Papers
Tue 24 Aug 2021
115 papers
- SimVLM: Simple Visual Language Model Pretraining with Weak SupervisionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- A Method for Inferring Polymers Based on Linear Regression and Integer Programming
- Binary Code based Hash Embedding for Web-scale Applications
- Spatio-temporal-spectral-angular observation model that integrates observations from UAV and mobile mapping vehicle for better urban mapping
- DQLEL: Deep Q-Learning for Energy-Optimized LoS/NLoS UWB Node Selection
- Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
- Self-optimizing adaptive optics control with Reinforcement Learning for high-contrast imaging
- Predicting Census Survey Response Rates With Parsimonious Additive Models and Structured Interactions
- The Effect of Noise Level on Causal Identification with Additive Noise Models
- OOWL500: Overcoming Dataset Collection Bias in the Wild
- NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstruction
- Online Dictionary Learning Based Fault and Cyber Attack Detection for Power Systems
- Using BERT Encoding and Sentence-Level Language Model for Sentence Ordering
- Domain Adaptation for Real-World Single View 3D Reconstruction
- An Effective Pixel-Wise Approach for Skin Colour Segmentation Using Pixel Neighbourhood Technique
- Real-time Indian Sign Language (ISL) Recognition
- Field-Guide-Inspired Zero-Shot Learning
- Entropic Gromov-Wasserstein between Gaussian Distributions
- Robustness Evaluation of Entity Disambiguation Using Prior Probes:the Case of Entity Overshadowing
- Correcting inter-scan motion artefacts in quantitative R1 mapping at 7T
- Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Posts
- Mitigating Statistical Bias within Differentially Private Synthetic Data
- The State of SLIVAR: What's next for robots, human-robot interaction, and (spoken) dialogue systems?
- Hybrid Multisource Feature Fusion for the Text Clustering
- The Word is Mightier than the Label: Learning without Pointillistic Labels using Data Programming
- GGNB: Graph-Based Gaussian Naive Bayes Intrusion Detection System for CAN Bus
- Are socially-aware trajectory prediction models really socially-aware?
- Quantum adaptive agents with efficient long-term memories
- A QuadTree Image Representation for Computational Pathology
- DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras
- Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density
- Cumulative Regret Analysis of the Piyavskii--Shubert Algorithm and Its Variants for Global Optimization
- Autoencoder-based Semantic Novelty Detection: Towards Dependable AI-based Systems
- Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision
- imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose
- Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark
- LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
- Physics-Informed Deep Learning: A Promising Technique for System Reliability Assessment
- S&P 500 Stock Price Prediction Using Technical, Fundamental and Text Data
- Adaptive Group Lasso Neural Network Models for Functions of Few Variables and Time-Dependent Data
- Graph Contrastive Pre-training for Effective Theorem Reasoning
- Next-generation perception system for automated defects detection in composite laminates via polarized computational imaging
- Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
- Reconcile Prediction Consistency for Balanced Object Detection
- Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation
- Reducing Exposure Bias in Training Recurrent Neural Network Transducers
- A Benchmark for Spray from Nearby Cutting Vehicles
- Adaptive Explainable Continual Learning Framework for Regression Problems with Focus on Power Forecasts
- DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
- Federated Learning for Privacy-Preserving Open Innovation Future on Digital Health
- More Than Words: Collocation Tokenization for Latent Dirichlet Allocation Models
- Relation Extraction from Tables using Artificially Generated Metadata
- Federated Learning for Open Banking
- Interpretable deep-learning models to help achieve the Sustainable Development Goals
- DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization
- Graph Neural Networks: Methods, Applications, and Opportunities
- Pen Spinning Hand Movement Analysis Using MediaPipe Hands
- From One to Many: A Deep Learning Coincident Gravitational-Wave Search
- MCUa: Multi-level Context and Uncertainty aware Dynamic Deep Ensemble for Breast Cancer Histology Image Classification
- REFINE: Random RangE FInder for Network Embedding
- Spatio-Temporal Self-Attention Network for Video Saliency Prediction
- Density-Based Dynamic Curriculum Learning for Intent Detection
- Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding
- Temporal Knowledge Consistency for Unsupervised Visual Representation Learning
- Energy time series forecasting-Analytical and empirical assessment of conventional and machine learning models
- On the Effectiveness of Genetic Operations in Symbolic Regression
- Data Aggregation for Reducing Training Data in Symbolic Regression
- Morality-based Assertion and Homophily on Social Media: A Cultural Comparison between English and Japanese Languages
- Are the Multilingual Models Better? Improving Czech Sentiment with Transformers
- GrADE: A graph based data-driven solver for time-dependent nonlinear partial differential equations
- Full-Velocity Radar Returns by Radar-Camera Fusion
- Layer-wise Adaptive Graph Convolution Networks Using Generalized Pagerank
- Improving Generalization of Batch Whitening by Convolutional Unit Optimization
- Data-Free Evaluation of User Contributions in Federated Learning
- Weakly Supervised Cross-platform Teenager Detection with Adversarial BERT
- Image-free single-pixel segmentation
- Outdoor Position Recovery from HeterogeneousTelco Cellular Data
- ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification
- Occlusion-robust Visual Markerless Bone Tracking for Computer-Assisted Orthopaedic Surgery
- Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
- Prompt-Learning for Fine-Grained Entity Typing
- DeepSleepNet-Lite: A Simplified Automatic Sleep Stage Scoring Model with Uncertainty Estimates
- Pooling Architecture Search for Graph Classification
- Detection of Criminal Texts for the Polish State Border Guard
- Lossy Medical Image Compression using Residual Learning-based Dual Autoencoder Model
- Support-Set Based Cross-Supervision for Video Grounding
- The staircase property: How hierarchical structure can guide deep learning
- Auto-Parsing Network for Image Captioning and Visual Question Answering
- sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification
- Taming the Beast: Learning to Control Neural Conversational Models
- Adaptation-Agnostic Meta-Training
- E-RAFT: Dense Optical Flow from Event Cameras
- Lossless Image Compression Using a Multi-Scale Progressive Statistical Model
- A generative adversarial approach to facilitate archival-quality histopathologic diagnoses from frozen tissue sections
- StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures
- Joint Learning Architecture for Multiple Object Tracking and Trajectory Forecasting
- Counterfactual Explainable Recommendation
- Making Person Search Enjoy the Merits of Person Re-identification
- Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning
All 115
- Unsupervised Depth Completion with Calibrated Backprojection Layers
- ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation
- Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study
- Improving Object Detection by Label Assignment Distillation
- Uncertainty Quantification of the 4th kind; optimal posterior accuracy-uncertainty tradeoff with the minimum enclosing ball
- ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones
- Maximum Likelihood Estimation for Multimodal Learning with Missing Modality
- CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation
- Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems
- Deep Signature FBSDE Algorithm
- Small Object Detection Based on Modified FSSD and Model Compression
- ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
- Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
- Continuous Treatment Recommendation with Deep Survival Dose Response Function
- Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications