Papers
Mon 18 Jul 2022
179 papers
- Romanus: Robust Task Offloading in Modular Multi-Sensor Autonomous Driving SystemsEnd-to-end autonomous driving → End-to-end system architecture
- Rethinking Data Augmentation for Robust Visual Question AnsweringKnowledge distillation → Multimodal distillation
- Active Exploration for Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-ResolutionKnowledge distillation → General knowledge distillation methods
- Towards the Human Global Context: Does the Vision-Language Model Really Judge Like a Human Being?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Towards a General Pre-training Framework for Adaptive Learning in MOOCs
- Vertical GaN Diode BV Maximization through Rapid TCAD Simulation and ML-enabled Surrogate Model
- Evaluation of key impression of resilient supply chain based on artificial intelligence of things (AIoT)
- Demystifying Graph Convolution with a Simple Concatenation
- Machine-learning accelerated identification of exfoliable two-dimensional materials
- A Variant of Concurrent Constraint Programming on GPU
- FewGAN: Generating from the Joint Distribution of a Few Images
- TaDaa: real time Ticket Assignment Deep learning Auto Advisor for customer support, help desk, and issue ticketing systems
- Supervised Contrastive ResNet and Transfer Learning for the In-vehicle Intrusion Detection System
- CTL-MTNet: A Novel CapsNet and Transfer Learning-Based Mixed Task Net for the Single-Corpus and Cross-Corpus Speech Emotion Recognition
- e3nn: Euclidean Neural Networks
- Quantum Feature Extraction for THz Multi-Layer Imaging
- Capabilities, Limitations and Challenges of Style Transfer with CycleGANs: A Study on Automatic Ring Design Generation
- Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices
- Selection Bias Induced Spurious Correlations in Large Language Models
- DeformIrisNet: An Identity-Preserving Model of Iris Texture Deformation
- SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Data
- Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift
- Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions
- The m-connecting imset and factorization for ADMG models
- Enhancing Space-time Video Super-resolution via Spatial-temporal Feature Interaction
- Online Learning with Off-Policy Feedback
- Exploiting Unlabeled Data with Vision and Language Models for Object Detection
- Residual and Attentional Architectures for Vector-Symbols
- MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments
- Adversarial Training Improves Joint Energy-Based Generative Modelling
- Multi-step domain adaptation by adversarial attack to H Delta H-divergence
- Gauge-equivariant flow models for sampling in lattice field theories with pseudofermions
- Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision Learning
- MRCLens: an MRC Dataset Bias Detection Toolkit
- Implicit Regularization with Polynomial Growth in Deep Tensor Factorization
- Easy Batch Normalization
- Learning Sparsity-Promoting Regularizers using Bilevel Optimization
- A Community-Aware Framework for Social Influence Maximization
- Image to Icosahedral Projection for SO(3) Object Reasoning from Single-View Images
- Recognizing Hand Use and Hand Role at Home After Stroke from Egocentric Video
- Conditional DETR V2: Efficient Detection Transformer with Box Queries
- Deeply-Learned Generalized Linear Models with Missing Data
- Benchmarking Machine Learning Robustness in Covid-19 Genome Sequence Classification
- On the Study of Sample Complexity for Polynomial Neural Networks
- A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games
- Distributed Differentiable Dynamic Game for Multi-robot Coordination
- NeuForm: Adaptive Overfitting for Neural Shape Editing
- Deep Sequence Models for Text Classification Tasks
- A hierarchical semantic segmentation framework for computer vision-based bridge damage detection
- Prior Knowledge Guided Unsupervised Domain Adaptation
- Consistent Polyhedral Surrogates for Top-k Classification and Variants
- FLAIR: Federated Learning Annotated Image Repository
- MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point
- Prior-Guided Adversarial Initialization for Fast Adversarial Training
- RESAM: Requirements Elicitation and Specification for Deep-Learning Anomaly Models with Applications to UAV Flight Controllers
- Contrastive Environmental Sound Representation Learning
- Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs
- Using attention methods to predict judicial outcomes
- Is Integer Arithmetic Enough for Deep Learning Training?
- The Multiple Subnetwork Hypothesis: Enabling Multidomain Learning by Isolating Task-Specific Subnetworks in Feedforward Neural Networks
- Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime
- SeLoC-ML: Semantic Low-Code Engineering for Machine Learning Applications in Industrial IoT
- Research Trends and Applications of Data Augmentation Algorithms
- Discovering Behavioral Predispositions in Data to Improve Human Activity Recognition
- Why do tree-based models still outperform deep learning on tabular data?
- PBRE: A Rule Extraction Method from Trained Neural Networks Designed for Smart Home Services
- Audio Input Generates Continuous Frames to Synthesize Facial Video Using Generative Adiversarial Networks
- Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations
- Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
- D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance
- Instance-Aware Observer Network for Out-of-Distribution Object Segmentation
- Simplifying Clustering with Graph Neural Networks
- Package for Fast ABC-Boost
- Rank-based Decomposable Losses in Machine Learning: A Survey
- Word Play for Playing Othello (Reverses)
- Amplitude Scintillation Forecasting Using Bagged Trees
- Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks
- An Information-Theoretic Analysis of Bayesian Reinforcement Learning
- Temporal Lift Pooling for Continuous Sign Language Recognition
- A framework for online, stabilizing reinforcement learning
- Semantic Novelty Detection via Relational Reasoning
- Label2Label: A Language Modeling Framework for Multi-Attribute Learning
- Learning differentiable solvers for systems with hard constraints
- Boosting Video Super Resolution with Patch-Based Temporal Redundancy Optimization
- Back to the Manifold: Recovering from Out-of-Distribution States
- pGMM Kernel Regression and Comparisons with Boosted Trees
- Action-based Contrastive Learning for Trajectory Prediction
- Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes
- An Enhanced Graph Representation for Machine Learning Based Automatic Intersection Management
- Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentation
- Boolean Decision Rules for Reinforcement Learning Policy Summarisation
- Upper Limb Movement Recognition utilising EEG and EMG Signals for Rehabilitative Robotics
- Interpolation, extrapolation, and local generalization in common neural networks
- A Sublinear-Time Quantum Algorithm for Approximating Partition Functions
- Lightweight Automated Feature Monitoring for Data Streams
- GOAL: Towards Benchmarking Few-Shot Sports Game Summarization
- Latent Partition Implicit with Surface Codes for 3D Representation
- FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs
- Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks
All 179
- Unifying Event Detection and Captioning as Sequence Generation via Pre-Training
- CACTUSS: Common Anatomical CT-US Space for US examinations
- ExAgt: Expert-guided Augmentation for Representation Learning of Traffic Scenarios
- Class-incremental Novel Class Discovery
- Abstraction between Structural Causal Models: A Review of Definitions and Properties
- Geometry-Aware Reference Synthesis for Multi-View Image Super-Resolution
- Applying Incremental Answer Set Solving to Product Configuration
- FunQG: Molecular Representation Learning Via Quotient Graphs
- Symmetrized Robust Procrustes: Constant-Factor Approximation and Exact Recovery
- The Brain-Inspired Decoder for Natural Visual Image Reconstruction
- MAD for Robust Reinforcement Learning in Machine Translation
- Study of the performance and scalability of federated learning for medical imaging with intermittent clients
- Positive Dependency Graphs Revisited
- ManiFeSt: Manifold-based Feature Selection for Small Data Sets
- Multi-manifold Attention for Vision Transformers
- DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing
- Latency-Aware Collaborative Perception
- AlexU-AIC at Arabic Hate Speech 2022: Contrast to Classify
- A Certifiable Security Patch for Object Tracking in Self-Driving Systems via Historical Deviation Modeling
- Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
- GANDALF: Gated Adaptive Network for Deep Automated Learning of Features
- Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation
- Hardware-agnostic Computation for Large-scale Knowledge Graph Embeddings
- Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization
- UniFusion: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View
- DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection
- Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration
- Classifying COVID-19 vaccine narratives
- HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation
- Explainable Deep Belief Network based Auto encoder using novel Extended Garson Algorithm
- Rethinking Alignment in Video Super-Resolution Transformers
- Neural Distributed Image Compression with Cross-Attention Feature Alignment
- Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications
- Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation
- wPINNs: Weak Physics informed neural networks for approximating entropy solutions of hyperbolic conservation laws
- Towards Automated Classification of Attackers' TTPs by combining NLP with ML Techniques
- High-Order Conditional Mutual Information Maximization for dealing with High-Order Dependencies in Feature Selection
- Segmenting white matter hyperintensities on isotropic three-dimensional Fluid Attenuated Inversion Recovery magnetic resonance images: Assessing deep learning tools on norwegian imaging database
- What does Transformer learn about source code?
- Multi-dimension Geospatial feature learning for urban region function recognition
- A Meta-Reinforcement Learning Algorithm for Causal Discovery
- Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding
- CD Tools -- Condensed Detachment and Structure Generating Theorem Proving (System Description)
- Automatic universal taxonomies for multi-domain semantic segmentation
- Revisiting PatchMatch Multi-View Stereo for Urban 3D Reconstruction
- Robust Simulation-Based Inference in Cosmology with Bayesian Neural Networks
- Efficient View Clustering and Selection for City-Scale 3D Reconstruction
- Adaptive Assignment for Geometry Aware Local Feature Matching
- Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games
- Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
- Outlier Explanation via Sum-Product Networks
- Multi-branch Cascaded Swin Transformers with Attention to k-space Sampling Pattern for Accelerated MRI Reconstruction
- TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
- STT: Soft Template Tuning for Few-Shot Adaptation
- Kullback-Leibler and Renyi divergences in reproducing kernel Hilbert space and Gaussian process settings
- MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects
- Bayesian Optimization for Macro Placement
- GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction
- Federated Learning for Non-IID Data via Client Variance Reduction and Adaptive Server Update
- MLGOPerf: An ML Guided Inliner to Optimize Performance
- A Semantic-aware Attention and Visual Shielding Network for Cloth-changing Person Re-identification
- Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
- Visual Representations of Physiological Signals for Fake Video Detection
- Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and Investigation
- Deep Manifold Learning with Graph Mining
- Human Brains Can't Detect Fake News: A Neuro-Cognitive Study of Textual Disinformation Susceptibility
- Adversarial Contrastive Learning via Asymmetric InfoNCE
- Protecting Global Properties of Datasets with Distribution Privacy Mechanisms
- CausNet : Generational orderings based search for optimal Bayesian networks via dynamic programming with parent set constraints
- Latent-Domain Predictive Neural Speech Coding
- Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention
- SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement
- Towards Understanding The Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search
- Retweet-BERT: Political Leaning Detection Using Language Features and Information Diffusion on Social Networks
- Private Convex Optimization in General Norms
- A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation
- MobileCodec: Neural Inter-frame Video Compression on Mobile Devices
- When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributes
- PlaneSDF-based Change Detection for Long-term Dense Mapping