Papers
Thu 7 Apr 2022
188 papers
- Unsupervised Prompt Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planningOffline RL and imitation learning from data → Imitation learning methods
- Learning to Compose Soft Prompts for Compositional Zero-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at ScaleOffline RL and imitation learning from data → Robot manipulation imitation learning
- Video Diffusion ModelsDiffusion models → Video generation
- Offline Reinforcement Learning for Safer Blood Glucose Control in People with Type 1 DiabetesOffline RL and imitation learning from data → Safe offline RL
- PALBERT: Teaching ALBERT to PonderEfficient LLM inference and serving → Early exit and edge inference
- 3D Perception based Imitation Learning under Limited Demonstration for Laparoscope Control in Robotic SurgeryOffline RL and imitation learning from data → Safe offline RL
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognitionMixture-of-experts → Multimodal MoE models
- Winoground: Probing Vision and Language Models for Visio-Linguistic CompositionalityLLM reasoning → Multimodal reasoning
- Matching Writers to Content Writing Tasks
- LSTM-RASA Based Agri Farm Assistant for Farmers
- Hybrid Transformer Network for Different Horizons-based Enriched Wind Speed Forecasting
- Twitter Dataset on the Russo-Ukrainian War
- Improving Information Cascade Modeling by Social Topology and Dual Role User Dependency
- So2Sat POP -- A Curated Benchmark Data Set for Population Estimation from Space on a Continental Scale
- Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy
- Farmer-Bot: An Interactive Bot for Farmers
- Stock Price Prediction using Sentiment Analysis and Deep Learning for Indian Markets
- PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets
- ShiftNAS: Towards Automatic Generation of Advanced Mulitplication-Less Neural Networks
- FastMapSVM: Classifying Complex Objects Using the FastMap Algorithm and Support-Vector Machines
- Forecasting new diseases in low-data settings using transfer learning
- Intelligent Sight and Sound: A Chronic Cancer Pain Dataset
- Measuring AI Systems Beyond Accuracy
- Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settings
- TorMentor: Deterministic dynamic-path, data augmentations with fractals
- Multi-objective optimization determines when, which and how to fuse deep networks: an application to predict COVID-19 outcomes
- Q-learning with online random forests
- Global ECG Classification by Self-Operational Neural Networks with Feature Injection
- Quantum version of the k-NN classifier based on a quantum sorting algorithm
- Compositional Generalization and Decomposition in Neural Program Synthesis
- Automated Isovist Computation for Minecraft
- Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling
- BankNote-Net: Open dataset for assistive universal currency recognition
- MHMS: Multimodal Hierarchical Multimedia Summarization
- GreaseVision: Rewriting the Rules of the Interface
- Decentralized Event-Triggered Federated Learning with Heterogeneous Communication Thresholds
- T4PdM: a Deep Neural Network based on the Transformer Architecture for Fault Diagnosis of Rotating Machinery
- A Kernel Method to Nonlinear Location Estimation with RSS-based Fingerprint
- Automated Design of Salient Object Detection Algorithms with Brain Programming
- A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework
- Gravitationally Lensed Black Hole Emission Tomography
- Using Multiple Self-Supervised Tasks Improves Model Robustness
- Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Data
- Introducing a Framework and a Decision Protocol to Calibrate Recommender Systems
- Physics-assisted Generative Adversarial Network for X-Ray Tomography
- Adaptive-Gravity: A Defense Against Adversarial Samples
- DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image
- Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision
- TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates
- Qade: Solving Differential Equations on Quantum Annealers
- Learning to Walk Autonomously via Reset-Free Quality-Diversity
- Identification of Autism spectrum disorder based on a novel feature selection method and Variational Autoencoder
- SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage
- Adapting CLIP For Phrase Localization Without Further Training
- FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment
- DaViT: Dual Attention Vision Transformers
- Total Variation Optimization Layers for Computer Vision
- Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction
- Unsupervised Image-to-Image Translation with Generative Prior
- Equivariance Discovery by Learned Parameter-Sharing
- Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
- tmVar 3.0: an improved variant concept recognition and normalization tool
- SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
- Zero-Shot Category-Level Object Pose Estimation
- Class-Incremental Learning with Strong Pre-trained Models
- The Effects of Regularization and Data Augmentation are Class Dependent
- Security Aspects of Quantum Machine Learning: Opportunities, Threats and Defenses
- Modeling Label Correlations for Second-Order Semantic Dependency Parsing with Mean-Field Inference
- Pneumonia Detection in Chest X-Rays using Neural Networks
- Unified Contrastive Learning in Image-Text-Label Space
- Pin the Memory: Learning to Generalize Semantic Segmentation
- Controlling Golog Programs against MTL Constraints
- Heterogeneous Target Speech Separation
- AutoRF: Learning 3D Object Radiance Fields from Single View Observations
- Testing the limits of natural language models for predicting human language judgments
- Risk-based regulation for all: The need and a method for a wide adoption solution for data-driven inspection targeting
- A Pathology-Based Machine Learning Method to Assist in Epithelial Dysplasia Diagnosis
- Accelerating ERM for data-driven algorithm design using output-sensitive techniques
- Practical Digital Disguises: Leveraging Face Swaps to Protect Patient Privacy
- Mapping the Multilingual Margins: Intersectional Biases of Sentiment Analysis Systems in English, Spanish, and Arabic
- Strong Admissibility, a Tractable Algorithmic Approach (proofs)
- Evaluating Procedures for Establishing Generative Adversarial Network-based Stochastic Image Models in Medical Imaging
- Abstracting Noisy Robot Programs
- Efficient Multiscale Object-based Superpixel Framework
- FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneity
- Visualizing Deep Neural Networks with Topographic Activation Maps
- Temporal Alignment for History Representation in Reinforcement Learning
- DeepXPalm: Tilt and Position Rendering using Palm-worn Haptic Display and CNN-based Tactile Pattern Recognition
- Distributed Reinforcement Learning for Robot Teams: A Review
- Many-to-many Splatting for Efficient Video Frame Interpolation
- Interval Bound Interpolation for Few-shot Learning with Few Tasks
- A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods
- Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutation
- Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models
- Covariance matrix preparation for quantum principal component analysis
- Optimizing the Long-Term Behaviour of Deep Reinforcement Learning for Pushing and Grasping
- ProbNVS: Fast Novel View Synthesis with Learned Probability-Guided Sampling
- Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results
All 188
- DynLight: Realize dynamic phase duration with multi-level traffic signal control
- Jacobian Norm for Unsupervised Source-Free Domain Adaptation
- BERTuit: Understanding Spanish language in Twitter through a native transformer
- Few-Shot Forecasting of Time-Series with Heterogeneous Channels
- Deep Visual Geo-localization Benchmark
- Task-Aware Active Learning for Endoscopic Image Analysis
- Half-sibling regression meets exoplanet imaging: PSF modeling and subtraction using a flexible, domain knowledge-driven, causal framework
- Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats
- Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence
- Finding Counterfactual Explanations through Constraint Relaxations
- Detecting Vocal Fatigue with Neural Embeddings
- Self-supervised learning for robust voice cloning
- Continual Inference: A Library for Efficient Online Inference with Deep Neural Networks in PyTorch
- Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0
- Incremental Prototype Tuning for Class Incremental Learning
- MAESTRO: Matched Speech Text Representations through Modality Matching
- Surface Vision Transformers: Flexible Attention-Based Modelling of Biomedical Surfaces
- Categorical Distributions of Maximum Entropy under Marginal Constraints
- Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations
- Correcting Mispronunciations in Speech using Spectrogram Inpainting
- Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances
- Detection of Distracted Driver using Convolution Neural Network
- Robust Event-Driven Interactions in Cooperative Multi-Agent Learning
- ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO
- Parameter-Efficient Abstractive Question Answering over Tables or Text
- Event Transformer. A sparse-aware solution for efficient event data processing
- Predictive coding and stochastic resonance as fundamental principles of auditory perception
- Learning Online Multi-Sensor Depth Fusion
- Implementing a Real-Time, YOLOv5 based Social Distancing Measuring System for Covid-19
- Inference over radiative transfer models using variational and expectation maximization methods
- Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift
- Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version
- PSTR: End-to-End One-Step Person Search With Transformers
- Learning to Sieve: Prediction of Grading Curves from Images of Concrete Aggregate
- Sparse Optical Flow-Based Line Feature Tracking
- Learning Local and Global Temporal Contexts for Video Semantic Segmentation
- A Comprehensive Review of Sign Language Recognition: Different Types, Modalities, and Datasets
- Enabling All In-Edge Deep Learning: A Literature Review
- Autoencoding Language Model Based Ensemble Learning for Commonsense Validation and Explanation
- Multi-Sample zeta-mixup: Richer, More Realistic Synthetic Samples from a p-Series Interpolant
- Using Decision Tree as Local Interpretable Model in Autoencoder-based LIME
- Swarm behavior tracking based on a deep vision algorithm
- Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model
- MTI-Net: A Multi-Target Speech Intelligibility Prediction Model
- Genre-conditioned Acoustic Models for Automatic Lyrics Transcription of Polyphonic Music
- MBI-Net: A Non-Intrusive Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids
- Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
- Sequence-Based Extractive Summarisation for Scientific Articles
- A Multi-Transformation Evolutionary Framework for Influence Maximization in Social Networks
- Deep Learning for Real Time Satellite Pose Estimation on Low Power Edge TPU
- CoCoSoDa: Effective Contrastive Learning for Code Search
- Entailment Graph Learning with Textual Entailment and Soft Transitivity
- mulEEG: A Multi-View Representation Learning on EEG Signals
- Multi-scale Context-aware Network with Transformer for Gait Recognition
- Korean Online Hate Speech Dataset for Multilabel Classification: How Can Social Science Improve Dataset on Hate Speech?
- Deep learning-based approach to reveal tumor mutational burden status from whole slide images across multiple cancer types
- Arabic Text-To-Speech (TTS) Data Preparation
- Towards Automatic Construction of Filipino WordNet: Word Sense Induction and Synset Induction Using Sentence Embeddings
- Composite Spatial Monte Carlo Integration Based on Generalized Least Squares
- HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection
- Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators
- Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum
- Leveraging Real Conversational Data for Multi-Channel Continuous Speech Separation
- What You See is What You Get: Principled Deep Learning via Distributional Generalization
- Accelerating Attention through Gradient-Based Learned Runtime Pruning
- Explicit Feature Interaction-aware Graph Neural Networks
- DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores
- Neural Implicit Flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal data
- Transformer-Based Language Models for Software Vulnerability Detection
- MC-UNet Multi-module Concatenation based on U-shape Network for Retinal Blood Vessels Segmentation
- A Joint Learning Approach for Semi-supervised Neural Topic Modeling
- L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation
- Convolutional Neural Network for Early Pulmonary Embolism Detection via Computed Tomography Pulmonary Angiography
- MDA GAN: Adversarial-Learning-based 3-D Seismic Data Interpolation and Reconstruction for Complex Missing
- MultiAuto-DeepONet: A Multi-resolution Autoencoder DeepONet for Nonlinear Dimension Reduction, Uncertainty Quantification and Operator Learning of Forward and Inverse Stochastic Problems
- Distributed Statistical Min-Max Learning in the Presence of Byzantine Agents
- FedCos: A Scene-adaptive Federated Optimization Enhancement for Performance Improvement
- Automated Sleep Staging via Parallel Frequency-Cut Attention
- Low-Dose CT Denoising via Sinogram Inner-Structure Transformer
- Flexible Sampling for Long-tailed Skin Lesion Classification
- Just-Noticeable-Difference Based Edge Map Quality Measure
- Optimization Models and Interpretations for Three Types of Adversarial Perturbations against Support Vector Machines
- DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors
- Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification
- Adversarial Machine Learning Attacks Against Video Anomaly Detection Systems
- Off-Policy Evaluation with Online Adaptation for Robot Exploration in Challenging Environments
- DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objects
- First-Order Algorithms for Nonlinear Generalized Nash Equilibrium Problems