Papers
Tue 27 Apr 2021
131 papers
- Self-distillation with Batch Knowledge Ensembling Improves ImageNet ClassificationKnowledge distillation → General knowledge distillation methods
- Dynamic Cat Swarm Optimization Algorithm for Backboard Wiring Problem
- Morphological classification of astronomical images with limited labelling
- VID-WIN: Fast Video Event Matching with Query-Aware Windowing at the Edge for the Internet of Multimedia Things
- Reconstruction of Convex Polytope Compositions from 3D Point-clouds
- On Addressing Practical Challenges for RNN-Transducer
- Identifying Hubs in Undergraduate Course Networks Based on Scaled Co-Enrollments: Extended Version
- Do Feature Attribution Methods Correctly Attribute Features?
- Sample selection from a given dataset to validate machine learning models
- Implementing Reinforcement Learning Algorithms in Retail Supply Chains with OpenAI Gym Toolkit
- Multi-class Text Classification using BERT-based Active Learning
- Learning Fair Canonical Polyadical Decompositions using a Kernel Independence Criterion
- KAMA: 3D Keypoint Aware Body Mesh Articulation
- Towards Clinical Encounter Summarization: Learning to Compose Discharge Summaries from Prior Notes
- ConTNet: Why not use convolution and transformer at the same time?
- An Energy-Based View of Graph Neural Networks
- Text Generation with Deep Variational GAN
- Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation
- Improved and Efficient Text Adversarial Attacks using Target Information
- Stochastic Neural Networks for Automatic Cell Tracking in Microscopy Image Sequences of Bacterial Colonies
- Phenotyping OSA: a time series analysis using fuzzy clustering and persistent homology
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- TRECVID 2020: A comprehensive campaign for evaluating video retrieval tasks across multiple application domains
- Discovering nonlinear resonances through physics-informed machine learning
- The Role of General Intelligence in Mathematical Reasoning
- An optical neural network using less than 1 photon per multiplication
- Deep Two-Stage High-Resolution Image Inpainting
- Robust Classification via Support Vector Machines
- Named Entity Recognition and Linking Augmented with Large-Scale Structured Data
- Estimating Egocentric 3D Human Pose in Global Space
- Meta-evaluation of Conversational Search Evaluation Metrics
- Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings
- SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment
- Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients
- Incident Detection on Junctions Using Image Processing
- Self-supervised Spatial Reasoning on Multi-View Line Drawings
- Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution
- DASEE A Synthetic Database of Domestic Acoustic Scenes and Events in Dementia Patients Environment
- Towards Fair Federated Learning with Zero-Shot Data Augmentation
- Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank
- Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs
- Semi-supervised Interactive Intent Labeling
- FrameExit: Conditional Early Exiting for Efficient Video Recognition
- SpikE: spike-based embeddings for multi-relational graph data
- ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception
- Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
- BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
- Explaining in Style: Training a GAN to explain a classifier in StyleSpace
- Unsupervised 3D Shape Completion through GAN Inversion
- NTIRE 2021 Depth Guided Image Relighting Challenge
- Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics
- Sifting out the features by pruning: Are convolutional networks the winning lottery ticket of fully connected ones?
- End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks
- Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization
- MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions
- Network Embedding via Deep Prediction Model
- UniTE -- The Best of Both Worlds: Unifying Function-Fitting and Aggregation-Based Approaches to Travel Time and Travel Speed Estimation
- Building-GAN: Graph-Conditioned Architectural Volumetric Design Generation
- Inductive Program Synthesis over Noisy Datasets using Abstraction Refinement Based Optimization
- Multi-fairness under class-imbalance
- Adaptive Adversarial Training for Meta Reinforcement Learning
- From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence
- Quantum circuit synthesis of Bell and GHZ states using projective simulation in the NISQ era
- Evidential segmentation of 3D PET/CT images
- A Dual Process Model for Optimizing Cross Entropy in Neural Networks
- MULTIMODAL ANALYSIS: Informed content estimation and audio source separation
- Semi-supervised Superpixel-based Multi-Feature Graph Learning for Hyperspectral Image Data
- Early Classification of Time Series is Meaningful
- Proceedings - AI/ML for Cybersecurity: Challenges, Solutions, and Novel Ideas at SIAM Data Mining 2021
- Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation
- Autotuning PolyBench Benchmarks with LLVM Clang/Polly Loop Optimization Pragmas Using Bayesian Optimization (extended version)
- Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques
- SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents
- LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking
- Extending Isolation Forest for Anomaly Detection in Big Data via K-Means
- Learning low bending and low distortion manifold embeddings
- Rethinking BiSeNet For Real-time Semantic Segmentation
- A Scalable and Reproducible System-on-Chip Simulation for Reinforcement Learning
- Efficient channel charting via phase-insensitive distance computation
- Controlling earthquake-like instabilities using artificial intelligence
- Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction
- Structured Sparse Non-negative Matrix Factorization with L20-Norm for scRNA-seq Data Analysis
- A unified framework for Hamiltonian deep neural networks
- UoT-UWF-PartAI at SemEval-2021 Task 5: Self Attention Based Bi-GRU with Multi-Embedding Representation for Toxicity Highlighter
- Watershed of Artificial Intelligence: Human Intelligence, Machine Intelligence, and Biological Intelligence
- Finding Good Proofs for Description Logic Entailments Using Recursive Quality Measures (Extended Technical Report)
- LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo
- Secure and Efficient Federated Learning Through Layering and Sharding Blockchain
- Fisheye Lens Camera based Autonomous Valet Parking System
- One Backward from Ten Forward, Subsampling for Large-Scale Deep Learning
- Semi-Supervised Joint Estimation of Word and Document Readability
- Initializing LSTM internal states via manifold learning
- Shellcode_IA32: A Dataset for Automatic Shellcode Generation
- Graph Neural Networks for Traffic Forecasting
- Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
- Detection of Fake Users in SMPs Using NLP and Graph Embeddings
- Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain Approach
- Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users
- Weakly Supervised Volumetric Segmentation via Self-taught Shape Denoising Model
- Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model's Complexity
All 131
- Graphical Modeling for Multi-Source Domain Adaptation
- Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework
- Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation
- Three-stream network for enriched Action Recognition
- Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning
- Unsupervised Deep Manifold Attributed Graph Embedding
- A Knowledge Enhanced Learning and Semantic Composition Model for Multi-Claim Fact Checking
- Dual Transformer for Point Cloud Analysis
- LAST at CMCL 2021 Shared Task: Predicting Gaze Data During Reading with a Gradient Boosting Decision Tree Approach
- Deep Learning of the Eddington Tensor in the Core-collapse Supernova Simulation
- AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptions
- A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
- The Hessian Screening Rule
- Simple yet Sharp Sensitivity Analysis for Unmeasured Confounding
- Attention and Prediction Guided Motion Detection for Low-Contrast Small Moving Targets
- Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding
- Node Embedding using Mutual Information and Self-Supervision based Bi-level Aggregation
- Structure-Aware Hierarchical Graph Pooling using Information Bottleneck
- Multi-view Deep One-class Classification: A Systematic Exploration
- SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfer
- A Review of the Non-Invasive Techniques for Monitoring Different Aspects of Sleep
- Unsupervised Multi-Source Domain Adaptation for Person Re-Identification
- Exploring Uncertainty in Deep Learning for Construction of Prediction Intervals
- Document Structure aware Relational Graph Convolutional Networks for Ontology Population
- Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions
- Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction
- If your data distribution shifts, use self-learning
- Detecting Personality and Emotion Traits in Crowds from Video Sequences
- One Billion Audio Sounds from GPU-enabled Modular Synthesis
- Equity and Artificial Intelligence in Education: Will "AIEd" Amplify or Alleviate Inequities in Education?
- Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News