Papers
Thu 18 Aug 2022
141 papers
- dPMP-Deep Probabilistic Motion Planning: A use case in Strawberry Picking RobotOffline RL and imitation learning from data → Robot learning from demonstration
- Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for ClassificationKnowledge distillation → General knowledge distillation methods
- Enhancing Diffusion-Based Image Synthesis with Robust Classifier GuidanceDiffusion models → Diffusion foundations and sampling
- Trustworthy modelling of atmospheric formaldehyde powered by deep learning
- Pathway to Future Symbiotic Creativity
- MARTI-4: new model of human brain, considering neocortex and basal ganglia -- learns to play Atari game by reinforcement learning on a single CPU
- T-Person-GAN: Text-to-Person Image Generation with Identity-Consistency and Manifold Mix-Up
- The DialPort tools
- Graph Embeddings via Tensor Products and Approximately Orthonormal Codes
- A semantic web approach to uplift decentralized household energy data
- Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
- Meta-Learning Online Control for Linear Dynamical Systems
- In Silico Prediction of Blood-Brain Barrier Permeability of Chemical Compounds through Molecular Feature Modeling
- Blind Image Deblurring with Unknown Kernel Size and Substantial Noise
- DCNNV-19: A Deep Convolutional Neural Network for COVID-19 Detection in Chest Computed Tomographies
- Shadows Aren't So Dangerous After All: A Fast and Robust Defense Against Shadow-Based Adversarial Attacks
- Reproducibility Report: Contrastive Learning of Socially-aware Motion Representations
- Representation Learning for the Automatic Indexing of Sound Effects Libraries
- Towards Situation Awareness and Attention Guidance in a Multiplayer Environment using Augmented Reality and Carcassonne
- Out-of-distribution Detection via Frequency-regularized Generative Models
- A Multi-Modal Wildfire Prediction and Personalized Early-Warning System Based on a Novel Machine Learning Framework
- Implicit Session Contexts for Next-Item Recommendations
- How important are socioeconomic factors for hurricane performance of power systems? An analysis of disparities through machine learning
- Mapping Husserlian phenomenology onto active inference
- A Review of Uncertainty for Deep Reinforcement Learning
- Machine learning algorithms for three-dimensional mean-curvature computation in the level-set method
- Self-Supervised Primal-Dual Learning for Constrained Optimization
- Monte Carlo is a good sampling strategy for polynomial approximation in high dimensions
- Quantitative Universal Approximation Bounds for Deep Belief Networks
- Communication-Efficient Collaborative Best Arm Identification
- GraTO: Graph Neural Network Framework Tackling Over-smoothing with Neural Architecture Search
- Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization
- VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social Media
- Improving Small Molecule Generation using Mutual Information Machine
- Treeformer: Dense Gradient Trees for Efficient Attention Computation
- A Kind Introduction to Lexical and Grammatical Aspect, with a Survey of Computational Approaches
- The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs
- Open-Vocabulary Universal Image Segmentation with MaskCLIP
- Quality issues in Machine Learning Software Systems
- "Melatonin": A Case Study on AI-induced Musical Style
- GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement
- Stable Object Reorientation using Contact Plane Registration
- DeepClouds.ai: Deep learning enabled computationally cheap direct numerical simulations
- Ered: Enhanced Text Representations with Entities and Descriptions
- KDD CUP 2022 Wind Power Forecasting Team 88VIP Solution
- Towards Automated Process Planning and Mining
- Meta Sparse Principal Component Analysis
- A Hybrid Self-Supervised Learning Framework for Vertical Federated Learning
- Sequence Prediction Under Missing Data : An RNN Approach Without Imputation
- ManiFlow: Implicitly Representing Manifolds with Normalizing Flows
- Detecting Environmental Violations with Satellite Imagery in Near Real Time: Land Application under the Clean Water Act
- Prompt Vision Transformer for Domain Generalization
- Learning-based estimation of in-situ wind speed from underwater acoustics
- Learned Indexing in Proteins: Extended Work on Substituting Complex Distance Calculations with Embedding and Clustering Techniques
- NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereo
- Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation
- Brand Celebrity Matching Model Based on Natural Language Processing
- Network inference via process motifs for lagged correlation in linear stochastic processes
- Lessons from a Space Lab -- An Image Acquisition Perspective
- A Two-stream Convolutional Network for Musculoskeletal and Neurological Disorders Prediction
- CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
- Mind the Gap in Distilling StyleGANs
- A Multi-modal Registration and Visualization Software Tool for Artworks using CraquelureNet
- Differentiable Architecture Search with Random Features
- Outlier Detection using Self-Organizing Maps for Automated Blood Cell Analysis
- Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning
- Learning Spatial-Frequency Transformer for Visual Object Tracking
- A Coarse-to-Fine Approach for Urban Land Use Mapping Based on Multisource Geospatial Data
- Siamese Prototypical Contrastive Learning
- Semi-supervised domain adaptation with CycleGAN guided by a downstream task loss
- COPE: End-to-end trainable Constant Runtime Object Pose Estimation
- Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members
- Exploiting Sentiment and Common Sense for Zero-shot Stance Detection
- An Adjustable Farthest Point Sampling Method for Approximately-sorted Point Cloud Data
- Explainable Reinforcement Learning on Financial Stock Trading using SHAP
- Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis
- Efficient data-driven gap filling of satellite image time series using deep neural networks with partial convolutions
- GraVoS: Voxel Selection for 3D Point-Cloud Detection
- Lifted Bregman Training of Neural Networks
- Memory and Capacity of Graph Embedding Methods
- TSCom-Net: Coarse-to-Fine 3D Textured Shape Completion Network
- Evaluating Continual Test-Time Adaptation for Contextual and Semantic Domain Shifts
- Runtime Analysis for the NSGA-II: Provable Speed-Ups From Crossover
- Understanding Interpersonal Conflict Types and their Impact on Perception Classification
- Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion
- Exploring and Exploiting Multi-Granularity Representations for Machine Reading Comprehension
- Active PETs: Active Data Annotation Prioritisation for Few-Shot Claim Verification with Pattern Exploiting Training
- Profiler: Profile-Based Model to Detect Phishing Emails
- Global Convergence of Two-timescale Actor-Critic for Solving Linear Quadratic Regulator
- Bayesian Optimization Augmented with Actively Elicited Expert Knowledge
- Transcending XAI Algorithm Boundaries through End-User-Inspired Design
- RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection
- Intelligent problem-solving as integrated hierarchical reinforcement learning
- Neural Capture of Animatable 3D Human from Monocular Video
- Efficient Signed Graph Sampling via Balancing & Gershgorin Disc Perfect Alignment
- Disentangled Contrastive Learning for Social Recommendation
- Temporal Up-Sampling for Asynchronous Events
- Merging Ontologies Algebraically
- Learning Generative Models for Active Inference using Tensor Networks
- L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training
All 141
- Deep Neural Network Approximation of Invariant Functions through Dynamical Systems
- Musika! Fast Infinite Waveform Music Generation
- Resisting Adversarial Attacks in Deep Neural Networks using Diverse Decision Boundaries
- A Survey on Open Information Extraction from Rule-based Model to Large Language Model
- Intention estimation from gaze and motion features for human-robot shared-control object manipulation
- Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization
- Mere Contrastive Learning for Cross-Domain Sentiment Analysis
- Enhancing Targeted Attack Transferability via Diversified Weight Pruning
- Tree species classification from hyperspectral data using graph-regularized neural networks
- RRWaveNet: A Compact End-to-End Multi-Scale Residual CNN for Robust PPG Respiratory Rate Estimation
- SDA-SNE: Spatial Discontinuity-Aware Surface Normal Estimation via Multi-Directional Dynamic Programming
- On an Application of Generative Adversarial Networks on Remaining Lifetime Estimation
- Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy
- Domain-Specific Risk Minimization for Out-of-Distribution Generalization
- A Two-Phase Paradigm for Joint Entity-Relation Extraction
- Generating Synthetic Clinical Data that Capture Class Imbalanced Distributions with Generative Adversarial Networks: Example using Antiretroviral Therapy for HIV
- Pandemic Control, Game Theory and Machine Learning
- Learning Program Representations with a Tree-Structured Transformer
- Lost in the Shuffle: Testing Power in the Presence of Errorful Network Vertex Labels
- Physics-Informed Neural Network Method for Parabolic Differential Equations with Sharply Perturbed Initial Conditions
- ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization
- Unifying Visual Perception by Dispersible Points Learning
- MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation
- CP-PINNs: Data-Driven Changepoints Detection in PDEs Using Online Optimized Physics-Informed Neural Networks
- Domain Camera Adaptation and Collaborative Multiple Feature Clustering for Unsupervised Person Re-ID
- Challenges and opportunities in applying Neural Temporal Point Processes to large scale industry data
- LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling
- Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes
- Hybrid Learning with New Value Function for the Maximum Common Subgraph Problem
- Intellectual Property Evaluation Utilizing Machine Learning
- A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables
- See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval
- AoI-based Temporal Attention Graph Neural Network for Popularity Prediction and Content Caching
- Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures
- Towards Practical Single-shot Phase Retrieval with Physics-Driven Deep Neural Network
- Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition
- Restoration of User Videos Shared on Social Media
- Robust Causal Graph Representation Learning against Confounding Effects
- Merchandise Recommendation for Retail Events with Word Embedding Weighted Tf-idf and Dynamic Query Expansion
- MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation
- DIET: Conditional independence testing with marginal dependence measures of residual information