Papers
Fri 2 Apr 2021
130 papers
- Using GPT-2 to Create Synthetic Data to Improve the Prediction Performance of NLP Machine Learning Classification ModelsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- Learning Online from Corrective Feedback: A Meta-Algorithm for RoboticsOffline RL and imitation learning from data → Imitation learning methods
- UAV-Assisted Communication in Remote Disaster Areas using Imitation Learning
- Federated Double Deep Q-learning for Joint Delay and Energy Minimization in IoT networks
- HMM-Free Encoder Pre-Training for Streaming RNN Transducer
- Robotic needle steering in deformable tissues with extreme learning machines
- Artificial intelligence, human rights, democracy, and the rule of law: a primer
- On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study
- Malignancy Prediction and Lesion Identification from Clinical Dermatological Images
- Optical Flow Dataset Synthesis from Unpaired Images
- Neurons learn slower than they think
- Learnable Dynamic Temporal Pooling for Time Series Classification
- COVID-19 Detection in Cough, Breath and Speech using Deep Transfer Learning and Bottleneck Features
- Solving Large Scale Quadratic Constrained Basis Pursuit
- Query2Prod2Vec Grounded Word Embeddings for eCommerce
- Toward Generating Synthetic CT Volumes using a 3D-Conditional Generative Adversarial Network
- PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
- Multi-class motion-based semantic segmentation for ureteroscopy and laser lithotripsy
- Designing for human-AI complementarity in K-12 education
- Attention Forcing for Machine Translation
- A Semantic Segmentation Network for Urban-Scale Building Footprint Extraction Using RGB Satellite Imagery
- Robotic Waste Sorter with Agile Manipulation and Quickly Trainable Detector
- Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision
- Autonomous Driving Data Chain & Interfaces
- Diverse Gaussian Noise Consistency Regularization for Robustness and Uncertainty Calibration
- Uncertainty-Aware Annotation Protocol to Evaluate Deformable Registration Algorithms
- The Coronavirus is a Bioweapon: Analysing Coronavirus Fact-Checked Stories
- Modeling Censored Mobility Demand through Quantile Regression Neural Networks
- Type Prediction Systems
- Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories
- Physics Informed Convex Artificial Neural Networks (PICANNs) for Optimal Transport based Density Estimation
- Learning Description Logic Ontologies. Five Approaches. Where Do They Stand?
- grASP: A Graph Based ASP-Solver and Justification System
- Scan Specific Artifact Reduction in K-space (SPARK) Neural Networks Synergize with Physics-based Reconstruction to Accelerate MRI
- How Powerful are Performance Predictors in Neural Architecture Search?
- Detecting Anomalies Through Contrast in Heterogeneous Data
- Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
- Developing a New Autism Diagnosis Process Based on a Hybrid Deep Learning Architecture Through Analyzing Home Videos
- LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
- Mining Trends of COVID-19 Vaccine Beliefs on Twitter with Lexical Embeddings
- Simulation-Based Optimization of User Interfaces for Quality-Assuring Machine Learning Model Predictions
- Fast Parallel Algorithms for Euclidean Minimum Spanning Tree and Hierarchical Spatial Clustering
- M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers
- Linear Systems can be Hard to Learn
- Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation
- Fast and Accurate Randomized Algorithms for Low-rank Tensor Decompositions
- TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training
- Defending Against Image Corruptions Through Adversarial Augmentations
- End-to-end learning of keypoint detection and matching for relative pose estimation
- What Taggers Fail to Learn, Parsers Need the Most
- ESTemd: A Distributed Processing Framework for Environmental Monitoring based on Apache Kafka Streaming Engine
- Blind Exploration and Exploitation of Stochastic Experts
- Enhancing Underwater Image via Adaptive Color and Contrast Enhancement, and Denoising
- Prediction of Tuberculosis using U-Net and segmentation techniques
- MOST: A Multi-Oriented Scene Text Detector with Localization Refinement
- An active inference model of collective intelligence
- Permutation-Invariant Subgraph Discovery
- Information Geometry and Classical Cram'er-Rao Type Inequalities
- IITK@LCP at SemEval 2021 Task 1: Classification for Lexical Complexity Regression Task
- Assessment of machine learning methods for state-to-state approaches
- Distributional Offline Continuous-Time Reinforcement Learning with Neural Physics-Informed PDEs (SciPhy RL for DOCTR-L)
- Effect of depth order on iterative nested named entity recognition models
- Hybrid Policy Learning for Energy-Latency Tradeoff in MEC-Assisted VR Video Service
- White paper: The Helix Pathogenicity Prediction Platform
- Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural Network
- Surfacing Estimation Uncertainty in the Decay Parameters of Hawkes Processes with Exponential Kernels
- Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
- A Comparison of Similarity Based Instance Selection Methods for Cross Project Defect Prediction
- LiftPool: Bidirectional ConvNet Pooling
- Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics
- Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation
- Visual Semantic Role Labeling for Video Understanding
- Bayesian Structural Learning for an Improved Diagnosis of Cyber-Physical Systems
- Brain Tumor Segmentation and Survival Prediction using 3D Attention UNet
- An Empirical Evaluation of Cost-based Federated SPARQL Query Processing Engines
- STARdom: an architecture for trusted and secure human-centered manufacturing systems
- Glioma Prognosis: Segmentation of the Tumor and Survival Prediction using Shape, Geometric and Clinical Information
- Use of 'off-the-shelf' information extraction algorithms in clinical informatics: a feasibility study of MetaMap annotation of Italian medical notes
- Resource-aware Time Series Imaging Classification for Wireless Link Layer Anomalies
- TubeR: Tubelet Transformer for Video Action Detection
- Variational Deep Image Denoising
- Skillful Precipitation Nowcasting using Deep Generative Models of Radar
- Learning Transferable Kinematic Dictionary for 3D Human Pose and Shape Reconstruction
- Multitask Recalibrated Aggregation Network for Medical Code Prediction
- Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey
- The CSO Classifier: Ontology-Driven Detection of Research Topics in Scholarly Articles
- A Detector-oblivious Multi-arm Network for Keypoint Matching
- UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles
- Multi-Class Data Description for Out-of-distribution Detection
- Humor@IITK at SemEval-2021 Task 7: Large Language Models for Quantifying Humor and Offensiveness
- Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques
- Sketch and Customize: A Counterfactual Story Generator
- VisQA: X-raying Vision and Language Reasoning in Transformers
- Landmarks Augmentation with Manifold-Barycentric Oversampling
- Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning
- AAformer: Auto-Aligned Transformer for Person Re-Identification
- Datacentric analysis to reduce pedestrians accidents: A case study in Colombia
- Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
- Network Quantization with Element-wise Gradient Scaling
- HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection
All 130
- Efficacy of Bayesian Neural Networks in Active Learning
- Low Dose Helical CBCT denoising by using domain filtering with deep reinforcement learning
- Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts
- Adaptive Class Suppression Loss for Long-Tail Object Detection
- Contrastively Learning Visual Attention as Affordance Cues from Demonstrations for Robotic Grasping
- S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation
- Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation
- Security Properties as Nested Causal Statements
- A Comparative Analysis of Machine Learning and Grey Models
- Inference of Recyclable Objects with Convolutional Neural Networks
- Constrained non-negative matrix factorization enabling real-time insights of textitin situ and high-throughput experiments
- PolyDNN: Polynomial Representation of NN for Communication-less SMPC Inference
- Self-supervised Video Representation Learning by Context and Motion Decoupling
- An NCAP-like Safety Indicator for Self-Driving Cars
- Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction
- The Spatially-Correlative Loss for Various Image Translation Tasks
- Streaming Social Event Detection and Evolution Discovery in Heterogeneous Information Networks
- Estimating the Generalization in Deep Neural Networks via Sparsity
- Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation
- SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom
- Bridging Global Context Interactions for High-Fidelity Image Completion
- Unconstrained Face Recognition using ASURF and Cloud-Forest Classifier optimized with VLAD
- DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation
- Cursed yet Satisfied Agents
- Learning to Filter: Siamese Relation Network for Robust Tracking
- How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?
- Towards High Fidelity Face Relighting with Realistic Shadows
- Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments
- LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions
- Partition-Guided GANs