Papers
Wed 24 Aug 2022
162 papers
- Augmenting Reinforcement Learning with Transformer-based Scene Representation Learning for Decision-making of Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
- Debias the Black-box: A Fair Ranking Framework via Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Deep Symbolic Learning: Discovering Symbols and Rules from PerceptionsLLM reasoning → Reasoning benchmarks and evaluation
- MuMUR : Multilingual Multimodal Universal RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Semi-supervised Semantic Segmentation with Mutual Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy LabelsMixture-of-experts → Vision mixture-of-experts
- AT-DDPM: Restoring Faces degraded by Atmospheric Turbulence using Denoising Diffusion Probabilistic ModelsDiffusion models → Inverse problems and image restoration
- Pixel-wise classification in graphene-detection with tree-based machine learning algorithms
- Too Fine or Too Coarse? The Goldilocks Composition of Data Complexity for Robust Left-Right Eye-Tracking Classifiers
- Automatic detection of faults in race walking from a smartphone camera: a comparison of an Olympic medalist and university athletes
- The cost of passing -- using deep learning AIs to expand our understanding of the ancient game of Go
- Prerequisite-driven Q-matrix Refinement for Learner Knowledge Assessment: A Case Study in Online Learning Context
- Full Body Video-Based Self-Avatars for Mixed Reality: from E2E System to User Study
- TMIC: App Inventor Extension for the Deployment of Image Classification Models Exported from Teachable Machine
- Four Algorithms for Correlation Clustering: A Survey
- Pushing the limits of fairness impossibility: Who's the fairest of them all?
- Identifying and Overcoming Transformation Bias in Forecasting Models
- Lifelong Learning for Neural powered Mixed Integer Programming
- Multi-Modality Abdominal Multi-Organ Segmentation with Deep Supervised 3D Segmentation Model
- Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
- Seamless Tracking of Group Targets and Ungrouped Targets Using Belief Propagation
- How (and Why) to Think that the Brain is Literally a Computer
- Prediction of the energy and exergy performance of F135 PW100 turbofan engine via deep learning
- A Survey of Open Source Automation Tools for Data Science Predictions
- Addressing Token Uniformity in Transformers via Singular Value Transformation
- Maximum Likelihood on the Joint (Data, Condition) Distribution for Solving Ill-Posed Problems with Conditional Flow Models
- Learning from Unlabeled 3D Environments for Vision-and-Language Navigation
- Comprehensive Dataset of Face Manipulations for Development and Evaluation of Forensic Tools
- IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages
- Entropy Regularization for Population Estimation
- AI-coupled HPC Workflows
- Enforcing Delayed-Impact Fairness Guarantees
- EEG4Students: An Experimental Design for EEG Data Collection and Machine Learning Analysis
- Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation
- Hyperparameter Optimization for Unsupervised Outlier Detection
- Wasserstein Task Embedding for Measuring Task Similarities
- gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window
- GAN-based generative modelling for dermatological applications -- comparative study
- Ontology-Driven Self-Supervision for Adverse Childhood Experiences Identification Using Social Media Datasets
- Bugs in the Data: How ImageNet Misrepresents Biodiversity
- ForestEyes Project: Conception, Enhancements, and Challenges
- Learned Lossless JPEG Transcoding via Joint Lossy and Residual Compression
- Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model
- Towards Sparsified Federated Neuroimaging Models via Weight Pruning
- Efficient Heterogeneous Video Segmentation at the Edge
- Statistical exploration of the Manifold Hypothesis
- PEER: A Collaborative Language Model
- Cross-Camera View-Overlap Recognition
- AGO-Net: Association-Guided 3D Point Cloud Object Detection Network
- Constraint-driven multi-task learning
- A Review of Knowledge Graph Completion
- Lane Change Classification and Prediction with Action Recognition Networks
- Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation
- Detecting the unknown in Object Detection
- Repair Is Nearly Generation: Multilingual Program Repair with LLMs
- Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path
- ImitAL: Learned Active Learning Strategy on Synthetic Data
- On a Built-in Conflict between Deep Learning and Systematic Generalization
- PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model
- Generative Adversarial Network (GAN) based Image-Deblurring
- Calibrated and Enhanced NRLMSIS 2.0 Model with Uncertainty Quantification
- Unrestricted Black-box Adversarial Attack Using GAN with Limited Queries
- Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution
- Sliding Window Recurrent Network for Efficient Video Super-Resolution
- Learning crop type mapping from regional label proportions in large-scale SAR and optical imagery
- Motion Robust High-Speed Light-Weighted Object Detection With Event Camera
- A Low-Complexity Approach to Rate-Distortion Optimized Variable Bit-Rate Compression for Split DNN Computing
- Active Gaze Control for Foveal Scene Exploration
- Outlier Robust and Sparse Estimation of Linear Regression Coefficients
- Graphical Models of False Information and Fact Checking Ecosystems
- Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
- Cats: Complementary CNN and Transformer Encoders for Segmentation
- Apple Counting using Convolutional Neural Networks
- Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models
- Knowledge-based and Data-driven Reasoning and Learning for Ad Hoc Teamwork
- CheapET-3: Cost-Efficient Use of Remote DNN Models
- Unsupervised Structure-Consistent Image-to-Image Translation
- Evaluating the Planning and Operational Resilience of Electrical Distribution Systems with Distributed Energy Resources using Complex Network Theory
- Metric Effects based on Fluctuations in values of k in Nearest Neighbor Regressor
- PeRFception: Perception using Radiance Fields
- A model-based approach to meta-Reinforcement Learning: Transformers and tree search
- ssFPN: Scale Sequence (S^2) Feature Based-Feature Pyramid Network for Object Detection
- A novel method for data augmentation: Nine Dot Moving Least Square (ND-MLS)
- Collaborative Algorithms for Online Personalized Mean Estimation
- Fast and Precise Binary Instance Segmentation of 2D Objects for Automotive Applications
- Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer
- Prostate Lesion Detection and Salient Feature Assessment Using Zone-Based Classifiers
- PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling
- DPTDR: Deep Prompt Tuning for Dense Passage Retrieval
- SubFace: Learning with Softmax Approximation for Face Recognition
- A Deep Learning Approach Using Masked Image Modeling for Reconstruction of Undersampled K-spaces
- Weakly Supervised Airway Orifice Segmentation in Video Bronchoscopy
- Tracking by weakly-supervised learning and graph optimization for whole-embryo C. elegans lineages
- Adverse Childhood Experiences Identification from Clinical Notes with Ontologies and NLP
- FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition
- Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations
- Scenario-Adaptive and Self-Supervised Model for Multi-Scenario Personalized Recommendation
- Q-Net: Query-Informed Few-Shot Medical Image Segmentation
- VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognition
- Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models
All 162
- Dynamic Template Initialization for Part-Aware Person Re-ID
- Trace and Detect Adversarial Attacks on CNNs using Feature Response Maps
- Bidirectional Contrastive Split Learning for Visual Question Answering
- YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception
- Automatic music mixing with deep learning and out-of-domain data
- Self-Supervised Endoscopic Image Key-Points Matching
- Spectrum of non-Hermitian deep-Hebbian neural networks
- Explainable AI for tailored electricity consumption feedback -- an experimental evaluation of visualizations
- Adaptive QoS of WebRTC for Vehicular Media Communications
- Augmented cross-selling through explainable AI -- a case from energy retailing
- Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers
- Radial Basis Function Networks for Convolutional Neural Networks to Learn Similarity Distance Metric and Improve Interpretability
- Event-based Image Deblurring with Dynamic Motion Awareness
- Approximate blocked Gibbs sampling for Bayesian neural networks
- WiCV 2022: The Tenth Women In Computer Vision Workshop
- DCSF: Deep Convolutional Set Functions for Classification of Asynchronous Time Series
- On the Design of Privacy-Aware Cameras: a Study on Deep Neural Networks
- Combining AI and AM - Improving Approximate Matching through Transformer Networks
- A novel approach for Fair Principal Component Analysis based on eigendecomposition
- Self-Supervised Exploration via Temporal Inconsistency in Reinforcement Learning
- Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors
- A New Method on Mask-Wearing Detection for Natural Population Based on Improved YOLOv4
- Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization
- Dynamic Memory-based Curiosity: A Bootstrap Approach for Exploration
- ICANet: A Method of Short Video Emotion Recognition Driven by Multimodal Data
- Time-to-Green predictions for fully-actuated signal control systems with supervised learning
- Discovering Transferable Forensic Features for CNN-generated Images Detection
- Advanced Tools and Methods for Treewidth-Based Problem Solving -- Extended Abstract
- A Spatio-Temporal Attentive Network for Video-Based Crowd Counting
- A Bayesian Variational principle for dynamic Self Organizing Maps
- Monetisation of and Access to in-Vehicle data and resources: the 5GMETA approach
- Next-Year Bankruptcy Prediction from Textual Data: Benchmark and Baselines
- Enhancing Deep Learning Performance of Massive MIMO CSI Feedback
- K-Order Graph-oriented Transformer with GraAttention for 3D Pose and Shape Estimation
- Robust Motion Averaging for Multi-view Registration of Point Sets Based Maximum Correntropy Criterion
- TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination
- Comparison of Object Detection Algorithms for Street-level Objects
- Modality Mixer for Multi-modal Action Recognition
- RZSR: Reference-based Zero-Shot Super-Resolution with Depth Guided Self-Exemplars
- Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments
- Deep model with built-in cross-attention alignment for acoustic echo cancellation
- Visual Subtitle Feature Enhanced Video Outline Generation
- Modeling Paragraph-Level Vision-Language Semantic Alignment for Multi-Modal Summarization
- Fast emulation of density functional theory simulations using approximate Gaussian processes
- Multi-objective optimization of actuation waveform for high-precision drop-on-demand inkjet printing
- E-NeRF: Neural Radiance Fields from a Moving Event Camera
- Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
- Robot Motion Planning as Video Prediction: A Spatio-Temporal Neural Network-based Motion Planner
- A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis
- Multi-AI Complex Systems in Humanitarian Response
- Federated Self-Supervised Contrastive Learning and Masked Autoencoder for Dermatological Disease Diagnosis
- Molecular Substructure-Aware Network for Drug-Drug Interaction Prediction
- SCALE: Online Self-Supervised Lifelong Learning without Prior Knowledge
- Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability
- Applying Eigencontours to PolarMask-Based Instance Segmentation
- 3D-FM GAN: Towards 3D-Controllable Face Manipulation
- FashionVQA: A Domain-Specific Visual Question Answering System
- Learnable human mesh triangulation for 3D human pose and shape estimation
- Secondary Protein Structure Prediction Using Neural Networks
- SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
- Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion
- A new explainable DTM generation algorithm with airborne LIDAR data: grounds are smoothly connected eventually