD: Anomaly Detection Approach in Astronomy with Distinct Inlier Categories
- Deep Learning Model Transfer in Forest Mapping using Multi-source Satellite SAR and Optical Images
- AspectMMKG: A Multi-modal Knowledge Graph with Aspect-aware Entities
- Foreground Object Search by Distilling Composite Image Feature
- Self-supervised Landmark Learning with Deformation Reconstruction and Cross-subject Consistency Objectives
- Exploring Multilingual Text Data Distillation
- Transferable Models for Bioacoustics with Human Language Supervision
- ModSec-AdvLearn: Countering Adversarial SQL Injections with Robust Machine Learning
- CasCIFF: A Cross-Domain Information Fusion Framework Tailored for Cascade Prediction in Social Networks
- Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning
- Improving Autonomous Separation Assurance through Distributed Reinforcement Learning with Attention Networks
- Improved Cryo-EM Pose Estimation and 3D Classification through Latent-Space Disentanglement
- Wirelessly Powered Federated Learning Networks: Joint Power Transfer, Data Sensing, Model Training, and Resource Allocation
- Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation
- Performance Analysis of Transformer Based Models (BERT, ALBERT and RoBERTa) in Fake News Detection
- Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation
- Extrapolating Large Language Models to Non-English by Aligning Languages
- Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey
- SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation
- LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking
- Gaussian Image Anomaly Detection with Greedy Eigencomponent Selection
- Differentially Private Graph Neural Network with Importance-Grained Noise Adaption
- Semantic Communications for Artificial Intelligence Generated Content (AIGC) Toward Effective Content Creation
- Integrating large language models and active inference to understand eye movements in reading and dyslexia
- An In-Depth Analysis of Discretization Methods for Communication Learning using Backpropagation with Multi-Agent Reinforcement Learning
All 197
- GeodesicPSIM: Predicting the Quality of Static Mesh with Texture Map via Geodesic Patch Similarity
- Deep Learning-Based Prediction of Fractional Flow Reserve along the Coronary Artery
- Service Reservation and Pricing for Green Metaverses: A Stackelberg Game Approach
- LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following
- Cross-view Semantic Alignment for Livestreaming Product Recognition
- SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentation
- Adversarial Deep Reinforcement Learning for Cyber Security in Software Defined Networks
- GraphCC: A Practical Graph Learning-based Approach to Congestion Control in Datacenters
- StableVQA: A Deep No-Reference Quality Assessment Model for Video Stability
- Towards true discovery of the differential equations
- Histogram-guided Video Colorization Structure with Spatial-Temporal Connection
- An Empirical Study on Using Large Language Models to Analyze Software Supply Chain Security Failures
- Transmission and Color-guided Network for Underwater Image Enhancement
- Targeted and Troublesome: Tracking and Advertising on Children's Websites
- Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance
- Information-Theoretic Characterization of Vowel Harmony: A Cross-Linguistic Study on Word Lists
- Deep Generative Networks for Heterogeneous Augmentation of Cranial Defects
- Learning multi-domain feature relation for visible and Long-wave Infrared image patch matching
- Comparing How a Chatbot References User Utterances from Previous Chatting Sessions: An Investigation of Users' Privacy Concerns and Perceptions
- Tracking Players in a Badminton Court by Two Cameras
- Decorrelating neurons using persistence
- InstantAvatar: Efficient 3D Head Reconstruction via Surface Rendering
- Learning Type-Generalized Actions for Symbolic Planning
- Emotion-Conditioned Text Generation through Automatic Prompt Optimization
- Scalability of Message Encoding Techniques for Continuous Communication Learned with Multi-Agent Reinforcement Learning
- Beyond Surprise: Improving Exploration Through Surprise Novelty
- View while Moving: Efficient Video Recognition in Long-untrimmed Videos
- TSSR: A Truncated and Signed Square Root Activation Function for Neural Networks
- VAST: Vivify Your Talking Avatar via Zero-Shot Expressive Facial Style Transfer
- MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation
- Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning
- WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields
- Evaluating the Generation Capabilities of Large Chinese Language Models
- HyperCoil-Recon: A Hypernetwork-based Adaptive Coil Configuration Task Switching Network for MRI Reconstruction
- Neuro-Symbolic RDF and Description Logic Reasoners: The State-Of-The-Art and Challenges
- CLEVA: Chinese Language Models EVAluation Platform
- Joint-Relation Transformer for Multi-Person Motion Prediction
- Generalized Unbiased Scene Graph Generation
- ADMUS: A Progressive Question Answering Framework Adaptable to Multiple Knowledge Sources
- Enhancing Mobile Privacy and Security: A Face Skin Patch-Based Anti-Spoofing Approach
- Bayes Risk Consistency of Nonparametric Classification Rules for Spike Trains Data
- NNPP: A Learning-Based Heuristic Model for Accelerating Optimal Path Planning on Uneven Terrain
- PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformer
- Multi-Scale Memory Comparison for Zero-/Few-Shot Anomaly Detection
- PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration
- Multi-View Fusion and Distillation for Subgrade Distresses Detection based on 3D-GPR
- Multi-modal Multi-view Clustering based on Non-negative Matrix Factorization
- E3-UAV: An Edge-based Energy-Efficient Object Detection System for Unmanned Aerial Vehicles
- SUnAA: Sparse Unmixing using Archetypal Analysis
- Objects do not disappear: Video object detection by single-frame object location anticipation
- Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization
- FaceSkin: A Privacy Preserving Facial skin patch Dataset for multi Attributes classification
- Automatically measuring speech fluency in people with aphasia: first achievements using read-speech data
- Tram-FL: Routing-based Model Training for Decentralized Federated Learning
- Feature Matching Data Synthesis for Non-IID Federated Learning
- Automated Driving Without Ethics: Meaning, Design and Real-World Implementation
- Bird's-Eye-View Scene Graph for Vision-Language Navigation
- Building Interpretable and Reliable Open Information Retriever for New Domains Overnight
- Collaborative Learning From Distributed Data With Differentially Private Synthetic Twin Data
- SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference
- Enhancing Efficient Continual Learning with Dynamic Structure Development of Spiking Neural Networks
- Fuzz4All: Universal Fuzzing with Large Language Models
- Optimizing a Transformer-based network for a deep learning seismic processing workflow
- Case Study: Using AI-Assisted Code Generation In Mobile Teams
- Going Deeper with Five-point Stencil Convolutions for Reaction-Diffusion Equations
- TextPainter: Multimodal Text Image Generation with Visual-harmony and Text-comprehension for Poster Design
- Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation
- JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games
- Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learning
- A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrology
- Generative Perturbation Analysis for Probabilistic Black-Box Anomaly Attribution
- Pareto Invariant Representation Learning for Multimedia Recommendation
- A Feature Set of Small Size for the PDF Malware Detection
- Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network
- GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
- An Analytical Study of Covid-19 Dataset using Graph-Based Clustering Algorithms
- Explainable AI in Orthopedics: Challenges, Opportunities, and Prospects
- Finite Element Operator Network for Solving Elliptic-type parametric PDEs
- Web crawler strategies for web pages under robot.txt restriction
- Generating News-Centric Crossword Puzzles As A Constraint Satisfaction and Optimization Problem
- Rapid Training Data Creation by Synthesizing Medical Images for Classification and Localization
- Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising
- Addressing Racial Bias in Facial Emotion Recognition
- SSL-Auth: An Authentication Framework by Fragile Watermarking for Pre-trained Encoders in Self-supervised Learning
- Resource Constrained Model Compression via Minimax Optimization for Spiking Neural Networks
- A General Implicit Framework for Fast NeRF Composition and Rendering
- Sudowoodo: a Chinese Lyric Imitation System with Source Lyrics
- Classification of lung cancer subtypes on CT images with synthetic pathological priors
- Efficient Bayesian Optimization with Deep Kernel Learning and Transformer Pre-trained on Multiple Heterogeneous Datasets
- Assessing the performance of deep learning-based models for prostate cancer segmentation using uncertainty scores
- Deep Metric Learning for the Hemodynamics Inference with Electrocardiogram Signals
- Enhancing Optimization Performance: A Novel Hybridization of Gaussian Crunching Search and Powell's Method for Derivative-Free Optimization
- Cross-Lingual Constituency Parsing for Middle High German: A Delexicalized Approach
- Long-Distance Gesture Recognition using Dynamic Neural Networks
- A Hierarchical Destroy and Repair Approach for Solving Very Large-Scale Travelling Salesman Problem
- GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priors
- Sparse Binary Transformers for Multivariate Time Series Modeling