Papers
Tue 5 Apr 2022
176 papers
- CLEVR-X: A Visual Reasoning Dataset for Natural Language ExplanationsLLM reasoning → Multimodal reasoning
- Learning Generalizable Dexterous Manipulation from Human Grasp AffordanceOffline RL and imitation learning from data → Robot manipulation imitation learning
- FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering DeepfakesLLM safety and security → Watermarking generated content and models
- SHAIL: Safety-Aware Hierarchical Adversarial Imitation Learning for Autonomous Driving in Urban EnvironmentsEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- An Exploratory Study on Code Attention in BERT
- LAMNER: Code Comment Generation Using Character Language Model and Named Entity Recognition
- On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages
- CGC: Contrastive Graph Clustering for Community Detection and Tracking
- Model-Based Deep Learning of Joint Probabilistic and Geometric Shaping for Optical Communication
- How Different are Pre-trained Transformers for Text Ranking?
- Comparative Survey of Multigraph Integration Methods for Holistic Brain Connectivity Mapping
- Brain-Inspired Hyperdimensional Computing: How Thermal-Friendly for Edge Computing?
- Mixing Signals: Data Augmentation Approach for Deep Learning Based Modulation Recognition
- Sliced gradient-enhanced Kriging for high-dimensional function approximation
- On the Effectiveness of Pretrained Models for API Learning
- Incremental Unsupervised Feature Selection for Dynamic Incomplete Multi-view Data
- Multi-task nonparallel support vector machine for classification
- A Transformer-Based Contrastive Learning Approach for Few-Shot Sign Language Recognition
- A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation
- Walk this Way! Entity Walks and Property Walks for RDF2vec
- Optimal service resource management strategy for IoT-based health information system considering value co-creation of users
- Inferring Rewards from Language in Context
- In-Pocket 3D Graphs Enhance Ligand-Target Compatibility in Generative Small-Molecule Creation
- Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows
- Deep Graphic FBSDEs for Opinion Dynamics Stochastic Control
- Privacy-Preserving Federated Learning via System Immersion and Random Matrix Encryption
- Efficient Pragmatic Program Synthesis with Informative Specifications
- Leveraging Disentangled Representations to Improve Vision-Based Keystroke Inference Attacks Under Low Data
- Towards End-to-end Unsupervised Speech Recognition
- Text2LIVE: Text-Driven Layered Image and Video Editing
- Pareto-optimal clustering with the primal deterministic information bottleneck
- Discovering and forecasting extreme events via active learning in neural operators
- Training-Free Robust Multimodal Learning via Sample-Wise Jacobian Regularization
- Considerations for Multilingual Wikipedia Research
- Adversarial Robustness through the Lens of Convolutional Filters
- Learning Optimal K-space Acquisition and Reconstruction using Physics-Informed Neural Networks
- Generative Enriched Sequential Learning (ESL) Approach for Molecular Design via Augmented Domain Knowledge
- "Does it come in black?" CLIP-like models are zero-shot recommenders
- Configuration Path Control
- Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation
- BeeTS: Smart Distributed Sensor Tuple Spaces combined with Agents using Bluetooth and IP Broadcasting
- Improving Voice Trigger Detection with Metric Learning
- Federated Cross Learning for Medical Image Segmentation
- Predicting and Explaining Mobile UI Tappability with Vision Modeling and Saliency Analysis
- Detecting Cloud-Based Phishing Attacks by Combining Deep Learning Models
- CHORE: Contact, Human and Object REconstruction from a single RGB image
- Imaging Conductivity from Current Density Magnitude using Neural Networks
- AAAI SSS-22 Symposium on Closing the Assessment Loop: Communicating Proficiency and Intent in Human-Robot Teaming
- OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses
- Texturify: Generating Textures on 3D Shape Surfaces
- A deep learning framework for the detection and quantification of drusen and reticular pseudodrusen on optical coherence tomography
- Zero-shot Blind Image Denoising via Implicit Neural Representations
- Hospital-Agnostic Image Representation Learning in Digital Pathology
- Explainable Deep Learning Algorithm for Distinguishing Incomplete Kawasaki Disease by Coronary Artery Lesions on Echocardiographic Imaging
- Comment on "Black Box Prediction Methods in Sports Medicine Deserve a Red Card for Reckless Practice: A Change of Tactics is Needed to Advance Athlete Care"
- SALISA: Saliency-based Input Sampling for Efficient Video Object Detection
- SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space
- Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining
- Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models
- Learning Pneumatic Non-Prehensile Manipulation with a Mobile Blower
- ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer
- Pyramid Frequency Network with Spatial Attention Residual Refinement Module for Monocular Depth Estimation
- Learning Speech Emotion Representations in the Quaternion Domain
- Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning
- Data-driven Influence Based Clustering of Dynamical Systems
- Jump-Start Reinforcement Learning
- Too Big to Fail? Active Few-Shot Learning Guided Logic Synthesis
- Towards Best Practices for Training Multilingual Dense Retrieval Models
- IFTT-PIN: Demonstrating the Self-Calibration Paradigm on a PIN-Entry Task
- MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering
- Can language models learn from explanations in context?
- A lightweight and accurate YOLO-like network for small target detection in Aerial Imagery
- Nearly minimax robust estimator of the mean vector by iterative spectral dimension reduction
- SAFARI: Sparsity enabled Federated Learning with Limited and Unreliable Communications
- Learning new physics efficiently with nonparametric methods
- Is it worth the effort? Understanding and contextualizing physical metrics in soccer
- PaLM: Scaling Language Modeling with Pathways
- Improving Human-AI Partnerships in Child Welfare: Understanding Worker Practices, Challenges, and Desires for Algorithmic Decision Support
- iSDF: Real-Time Neural Signed Distance Fields for Robot Perception
- ZETAR: Modeling and Computational Design of Strategic and Adaptive Compliance Policies
- Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval
- Aggregating distribution forecasts from deep ensembles
- Neural Convolutional Surfaces
- Rethinking Visual Geo-localization for Large-Scale Applications
- SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering
- Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation
- Design Guidelines for Inclusive Speaker Verification Evaluation Datasets
- Grounding of the Functional Object-Oriented Network in Industrial Tasks
- Arbitrary-Scale Image Synthesis
- Deep surrogate accelerated delayed-acceptance HMC for Bayesian inference of spatio-temporal heat fluxes in rotating disc systems
- Repeat after me: Self-supervised learning of acoustic-to-articulatory mapping by vocal imitation
- Learning to Bid Long-Term: Multi-Agent Reinforcement Learning with Long-Term and Sparse Reward in Repeated Auction Games
- Multi-Agent Distributed Reinforcement Learning for Making Decentralized Offloading Decisions
- Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors
- The Probabilistic Normal Epipolar Constraint for Frame-To-Frame Rotation Optimization under Uncertain Feature Positions
- Towards Explainable Meta-Learning for DDoS Detection
- RBGNet: Ray-based Grouping for 3D Object Detection
- Normalizing Flow-based Day-Ahead Wind Power Scenario Generation for Profitable and Reliable Delivery Commitments by Wind Farm Operators
- A Set Membership Approach to Discovering Feature Relevance and Explaining Neural Classifier Decisions
- IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images
All 176
- SD-Conv: Towards the Parameter-Efficiency of Dynamic Convolution
- Neural Computing with Coherent Laser Networks
- SNUG: Self-Supervised Neural Dynamic Garments
- EntSUM: A Data Set for Entity-Centric Summarization
- Model Based Meta Learning of Critics for Policy Gradients
- Abstractive summarization of hospitalisation histories with transformer networks
- Penalised FTRL With Time-Varying Constraints
- Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Task
- Multi-View Transformer for 3D Visual Grounding
- Multilinguals at SemEval-2022 Task 11: Transformer Based Architecture for Complex NER
- Hybrid Predictive Coding: Inferring, Fast and Slow
- Joint Learning of Feature Extraction and Cost Aggregation for Semantic Correspondence
- Leveraging Equivariant Features for Absolute Pose Regression
- Positive and Negative Critiquing for VAE-based Recommenders
- Detecting Anchors' Opinion in Hinghlish News Delivery
- Automatic Image Content Extraction: Operationalizing Machine Learning in Humanistic Photographic Studies of Large Visual Archives
- Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition
- Detector-Free Weakly Supervised Group Activity Recognition
- Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation
- SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model
- Improved and Efficient Conversational Slot Labeling through Question Answering
- MetaAudio: A Few-Shot Audio Classification Benchmark
- GP-BART: a novel Bayesian additive regression trees approach using Gaussian processes
- Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
- How do media talk about the Covid-19 pandemic? Metaphorical thematic clustering in Italian online newspapers
- Self-supervised learning -- A way to minimize time and effort for precision agriculture?
- Collective control of modular soft robots via embodied Spiking Neural Cellular Automata
- A machine learning-based framework for high resolution mapping of PM2.5 in Tehran, Iran, using MAIAC AOD data
- P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior
- VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices
- Real-time Hyperspectral Imaging in Hardware via Trained Metasurface Encoders
- Real-time Online Multi-Object Tracking in Compressed Domain
- Semi-supervised Semantic Segmentation with Error Localization Network
- Complex-Valued Autoencoders for Object Discovery
- Split Hierarchical Variational Compression
- Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation
- Design considerations for a hierarchical semantic compositional framework for medical natural language understanding
- HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings
- An efficient real-time target tracking algorithm using adaptive feature fusion
- Automating Reinforcement Learning with Example-based Resets
- DT2I: Dense Text-to-Image Generation from Region Descriptions
- Learning to Reduce Information Bottleneck for Object Detection in Aerial Images
- textitlatent-GLAT: Glancing at Latent Variables for Parallel Text Generation
- A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts
- A Survey on Dropout Methods and Experimental Verification in Recommendation
- A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition
- RL4ReAl: Reinforcement Learning for Register Allocation
- ELECRec: Training Sequential Recommenders as Discriminators
- LatentGAN Autoencoder: Learning Disentangled Latent Distribution
- Learning Video Salient Object Detection Progressively from Unlabeled Videos
- Fact Checking with Insufficient Evidence
- Bimodal Distributed Binarized Neural Networks
- The COVMis-Stance dataset: Stance Detection on Twitter for COVID-19 Misinformation
- An End-to-End Integrated Computation and Communication Architecture for Goal-oriented Networking: A Perspective on Live Surveillance Video
- Multi-Weight Respecification of Scan-specific Learning for Parallel Imaging
- Audio-visual multi-channel speech separation, dereverberation and recognition
- GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning
- Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation
- Region Rebalance for Long-Tailed Semantic Segmentation
- PSDoodle: Searching for App Screens via Interactive Sketching
- Controllable Garment Transfer
- Data Augmentation for Intent Classification with Off-the-shelf Large Language Models
- Autoregressive 3D Shape Generation via Canonical Mapping
- Towards On-Board Panoptic Segmentation of Multispectral Satellite Images
- Digital Twin Virtualization with Machine Learning for IoT and Beyond 5G Networks: Research Directions for Security and Optimal Control
- Unified Implicit Neural Stylization
- Fault-Tolerant Deep Learning: A Hierarchical Perspective
- Nonlocal optimization of binary neural networks
- Attention Distraction: Watermark Removal Through Continual Learning with Selective Forgetting
- High-Quality Pluralistic Image Completion via Code Shared VQGAN
- Online No-regret Model-Based Meta RL for Personalized Navigation
- Text Spotting Transformers
- Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data
- An Exploration of Active Learning for Affective Digital Phenotyping
- Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks
- Learning to Adapt to Domain Shifts with Few-shot Samples in Anomalous Sound Detection