Papers
Fri 6 Aug 2021
102 papers
- What Matters in Learning from Offline Human Demonstrations for Robot ManipulationOffline RL and imitation learning from data → Real-world robot offline RL
- Transferring Knowledge Distillation for Multilingual Social Event DetectionKnowledge distillation → Knowledge distillation for LLMs
- Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous VehiclesEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- ILVR: Conditioning Method for Denoising Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- Creating and Querying Personalized Versions of Wikidata on a Laptop
- A Robust Lane Detection Associated with Quaternion Hardy Filter
- Improving Global Forest Mapping by Semi-automatic Sample Labeling with Deep Learning on Google Earth Images
- Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computing
- Estimating Graph Dimension with Cross-validated Eigenvalues
- Towards Zero-shot Language Modeling
- BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments
- Feature-Supervised Action Modality Transfer
- Distilling Transformers for Neural Cross-Domain Search
- A Deep Neural Network Approach for Crop Selection and Yield Prediction in Bangladesh
- Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning
- Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learning
- Medical image segmentation with imperfect 3D bounding boxes
- Joint AP Probing and Scheduling: A Contextual Bandit Approach
- A Smart and Defensive Human-Machine Approach to Code Analysis
- Ensemble Augmentation for Deep Neural Networks Using 1-D Time Series Vibration Data
- Semantic Segmentation and Object Detection Towards Instance Segmentation: Breast Tumor Identification
- Smooth Symbolic Regression: Transformation of Symbolic Regression into a Real-valued Optimization Problem
- Concept Drift Detection with Variable Interaction Networks
- iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks
- BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
- Facebook AI WMT21 News Translation Task Submission
- (Just) A Spoonful of Refinements Helps the Registration Error Go Down
- The Right to Talk: An Audio-Visual Transformer Approach
- SMOTified-GAN for class imbalanced pattern classification problems
- Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images
- GLASS: Geometric Latent Augmentation for Shape Spaces
- A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning
- Active Learning of Driving Scenario Trajectories
- Simple Modifications to Improve Tabular Neural Networks
- Temporally Abstract Partial Models
- Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
- Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference
- Shift-invariant waveform learning on epileptic ECoG
- Source-Free Domain Adaptation for Image Segmentation
- Full-Duplex Strategy for Video Object Segmentation
- Attainment Regions in Feature-Parameter Space for High-Level Debugging in Autonomous Robots
- ELSED: Enhanced Line SEgment Drawing
- SELM: Siamese Extreme Learning Machine with Application to Face Biometrics
- Lung Ultrasound Segmentation and Adaptation between COVID-19 and Community-Acquired Pneumonia
- Beyond Cuts in Small Signal Scenarios -- Enhanced Sneutrino Detectability Using Machine Learning
- Contrastive Learning for View Classification of Echocardiograms
- Uncertainty-Based Dynamic Graph Neighborhoods For Medical Segmentation
- TS4Net: Two-Stage Sample Selective Strategy for Rotating Object Detection
- Reasoning on Multi-Relational Contextual Hierarchies via Answer Set Programming with Algebraic Measures
- Localization in 1D non-parametric latent space models from pairwise affinities
- Path classification by stochastic linear recurrent neural networks
- Cross-lingual Capsule Network for Hate Speech Detection in Social Media
- Detecting Requirements Smells With Deep Learning: Experiences, Challenges and Future Work
- Rectified Euler k-means and Beyond
- STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routing
- SWSR: A Chinese Dataset and Lexicon for Online Sexism Detection
- Machine learning for surface prediction in ACTS
- Deriving Disinformation Insights from Geolocalized Twitter Callouts
- Spatiotemporal Contrastive Learning of Facial Expressions in Videos
- Towards a Semantics for Hybrid ASP systems
- Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effects
- Nonground Abductive Logic Programming with Probabilistic Integrity Constraints
- Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
- Utilizing Treewidth for Quantitative Reasoning on Epistemic Logic Programs
- Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations
- Tell me a story about yourself: The words of shopping experience and self-satisfaction
- Feature Detection for Hand Hygiene Stages
- Interpretable Summaries of Black Box Incident Triaging with Subgroup Discovery
- Inspecting the Process of Bank Credit Rating via Visual Analytics
- An Empirical Study on End-to-End Singing Voice Synthesis with Encoder-Decoder Architectures
- MmWave Radar and Vision Fusion for Object Detection in Autonomous Driving: A Review
- Two New Low Rank Tensor Completion Methods Based on Sum Nuclear Norm
- Learning to Rank Ace Neural Architectures via Normalized Discounted Cumulative Gain
- AI-based Aortic Vessel Tree Segmentation for Cardiovascular Diseases Treatment: Status Quo
- Efficient and Generic Interactive Segmentation Framework to Correct Mispredictions during Clinical Evaluation of Medical Images
- Sentence Semantic Regression for Text Generation
- Improving Contrastive Learning by Visualizing Feature Transformation
- Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation
- Reducing Spatial Labeling Redundancy for Semi-supervised Crowd Counting
- Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning
- Learning Meta-class Memory for Few-Shot Semantic Segmentation
- Smooth Mesh Estimation from Depth Data using Non-Smooth Convex Optimization
- Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding
- Auxiliary Class Based Multiple Choice Learning
- Deep Learning-based Biological Anatomical Landmark Detection in Colonoscopy Videos
- A review on vision-based analysis for automatic dietary assessment
- Unsupervised Learning of Debiased Representations with Pseudo-Attributes
- Is it Fake? News Disinformation Detection on South African News Websites
- High-frequency shape recovery from shading by CNN and domain adaptation
- From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data
- Incremental Feature Learning For Infinite Data
- Detailed Avatar Recovery from Single Image
- VinaFood21: A Novel Dataset for Evaluating Vietnamese Food Recognition
- DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features
- Interpretable Visual Understanding with Cognitive Attention Network
- StrucTexT: Structured Text Understanding with Multi-Modal Transformers
- Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers
- LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching
- Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economist
- Lights, Camera, Action! A Framework to Improve NLP Accuracy over OCR documents