Thread by @stephenwithavee

Time for #PapersThatMakeYouGoHmmm! A weekly summary of new ML papers from arXiv that make me think one or more of:

1. That looks useful!
2. That's an interesting approach!
3. A business could be built around this!
4. How did they do that?!

Cognitive Coding of Speech

sciencewise.info/bookmarks/2110…

Momentum Doesn't Change the Implicit Bias

sciencewise.info/bookmarks/2110…

Anomaly Detection in Beehives: An Algorithm Comparison

sciencewise.info/bookmarks/2110…

Neural Tangent Kernel Eigenvalues Accurately Predict Generalization

sciencewise.info/bookmarks/2110…

On the Limitations of Multimodal VAEs

sciencewise.info/bookmarks/2110…

Towards Sample-efficient Apprenticeship Learning from Suboptimal Demonstration

sciencewise.info/bookmarks/2110…

When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits

sciencewise.info/bookmarks/2110…

Teaching Robots to Grasp Like Humans: An Interactive Approach

sciencewise.info/bookmarks/2110…

Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design

sciencewise.info/bookmarks/2110…

Topological Data Analysis (TDA) Techniques Enhance Hand Pose Classification from ECoG Neural Recordings

sciencewise.info/bookmarks/2110…

β-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap

sciencewise.info/bookmarks/2110…

A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution

sciencewise.info/bookmarks/2110…

COVID-Datathon: Biomarker identification for COVID-19 severity based on BALF scRNA-seq data

sciencewise.info/bookmarks/2110…

A Review on Part-of-Speech Technologies

sciencewise.info/bookmarks/2110…

NormVAE: Normative Modeling on Neuroimaging Data using Variational Autoencoders

sciencewise.info/bookmarks/2110…

Mixture Model Auto-Encoders: Deep Clustering through Dictionary Learning

sciencewise.info/bookmarks/2110…

Learning to Follow Language Instructions with Compositional Policies

sciencewise.info/bookmarks/2110…

Does Preprocessing Help Training Over-parameterized Neural Networks?

sciencewise.info/bookmarks/2110…

Self-explaining Neural Network with Plausible Explanations

sciencewise.info/bookmarks/2110…

Deep Learning of Potential Outcomes

sciencewise.info/bookmarks/2110…

Explainable Fact-checking through Question Answering

sciencewise.info/bookmarks/2110…

REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents

sciencewise.info/bookmarks/2110…

A Survey on Proactive Customer Care: Enabling Science and Steps to Realize it

sciencewise.info/bookmarks/2110…

NFT-K: Non-Fungible Tangent Kernels

sciencewise.info/bookmarks/2110…

SCEHR: Supervised Contrastive Learning for Clinical Risk Prediction using Electronic Health Records

sciencewise.info/bookmarks/2110…

CoRGi: Content-Rich Graph Neural Networks with Attention

sciencewise.info/bookmarks/2110…

Long Expressive Memory for Sequence Modeling

sciencewise.info/bookmarks/2110…

On the Self-Penalization Phenomenon in Feature Selection

sciencewise.info/bookmarks/2110…

BERTraffic: A Robust BERT-Based Approach for Speaker Change Detection and Role Identification of Air-Traffic Communications

sciencewise.info/bookmarks/2110…

BotNet Detection On Social Media

sciencewise.info/bookmarks/2110…

DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filtering

sciencewise.info/bookmarks/2110…

Spatial Data Mining of Public Transport Incidents reported in Social Media

sciencewise.info/bookmarks/2110…

Study of Drug Assimilation in Human System using Physics Informed Neural Networks

sciencewise.info/bookmarks/2110…

Disease Informed Neural Networks

sciencewise.info/bookmarks/2110…

Leveraging Transformers for StarCraft Macromanagement Prediction

sciencewise.info/bookmarks/2110…

Real-time EEG-based Emotion Recognition using Discrete Wavelet Transforms on Full and Reduced Channel Signals

sciencewise.info/bookmarks/2110…

Signal Processing on Cell Complexes

sciencewise.info/bookmarks/2110…

Which Samples Should be Learned First: Easy or Hard?

sciencewise.info/bookmarks/2110…

Predicting the spread of COVID-19 in Delhi, India using Deep Residual Recurrent Neural Networks

sciencewise.info/bookmarks/2110…

EEG functional connectivity and deep learning for automatic diagnosis of brain disorders: Alzheimer's disease and schizophrenia

sciencewise.info/bookmarks/2110…

Classification of anomalous gait using Machine Learning techniques and embedded sensors

sciencewise.info/bookmarks/2110…

An Activity Recognition Framework for Continuous Monitoring of Non-Steady-State Locomotion of Individuals with Parkinson's Disease

sciencewise.info/bookmarks/2110…

Fetal Gender Identification using Machine and Deep Learning Algorithms on Phonocardiogram Signals

sciencewise.info/bookmarks/2110…

Privacy-Preserving Phishing Email Detection Based on Federated Learning and LSTM

sciencewise.info/bookmarks/2110…

Tell Me How to Survey: Literature Review Made Simple with Automatic Reading Path Generation

sciencewise.info/bookmarks/2110…

Predicting the Stereoselectivity of Chemical Transformations by Machine Learning

sciencewise.info/bookmarks/2110…

The Rich Get Richer: Disparate Impact of Semi-Supervised Learning

sciencewise.info/bookmarks/2110…

Molecular Graph Generation via Geometric Scattering

sciencewise.info/bookmarks/2110…

A Survey of Online Auction Mechanism Design Using Deep Learning Approaches

sciencewise.info/bookmarks/2110…

Leveraging Automated Unit Tests for Unsupervised Code Translation

sciencewise.info/bookmarks/2110…

On the Parameter Combinations That Matter and on Those That do Not

sciencewise.info/bookmarks/2110…

Human-Robot Collaboration and Machine Learning: A Systematic Review of Recent Research

sciencewise.info/bookmarks/2110…

Few-shot Controllable Style Transfer for Low-Resource Settings: A Study in Indian Languages

sciencewise.info/bookmarks/2110…

Neural Attention-Aware Hierarchical Topic Model

sciencewise.info/bookmarks/2110…

Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance

sciencewise.info/bookmarks/2110…

Physics informed neural networks for continuum micromechanics

sciencewise.info/bookmarks/2110…

Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer

sciencewise.info/bookmarks/2110…

How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies

sciencewise.info/bookmarks/2110…

AI Total: Analyzing Security ML Models with Imperfect Data in Production

sciencewise.info/bookmarks/2110…

Novel EEG-based BCIs for Elderly Rehabilitation Enhancement

sciencewise.info/bookmarks/2110…

Contextual Sentence Classification: Detecting Sustainability Initiatives in Company Reports

sciencewise.info/bookmarks/2110…

Omni-Training for Data-Efficient Deep Learning

sciencewise.info/bookmarks/2110…

Explaining Reward Functions to Humans for Better Human-Robot Collaboration

sciencewise.info/bookmarks/2110…

Medical Dead-ends and Learning to Identify High-risk States and Treatments

sciencewise.info/bookmarks/2110…

Arachnophobia Exposure Therapy using Experience-driven Procedural Content Generation via Reinforcement Learning (EDPCGRL)

sciencewise.info/bookmarks/2110…

A Mining Software Repository Extended Cookbook: Lessons learned from a literature review

sciencewise.info/bookmarks/2110…

Task Allocation for Multi-Robot Task and Motion Planning: a case for Object Picking in Cluttered Workspaces

sciencewise.info/bookmarks/2110…

An Augmented Reality Platform for Introducing Reinforcement Learning to K-12 Students with Robots

sciencewise.info/bookmarks/2110…

Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization

sciencewise.info/bookmarks/2110…

Learning Visual Shape Control of Novel 3D Deformable Objects from Partial-View Point Clouds

sciencewise.info/bookmarks/2110…

Learning to Control Complex Robots Using High-Dimensional Interfaces: Preliminary Insights

sciencewise.info/bookmarks/2110…

A Framework for Rationale Extraction for Deep QA models

sciencewise.info/bookmarks/2110…

A Review of Physics-based Machine Learning in Civil Engineering

sciencewise.info/bookmarks/2110…

Human-Aware Robot Navigation via Reinforcement Learning with Hindsight Experience Replay and Curriculum Learning

sciencewise.info/bookmarks/2110…

Generating Disentangled Arguments with Prompts: A Simple Event Extraction Framework that Works

sciencewise.info/bookmarks/2110…

Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Neural Networks

sciencewise.info/bookmarks/2110…

Computing an Optimal Pitching Strategy in a Baseball At-Bat

sciencewise.info/bookmarks/2110…

How Can AI Recognize Pain and Express Empathy

sciencewise.info/bookmarks/2110…

TEET! Tunisian Dataset for Toxic Speech Detection

sciencewise.info/bookmarks/2110…

Multi-modal Self-supervised Pre-training for Regulatory Genome Across Cell Types

sciencewise.info/bookmarks/2110…

A MultiModal Social Robot Toward Personalized Emotion Interaction

sciencewise.info/bookmarks/2110…

Using Personality Detection Tools for Software Engineering Research: How Far Can We Go?

sciencewise.info/bookmarks/2110…

Bid Optimization using Maximum Entropy Reinforcement Learning

sciencewise.info/bookmarks/2110…

Advances in Multi-turn Dialogue Comprehension: A Survey

sciencewise.info/bookmarks/2110…

Feature Imitating Networks

sciencewise.info/bookmarks/2110…

Nano Version Control and Robots of Robots: Data Driven, Regenerative Production Code

sciencewise.info/bookmarks/2110…

An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design

sciencewise.info/bookmarks/2110…

Towards AI Logic for Social Reasoning

sciencewise.info/bookmarks/2110…

TiKick: Toward Playing Multi-agent Football Full Games from Single-agent Demonstrations

sciencewise.info/bookmarks/2110…

2021 Drexel Society of Artificial Intelligence Research Conference

sciencewise.info/bookmarks/2110…

CASPR: A Commonsense Reasoning-based Conversational Socialbot

sciencewise.info/bookmarks/2110…

An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design

sciencewise.info/bookmarks/2110…

DecGAN: Decoupling Generative Adversarial Network detecting abnormal neural circuits for Alzheimer's disease

sciencewise.info/bookmarks/2110…

Prediction of Political Leanings of Chinese Speaking Twitter Users

sciencewise.info/bookmarks/2110…

Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables

sciencewise.info/bookmarks/2110…

Relative Molecule Self-Attention Transformer

sciencewise.info/bookmarks/2110…

One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latency

sciencewise.info/bookmarks/2110…

Smart Crawling: A New Approach toward Focus Crawling from Twitter

sciencewise.info/bookmarks/2110…

Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models

sciencewise.info/bookmarks/2110…

Relative Molecule Self-Attention Transformer

sciencewise.info/bookmarks/2110…

Aspect-driven User Preference and News Representation Learning for News Recommendation

sciencewise.info/bookmarks/2110…

Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables

sciencewise.info/bookmarks/2110…

DecGAN: Decoupling Generative Adversarial Network detecting abnormal neural circuits for Alzheimer's disease

sciencewise.info/bookmarks/2110…

An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design

sciencewise.info/bookmarks/2110…

SAR-Net: A Scenario-Aware Ranking Network for PersonalizedFair Recommendation in Hundreds of Travel Scenarios

sciencewise.info/bookmarks/2110…

Learning to Select Historical News Articles for Interaction based Neural News Recommendation

sciencewise.info/bookmarks/2110…

Enabling Level-4 Autonomous Driving on a Single $1k Off-the-Shelf Card

sciencewise.info/bookmarks/2110…

StARformer: Transformer with State-Action-Reward Representations

sciencewise.info/bookmarks/2110…

Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression

sciencewise.info/bookmarks/2110…

Model-based analysis of brain activity reveals the hierarchy of language in 305 subjects

sciencewise.info/bookmarks/2110…

Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation

sciencewise.info/bookmarks/2110…

A Novel Clustering-Based Algorithm for Continuous and Non-invasive Cuff-Less Blood Pressure Estimation

sciencewise.info/bookmarks/2110…

NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment

sciencewise.info/bookmarks/2110…

Feudal Reinforcement Learning by Reading Manuals

sciencewise.info/bookmarks/2110…

OPEn: An Open-ended Physics Environment for Learning Without a Task

sciencewise.info/bookmarks/2110…

ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers

sciencewise.info/bookmarks/2110…

A Speaker-Aware Learning Framework for Improving Multi-turn Dialogue Coherence

sciencewise.info/bookmarks/2110…

Using UAVs for vehicle tracking and collision risk assessment at intersections

sciencewise.info/bookmarks/2110…

Truthful AI: Developing and governing AI that does not lie

sciencewise.info/bookmarks/2110…

Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese

sciencewise.info/bookmarks/2110…

MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction

sciencewise.info/bookmarks/2110…

Exploring Dense Retrieval for Dialogue Response Selection

sciencewise.info/bookmarks/2110…

Looper: An end-to-end ML platform for product decisions

sciencewise.info/bookmarks/2110…

SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures

sciencewise.info/bookmarks/2110…

BI-RADS BERT & Using Section Tokenization to Understand Radiology Reports

sciencewise.info/bookmarks/2110…

Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization

sciencewise.info/bookmarks/2110…

A Survey on Legal Question Answering Systems

sciencewise.info/bookmarks/2110…

Building Chinese Biomedical Language Models via Multi-Level Text Discrimination

sciencewise.info/bookmarks/2110…

Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer

sciencewise.info/bookmarks/2110…

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline

sciencewise.info/bookmarks/2110…

Token Pooling in Vision Transformers

sciencewise.info/bookmarks/2110…

StyleGAN-induced data-driven regularization for inverse problems

sciencewise.info/bookmarks/2110…

FOCUS: Familiar Objects in Common and Uncommon Settings

sciencewise.info/bookmarks/2110…

SVG-Net: An SVG-based Trajectory Prediction Model

sciencewise.info/bookmarks/2110…

Toward a Human-Level Video Understanding Intelligence

sciencewise.info/bookmarks/2110…

Lightweight Convolutional Neural Networks By Hypercomplex Parameterization

sciencewise.info/bookmarks/2110…

Diabetic Retinopathy Screening Using Custom-Designed Convolutional Neural Network

sciencewise.info/bookmarks/2110…

Boundary-aware Transformers for Skin Lesion Segmentation

sciencewise.info/bookmarks/2110…

SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection

sciencewise.info/bookmarks/2110…

Proposing a System Level Machine Learning Hybrid Architecture and Approach for a Comprehensive Autism Spectrum Disorder Diagnosis

sciencewise.info/bookmarks/2110…

An algorithm for a fairer and better voting system

sciencewise.info/bookmarks/2110…

Deep Slap Fingerprint Segmentation for Juveniles and Adults

sciencewise.info/bookmarks/2110…

A Neural Anthropometer Learning from Body Dimensions Computed on Human 3D Meshes

sciencewise.info/bookmarks/2110…

Trident Pyramid Networks: The importance of processing at the feature pyramid level for better object detection

sciencewise.info/bookmarks/2110…

How to Build a Curb Dataset with LiDAR Data for Autonomous Driving

sciencewise.info/bookmarks/2110…

Stereo Dense Scene Reconstruction and Accurate Laparoscope Localization for Learning-Based Navigation in Robot-Assisted Surgery

sciencewise.info/bookmarks/2110…

Neural Strokes: Stylized Line Drawing of 3D Shapes

sciencewise.info/bookmarks/2110…

Vision Transformer based COVID-19 Detection using Chest X-rays

sciencewise.info/bookmarks/2110…

Scene Editing as Teleoperation: A Case Study in 6DoF Kit Assembly

sciencewise.info/bookmarks/2110…

Causal ImageNet: How to discover spurious features in Deep Learning?

sciencewise.info/bookmarks/2110…

2nd Place Solution to Google Landmark Retrieval 2021

sciencewise.info/bookmarks/2110…

Toward a Visual Concept Vocabulary for GAN Latent Space

sciencewise.info/bookmarks/2110…

Field Extraction from Forms with Unlabeled Data

sciencewise.info/bookmarks/2110…

Inferring Offensiveness In Images From Natural Language Supervision

sciencewise.info/bookmarks/2110…

Explainability-Aware One Point Attack for Point Cloud Neural Networks

sciencewise.info/bookmarks/2110…

Landslide Detection in Real-Time Social Media Image Streams

sciencewise.info/bookmarks/2110…

A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection

sciencewise.info/bookmarks/2110…

EfficientPhys: Enabling Simple, Fast and Accurate Camera-Based Vitals Measurement

sciencewise.info/bookmarks/2110…

Arabic Speech Emotion Recognition Employing Wav2vec2.0 and HuBERT Based on BAVED Dataset

sciencewise.info/bookmarks/2110…

Adversarial Token Attacks on Vision Transformers

sciencewise.info/bookmarks/2110…

COVID-19 Face Mask Recognition with Advanced Face Cut Algorithm for Human Safety Measures

sciencewise.info/bookmarks/2110…

3D Meta-Segmentation Neural Network

sciencewise.info/bookmarks/2110…

Spatial-temporal V-Net for automatic segmentation and quantification of right ventricles in gated myocardial perfusion SPECT images

sciencewise.info/bookmarks/2110…

Mesh Draping: Parametrization-Free Neural Mesh Transfer

sciencewise.info/bookmarks/2110…

Self-supervised Learning is More Robust to Dataset Imbalance

sciencewise.info/bookmarks/2110…

6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning

sciencewise.info/bookmarks/2110…

Fast and Robust Structural Damage Analysis of Civil Infrastructure Using UAV Imagery

sciencewise.info/bookmarks/2110…

Deep Learning Based Person Re-Identification Methods: A Survey and Outlook of Recent Works

sciencewise.info/bookmarks/2110…

ZARTS: On Zero-order Optimization for Neural Architecture Search

sciencewise.info/bookmarks/2110…

Sketch Me A Video

sciencewise.info/bookmarks/2110…

3D Object Detection Combining Semantic and Geometric Features from Point Clouds

sciencewise.info/bookmarks/2110…

Beyond Road Extraction: A Dataset for Map Update using Aerial Images

sciencewise.info/bookmarks/2110…

Vector-quantized Image Modeling with Improved VQGAN

sciencewise.info/bookmarks/2110…

Google Landmark Retrieval 2021 Competition Third Place Solution

sciencewise.info/bookmarks/2110…

Deep Long-Tailed Learning: A Survey

sciencewise.info/bookmarks/2110…

CLIP-Adapter: Better Vision-Language Models with Feature Adapters

sciencewise.info/bookmarks/2110…

Adaptively Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation

sciencewise.info/bookmarks/2110…

Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques

sciencewise.info/bookmarks/2110…

Performance Evaluation of Deep Transfer Learning on Multiclass Identification of Common Weed Species in Cotton Production Systems

sciencewise.info/bookmarks/2110…

BuildingNet: Learning to Label 3D Buildings

sciencewise.info/bookmarks/2110…

Compact CNN Models for On-device Ocular-based User Recognition in Mobile Devices

sciencewise.info/bookmarks/2110…

Vectorization of Raster Manga by Deep Reinforcement Learning

sciencewise.info/bookmarks/2110…

Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency

sciencewise.info/bookmarks/2110…

SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition

sciencewise.info/bookmarks/2110…

Semi-Autoregressive Image Captioning

sciencewise.info/bookmarks/2110…

Learnable Adaptive Cosine Estimator (LACE) for Image Classification

sciencewise.info/bookmarks/2110…

Efficient Training of High-Resolution Representation Seismic Image Fault Segmentation Network by Weakening Anomaly Labels

sciencewise.info/bookmarks/2110…

Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block

sciencewise.info/bookmarks/2110…

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

sciencewise.info/bookmarks/2110…

CLIP4Caption ++: Multi-CLIP for Video Caption

sciencewise.info/bookmarks/2110…

ViSeRet: A simple yet effective approach to moment retrieval via fine-grained video segmentation

sciencewise.info/bookmarks/2110…

Sim2Air - Synthetic aerial dataset for UAV monitoring

sciencewise.info/bookmarks/2110…

An automated threshold Edge Drawing algorithm

sciencewise.info/bookmarks/2110…

Multiple Object Trackers in OpenCV: A Benchmark

sciencewise.info/bookmarks/2110…

SurroundNet: Towards Effective Low-Light Image Enhancement

sciencewise.info/bookmarks/2110…

Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos

sciencewise.info/bookmarks/2110…

Development and testing of an image transformer for explainable autonomous driving systems

sciencewise.info/bookmarks/2110…

UnfairGAN: An Enhanced Generative Adversarial Network for Raindrop Removal from A Single Image

sciencewise.info/bookmarks/2110…

MEDUSA: Multi-scale Encoder-Decoder Self-Attention Deep Neural Network Architecture for Medical Image Analysis

sciencewise.info/bookmarks/2110…

Early Melanoma Diagnosis with Sequential Dermoscopic Images

sciencewise.info/bookmarks/2110…

OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages

sciencewise.info/bookmarks/2110…

Inclusive Design: Accessibility Settings for People with Cognitive Disabilities

sciencewise.info/bookmarks/2110…

TAda! Temporally-Adaptive Convolutions for Video Understanding

sciencewise.info/bookmarks/2110…

M2GAN: A Multi-Stage Self-Attention Network for Image Rain Removal on Autonomous Vehicles

sciencewise.info/bookmarks/2110…

Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble

sciencewise.info/bookmarks/2110…

SlideGraph+: Whole Slide Image Level Graphs to Predict HER2Status in Breast Cancer

sciencewise.info/bookmarks/2110…

Improved Pillar with Fine-grained Feature for 3D Object Detection

sciencewise.info/bookmarks/2110…

Can machines learn to see without visual databases?

sciencewise.info/bookmarks/2110…

Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be

sciencewise.info/bookmarks/2110…

Satellite Image Semantic Segmentation

sciencewise.info/bookmarks/2110…

HyperCube: Implicit Field Representations of Voxelized 3D Models

sciencewise.info/bookmarks/2110…

MMIU: Dataset for Visual Intent Understanding in Multimodal Assistants

sciencewise.info/bookmarks/2110…

NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labels

sciencewise.info/bookmarks/2110…

Leveraging redundancy in attention with Reuse Transformers

sciencewise.info/bookmarks/2110…

Optical Character Recognition of 19th Century Classical Commentaries: the Current State of Affairs

sciencewise.info/bookmarks/2110…

The Dawn of Quantum Natural Language Processing

sciencewise.info/bookmarks/2110…

Breaking the Dilemma of Medical Image-to-image Translation

sciencewise.info/bookmarks/2110…

CovXR: Automated Detection of COVID-19 Pneumonia in Chest X-Rays through Machine Learning

sciencewise.info/bookmarks/2110…

Open-Set Recognition: A Good Closed-Set Classifier is All You Need

sciencewise.info/bookmarks/2110…

RelationRS: Relationship Representation Network for Object Detection in Aerial Images

sciencewise.info/bookmarks/2110…

The Computerized Classification of Micro-Motions in the Hand using Waveforms from Mobile Phone

sciencewise.info/bookmarks/2110…

DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning

sciencewise.info/bookmarks/2110…

Color Counting for Fashion, Art, and Design

sciencewise.info/bookmarks/2110…

EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation

sciencewise.info/bookmarks/2110…

Unsupervised Representation Learning for 3D Point Cloud Data

sciencewise.info/bookmarks/2110…

Oriented Feature Alignment for Fine-grained Object Recognition in High-Resolution Satellite Imagery

sciencewise.info/bookmarks/2110…

CLIP4Caption: CLIP for Video Caption

sciencewise.info/bookmarks/2110…

LENS: Localization enhanced by NeRF synthesis

sciencewise.info/bookmarks/2110…

Understanding of Emotion Perception from Art

sciencewise.info/bookmarks/2110…

Updating Street Maps using Changes Detected in Satellite Imagery

sciencewise.info/bookmarks/2110…

Ego4D: Around the World in 3,000 Hours of Egocentric Video

sciencewise.info/bookmarks/2110…

Data Incubation -- Synthesizing Missing Data for Handwriting Recognition

sciencewise.info/bookmarks/2110…

Top 3 in FG 2021 Families In the Wild Kinship Verification Challenge

sciencewise.info/bookmarks/2110…

Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset

sciencewise.info/bookmarks/2110…

Multi-center, multi-vendor automated segmentation of left ventricular anatomy in contrast-enhanced MRI

sciencewise.info/bookmarks/2110…

Unsupervised Data-Driven Nuclei Segmentation For Histology Images

sciencewise.info/bookmarks/2110…

Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers

sciencewise.info/bookmarks/2110…

A Review on Human Pose Estimation

sciencewise.info/bookmarks/2110…

Improving Users' Mental Model with Attention-directed Counterfactual Edits

sciencewise.info/bookmarks/2110…

Reason induced visual attention for explainable autonomous driving

sciencewise.info/bookmarks/2110…

Towards Safer Transportation: a self-supervised learning approach for traffic video deraining

sciencewise.info/bookmarks/2110…

Multiple Style Transfer via Variational AutoEncoder

sciencewise.info/bookmarks/2110…

DeepMoCap: Deep Optical Motion Capture Using Multiple Depth Sensors and Retro-Reflectors

sciencewise.info/bookmarks/2110…

HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media

sciencewise.info/bookmarks/2110…

Task-Driven Deep Image Enhancement Network for Autonomous Driving in Bad Weather

sciencewise.info/bookmarks/2110…

Coarse to Fine: Video Retrieval before Moment Localization

sciencewise.info/bookmarks/2110…

DeepSSM: A Blueprint for Image-to-Shape Deep Learning Models

sciencewise.info/bookmarks/2110…

A CLIP-Enhanced Method for Video-Language Understanding

sciencewise.info/bookmarks/2110…

Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast

sciencewise.info/bookmarks/2110…

Video-based cattle identification and action recognition

sciencewise.info/bookmarks/2110…

A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification

sciencewise.info/bookmarks/2110…

Wake-Cough: cough spotting and cougher identification for personalised long-term cough monitoring

sciencewise.info/bookmarks/2110…

Sequence-To-Sequence Voice Conversion using F0 and Time Conditioning and Adversarial Learning

sciencewise.info/bookmarks/2110…

Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training

sciencewise.info/bookmarks/2110…

Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech

sciencewise.info/bookmarks/2110…

KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms

sciencewise.info/bookmarks/2110…

A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming

sciencewise.info/bookmarks/2110…

Environment Aware Text-to-Speech Synthesis

sciencewise.info/bookmarks/2110…

Explaining the Attention Mechanism of End-to-End Speech Recognition Using Decision Trees

sciencewise.info/bookmarks/2110…

A study on the efficacy of model pre-training in developing neural text-to-speech system

sciencewise.info/bookmarks/2110…

Machine Translation Verbosity Control for Automatic Dubbing

sciencewise.info/bookmarks/2110…

NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild

sciencewise.info/bookmarks/2110…

Sub-word Level Lip Reading With Visual Attention

sciencewise.info/bookmarks/2110…

Playing for 3D Human Recovery

sciencewise.info/bookmarks/2110…

Learning Temporal 3D Human Pose Estimation with Pseudo-Labels

sciencewise.info/bookmarks/2110…

Simple Baseline for Single Human Motion Forecasting

sciencewise.info/bookmarks/2110…

Possibilistic Fuzzy Local Information C-Means with Automated Feature Selection for Seafloor Segmentation

sciencewise.info/bookmarks/2110…

Multi-View Self-Attention Based Transformer for Speaker Recognition

sciencewise.info/bookmarks/2110…

Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition

sciencewise.info/bookmarks/2110…

Crack detection using tap-testing and machine learning techniques to prevent potential rockfall incidents

sciencewise.info/bookmarks/2110…

Personalizing ASR with limited data using targeted subset selection

sciencewise.info/bookmarks/2110…

Poformer: A simple pooling transformer for speaker verification

sciencewise.info/bookmarks/2110…

Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets

sciencewise.info/bookmarks/2110…

Complex Network-Based Approach for Feature Extraction and Classification of Musical Genres

sciencewise.info/bookmarks/2110…

An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition

sciencewise.info/bookmarks/2110…

Data Augmentation with Locally-time Reversed Speech for Automatic Speech Recognition

sciencewise.info/bookmarks/2110…

Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis

sciencewise.info/bookmarks/2110…

TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context

sciencewise.info/bookmarks/2110…

MusicNet: Compact Convolutional Neural Network for Real-time Background Music Detection

sciencewise.info/bookmarks/2110…

UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training

sciencewise.info/bookmarks/2110…

Pitch Preservation In Singing Voice Synthesis

sciencewise.info/bookmarks/2110…

LaughNet: synthesizing laughter utterances from waveform silhouettes and a single laughter example

sciencewise.info/bookmarks/2110…

Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding

sciencewise.info/bookmarks/2110…

An Overview of Techniques for Biomarker Discovery in Voice Signal

sciencewise.info/bookmarks/2110…

Universal Paralinguistic Speech Representations Using Self-Supervised Conformers

sciencewise.info/bookmarks/2110…

PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Control

sciencewise.info/bookmarks/2110…

Using multiple reference audios and style embedding constraints for speech synthesis

sciencewise.info/bookmarks/2110…

Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition

sciencewise.info/bookmarks/2110…

S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations

sciencewise.info/bookmarks/2110…

A Melody-Unsupervision Model for Singing Voice Synthesis

sciencewise.info/bookmarks/2110…

DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding

sciencewise.info/bookmarks/2110…

All-neural beamformer for continuous speech separation

sciencewise.info/bookmarks/2110…

Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition

sciencewise.info/bookmarks/2110…

Fine-grained style control in Transformer-based Text-to-speech Synthesis

sciencewise.info/bookmarks/2110…

Speech Summarization using Restricted Self-Attention

sciencewise.info/bookmarks/2110…

COVID-19 Diagnosis from Cough Acoustics using ConvNets and Data Augmentation

sciencewise.info/bookmarks/2110…

Adapting TTS models For New Speakers using Transfer Learning

sciencewise.info/bookmarks/2110…

Music Sentiment Transfer

sciencewise.info/bookmarks/2110…

Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification

sciencewise.info/bookmarks/2110…

vocadito: A dataset of solo vocals with $f_0$, note, and lyric annotations

sciencewise.info/bookmarks/2110…

Word Order Does Not Matter For Speech Recognition

sciencewise.info/bookmarks/2110…

A sentiment-based modeling and analysis of stock price during the COVID-19: U- and Swoosh-shaped recovery

sciencewise.info/bookmarks/2110…

Protecting Retail Investors from Order Book Spoofing using a GRU-based Detection Model

sciencewise.info/bookmarks/2110…

Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks

sciencewise.info/bookmarks/2110…

Improve Cross-lingual Voice Cloning Using Low-quality Code-switched Data

sciencewise.info/bookmarks/2110…

Toward Degradation-Robust Voice Conversion

sciencewise.info/bookmarks/2110…

SingGAN: Generative Adversarial Network For High-Fidelity Singing Voice Generation

sciencewise.info/bookmarks/2110…

Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning

sciencewise.info/bookmarks/2110…

Music Playlist Title Generation: A Machine-Translation Approach

sciencewise.info/bookmarks/2110…

FedSpeech: Federated Text-to-Speech with Continual Learning

sciencewise.info/bookmarks/2110…

Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech

sciencewise.info/bookmarks/2110…

Revisiting IPA-based Cross-lingual Text-to-speech

sciencewise.info/bookmarks/2110…

Singer separation for karaoke content generation

sciencewise.info/bookmarks/2110…

End-to-end translation of human neural activity to speech with a dual-dual generative adversarial network

sciencewise.info/bookmarks/2110…

EIHW-MTG DiCOVA 2021 Challenge System Report

sciencewise.info/bookmarks/2110…

Reinforcement Learning for Systematic FX Trading

sciencewise.info/bookmarks/2110…

A Response to Philippe Lemoine's Critique on our Paper "Causal Impact of Masks, Policies, Behavior on Early Covid-19 Pandemic in the U.S."

sciencewise.info/bookmarks/2110…

An Automated Portfolio Trading System with Feature Preprocessing and Recurrent Reinforcement Learning

sciencewise.info/bookmarks/2110…

Exploring the Endogenous Nature of Meme Stocks Using the Log-Periodic Power Law Model and Confidence Indicator

sciencewise.info/bookmarks/2110…

Online Segregation

sciencewise.info/bookmarks/2110…

The Effects of Temperature on Economic Preferences

sciencewise.info/bookmarks/2110…

Towards a fully RL-based Market Simulator

sciencewise.info/bookmarks/2110…

An Empirical Analysis of how Internet Access Influences Public Opinion towards Undocumented Immigrants and Unaccompanied Children

sciencewise.info/bookmarks/2110…

@threadreaderapp unroll