Papers
Wed 25 Aug 2021
116 papers
- YOLOP: You Only Look Once for Panoptic Driving PerceptionWorld models → World models for autonomous driving
- GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight SparsityEfficient LLM inference and serving → Early exit and edge inference
- EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive LearningLLM safety and security → Membership inference attacks
- 2021 Drexel Society of Artificial Intelligence Research Conference
- Neural Upscaling from Residue-level Protein Structure Networks to Atomistic Structure
- Uniform Manifold Approximation and Projection (UMAP) and its Variants: Tutorial and Survey
- Recommendation System Simulations: A Discussion of Two Key Challenges
- TraverseNet: Unifying Space and Time in Message Passing for Traffic Forecasting
- Forecasting High-Dimensional Covariance Matrices of Asset Returns with Hybrid GARCH-LSTMs
- Multi-task learning from fixed-wing UAV images for 2D/3D city modeling
- Fiducial marker recovery and detection from severely truncated data in navigation assisted spine surgery
- On the approximation of a matrix
- Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process
- Quantum Machine Learning for Health State Diagnosis and Prognostics
- Anomaly Detection in Medical Imaging -- A Mini Review
- Simulating progressive intramural damage leading to aortic dissection using an operator-regression neural network
- Cascading Neural Network Methodology for Artificial Intelligence-Assisted Radiographic Detection and Classification of Lead-Less Implanted Electronic Devices within the Chest
- Attention-based Neural Load Forecasting: A Dynamic Feature Selection Approach
- A Framework for Learning Ante-hoc Explainable Models via Concepts
- Robust High-Resolution Video Matting with Temporal Guidance
- Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
- Generalized Real-World Super-Resolution through Adversarial Robustness
- Maneuver Identification Challenge
- Improving Object Detection and Attribute Recognition by Feature Entanglement Reduction
- Physics-informed neural networks for improving cerebral hemodynamics predictions
- The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks
- Heavy-tailed Streaming Statistical Estimation
- ETA Prediction with Graph Neural Networks in Google Maps
- Learning to discover: expressive Gaussian mixture models for multi-dimensional simulation and parameter inference in the physical sciences
- SomnNET: An SpO2 Based Deep Learning Network for Sleep Apnea Detection in Smartwatches
- Reducing Label Effort: Self-Supervised meets Active Learning
- From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey
- A Riemannian Framework for Analysis of Human Body Surface
- PIVODL: Privacy-preserving vertical federated learning over distributed labels
- Design and Scaffolded Training of an Efficient DNN Operator for Computer Vision on the Edge
- PGTRNet: Two-phase Weakly Supervised Object Detection with Pseudo Ground Truth Refinement
- Integrated Speech and Gesture Synthesis
- Towards Memory-Efficient Neural Networks via Multi-Level in situ Generation
- Model-based Decision Making with Imagination for Autonomous Parking
- Unsupervised Reservoir Computing for Solving Ordinary Differential Equations
- Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization
- CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training
- Blind Image Decomposition
- ProoFVer: Natural Logic Theorem Proving for Fact Verification
- Multi-Task Self-Training for Learning General Representations
- Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral
- A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits
- Lightweight Self-Attentive Sequential Recommendation
- What do pre-trained code models know about code?
- CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing
- Certifiers Make Neural Networks Vulnerable to Availability Attacks
- Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing
- Automatic Feature Highlighting in Noisy RES Data With CycleGAN
- Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning
- Ontology-Enhanced Slot Filling
- Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge
- Deep few-shot learning for bi-temporal building change detection
- Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
- Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction
- Cell Multi-Bernoulli (Cell-MB) Sensor Control for Multi-object Search-While-Tracking (SWT)
- Multi-domain semantic segmentation with overlapping labels
- Toward Formal Data Set Verification for Building Effective Machine Learning Models
- Exploring the Promises of Transformer-Based LMs for the Representation of Normative Claims in the Legal Domain
- Clustering acoustic emission data streams with sequentially appearing clusters using mixture models
- Subgoal Search For Complex Reasoning Tasks
- Lizard: A Large-Scale Dataset for Colonic Nuclear Instance Segmentation and Classification
- Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
- Recall@k Surrogate Loss with Large Batches and Similarity Mixup
- Superpixel-guided Discriminative Low-rank Representation of Hyperspectral Images for Classification
- Adversarially Robust One-class Novelty Detection
- Duo-SegNet: Adversarial Dual-Views for Semi-Supervised Medical Image Segmentation
- A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games
- Learning GraphQL Query Costs (Extended Version)
- Bridged Adversarial Training
- Semantic Scene Segmentation for Robotics Applications
- AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection
- YANMTT: Yet Another Neural Machine Translation Toolkit
- Inductive Matrix Completion Using Graph Autoencoder
- Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training
- GlassNet: Label Decoupling-based Three-stream Neural Network for Robust Image Glass Detection
- TransFER: Learning Relation-aware Facial Expression Representations with Transformers
- Dropout against Deep Leakage from Gradients
- Lightweight Monocular Depth with a Novel Neural Architecture Search Method
- Detecting Small Objects in Thermal Images Using Single-Shot Detector
- Multi-Attributed and Structured Text-to-Face Synthesis
- Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss
- Learning From Long-Tailed Data With Noisy Labels
- INVIGORATE: Interactive Visual Grounding and Grasping in Clutter
- Transformer for Single Image Super-Resolution
- 3D Face Recognition: A Survey
- Heredity-aware Child Face Image Generation with Latent Space Disentanglement
- Learning Class-level Prototypes for Few-shot Learning
- Decentralized optimization with non-identical sampling in presence of stragglers
- Understanding Longitudinal Dynamics of Recommender Systems with Agent-Based Modeling and Simulation
- Viola: A Topic Agnostic Generate-and-Rank Dialogue System
- Opportunistic Emulation of Computationally Expensive Simulations via Deep Learning
- Social Norm Bias: Residual Harms of Fairness-Aware Algorithms
- Normal Learning in Videos with Attention Prototype Network
- Understanding of Kernels in CNN Models by Suppressing Irrelevant Visual Features in Images
- Applying Semi-Automated Hyperparameter Tuning for Clustering Algorithms
All 116
- Memory-Augmented Non-Local Attention for Video Super-Resolution
- Localization Uncertainty-Based Attention for Object Detection
- How COVID-19 has Impacted American Attitudes Toward China: A Study on Twitter
- NGC: A Unified Framework for Learning with Open-World Noisy Data
- Natural Language Processing Accurately Categorizes Indications, Findings and Pathology Reports from Multicenter Colonoscopy
- Improving Visual Quality of Unrestricted Adversarial Examples with Wavelet-VAE
- Tree Decomposed Graph Neural Network
- Layer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection
- Vector Transport Free Riemannian LBFGS for Optimization on Symmetric Positive Definite Matrix Manifolds
- A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?
- iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization
- Responsive Regulation of Dynamic UAV Communication Networks Based on Deep Reinforcement Learning
- Adversary agent reinforcement learning for pursuit-evasion
- Wanderlust: Online Continual Object Detection in the Real World
- Reasoning about Counterfactuals and Explanations: Problems, Results and Directions
- Layer Adaptive Node Selection in Bayesian Neural Networks: Statistical Guarantees and Implementation Details