Papers
Mon 5 Apr 2021
140 papers
- Compressing Visual-linguistic Model via Knowledge DistillationKnowledge distillation → Multimodal distillation
- CBench: Towards Better Evaluation of Question Answering Over Knowledge Graphs
- COVID-19 sentiment analysis via deep learning during the rise of novel cases
- Towards Automated Psychotherapy via Language Modeling
- Financial Markets Prediction with Deep Learning
- A review of artificial intelligence methods combined with Raman spectroscopy to identify the composition of substances
- An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network
- Fast Design Space Exploration of Nonlinear Systems: Part II
- Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
- Robust Classification Under ℓ0 Attack for the Gaussian Mixture Model
- GPU Domain Specialization via Composable On-Package Architecture
- A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrays
- AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
- Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
- Insight about Detection, Prediction and Weather Impact of Coronavirus (Covid-19) using Neural Network
- Learning Optical Flow from a Few Matches
- A data-driven personalized smart lighting recommender system
- Identity and Posture Recognition in Smart Beds with Deep Multitask Learning
- Unified Detection of Digital and Physical Face Attacks
- Adaptive Clustering of Robust Semantic Representations for Adversarial Image Purification
- Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks
- Distributed Learning in Wireless Networks: Recent Progress and Future Challenges
- Revisiting Rashomon: A Comment on "The Two Cultures"
- Automatic Micro-Expression Apex Frame Spotting using Local Binary Pattern from Six Intersection Planes
- Semi-Supervised Clustering with Inaccurate Pairwise Annotations
- What Will it Take to Fix Benchmarking in Natural Language Understanding?
- A Concise Review of Transfer Learning
- Learning Latent and Hierarchical Structures in Cognitive Diagnosis Models
- Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding
- ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities
- SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
- End-to-End Speaker-Attributed ASR with Transformer
- SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification System
- Nonlinear model reduction for slow-fast stochastic systems near unknown invariant manifolds
- Action Shuffle Alternating Learning for Unsupervised Action Segmentation
- Discrete Reasoning Templates for Natural Language Understanding
- Anchor-Constrained Viterbi for Set-Supervised Action Segmentation
- Efficient Attentions for Long Document Summarization
- Streaming Multi-talker Speech Recognition with Joint Speaker Identification
- Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
- Automated Performance Testing Based on Active Deep Learning
- Analytic function approximation by path norm regularized deep networks
- Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection
- An Empirical Study of Training Self-Supervised Vision Transformers
- Generating Furry Cars: Disentangling Object Shape & Appearance across Multiple Domains
- Automated lung segmentation from CT images of normal and COVID-19 pneumonia patients
- Exploring Transformers in Emotion Recognition: a comparison of BERT, DistillBERT, RoBERTa, XLNet and ELECTRA
- Segmentation of EM showers for neutrino experiments with deep graph neural networks
- Artificial Neural Network Modeling for Airline Disruption Management
- Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation
- Intent Detection and Slot Filling for Vietnamese
- Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification
- Efficient Personalized Speech Enhancement through Self-Supervised Learning
- SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition
- Quantized Gromov-Wasserstein
- Graph Neural Networks Based Detection of Stealth False Data Injection Attacks in Smart Grids
- Domain Generalization with MixStyle
- Uncertainty-Aware COVID-19 Detection from Imbalanced Sound Data
- Can audio-visual integration strengthen robustness under multimodal attacks?
- Generalized Joint Probability Density Function Formulation inTurbulent Combustion using DeepONet
- Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognition
- Rejoinder: Gaussian Differential Privacy
- Using spatial-temporal ensembles of convolutional neural networks for lumen segmentation in ureteroscopy
- HLA-Face: Joint High-Low Adaptation for Low Light Face Detection
- ECRM: Efficient Fault Tolerance for Recommendation Model Training via Erasure Coding
- Probabilistic Programming Bots in Intuitive Physics Game Play
- Acted vs. Improvised: Domain Adaptation for Elicitation Approaches in Audio-Visual Emotion Recognition
- Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentation
- DataOps for Societal Intelligence: a Data Pipeline for Labor Market Skills Extraction and Matching
- Performance Evaluation of Machine Learning Techniques for DoS Detection in Wireless Sensor Network
- Multi-Atlas Based Pathological Stratification of d-TGA Congenital Heart Disease
- Automating Transfer Credit Assessment in Student Mobility -- A Natural Language Processing-based Approach
- Robust Trust Region for Weakly Supervised Segmentation
- Machine Learning Applications in the Routing in Computer Networks
- Multilevel Stein variational gradient descent with applications to Bayesian inverse problems
- What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult
- NQMIX: Non-monotonic Value Function Factorization for Deep Multi-Agent Reinforcement Learning
- Mining Customers' Opinions for Online Reputation Generation and Visualization in e-Commerce Platforms
- Few-Cost Salient Object Detection with Adversarial-Paced Learning
- Optimal Query Complexity of Secure Stochastic Convex Optimization
- DexDeepFM: Ensemble Diversity Enhanced Extreme Deep Factorization Machine Model
- Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images
- Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval
- Adaptive Prototype Learning and Allocation for Few-Shot Segmentation
- Adaptive Gradient Balancing for Undersampled MRI Reconstruction and Image-to-Image Translation
- Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
- Conformal testing in a binary model situation
- A General Derivative Identity for the Conditional Mean Estimator in Gaussian Noise and Some Applications
- MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition
- Lipstick ain't enough: Beyond Color Matching for In-the-Wild Makeup Transfer
- An Artificial Intelligence Framework for Bidding Optimization with Uncertainty in Multiple Frequency Reserve Markets
- FedPandemic: A Cross-Device Federated Learning Approach Towards Elementary Prognosis of Diseases During a Pandemic
- Integrating 2D and 3D Digital Plant Information Towards Automatic Generation of Digital Twins
- Rethinking Perturbations in Encoder-Decoders for Fast Training
- Improving the Expressive Power of Graph Neural Network with Tinhofer Algorithm
- Unsupervised Multi-source Domain Adaptation Without Access to Source Data
- Stopping Criterion for Active Learning Based on Error Stability
- Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning
- Model Compression for Dynamic Forecast Combination
- When Can Liquid Democracy Unveil the Truth?
All 140
- Semi-supervised Variational Temporal Convolutional Network for IoT Communication Multi-anomaly Detection
- Modeling Gate-Level Abstraction Hierarchy Using Graph Convolutional Neural Networks to Predict Functional De-Rating Factors
- Frequency Estimation Under Multiparty Differential Privacy: One-shot and Streaming
- StarGAN-based Emotional Voice Conversion for Japanese Phrases
- Deep Neural Networks for Relation Extraction
- Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks
- CCSNet: a deep learning modeling suite for CO2 storage
- Hierarchical Pyramid Representations for Semantic Segmentation
- A Heuristic-driven Uncertainty based Ensemble Framework for Fake News Detection in Tweets and News Articles
- Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses
- Neural Clinical Event Sequence Prediction through Personalized Online Adaptive Learning
- Annotating Columns with Pre-trained Language Models
- BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detection
- BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text Classification
- Reducing Racial Bias in Facial Age Prediction using Unsupervised Domain Adaptation in Regression
- AST: Audio Spectrogram Transformer
- Application of Neural Network Algorithm in Propylene Distillation
- Convolutional Neural Opacity Radiance Fields
- FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images
- Procrustean Training for Imbalanced Deep Learning
- WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach
- GSECnet: Ground Segmentation of Point Clouds for Edge Computing
- 3D Human Body Reshaping with Anthropometric Modeling
- Paired Examples as Indirect Supervision in Latent Decision Models
- Predicting Mergers and Acquisitions using Graph-based Deep Learning
- Potential Convolution: Embedding Point Clouds into Potential Fields
- Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics
- Optimal Sampling Gaps for Adaptive Submodular Maximization
- Fast Design Space Exploration of Nonlinear Systems: Part I
- A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification
- Explainability-aided Domain Generalization for Image Classification
- A Dual-Critic Reinforcement Learning Framework for Frame-level Bit Allocation in HEVC/H.265
- Opportunistic Screening of Osteoporosis Using Plain Film Chest X-ray
- Semantically Stealthy Adversarial Attacks against Segmentation Models
- Training Deep Neural Networks via Branch-and-Bound
- A New Approach to Overgenerating and Scoring Abstractive Summaries
- Graph Generative Models for Fast Detector Simulations in High Energy Physics
- Inference Time Style Control for Summarization
- Analyzing Flight Delay Prediction Under Concept Drift
- Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling