Papers
Tue 22 Nov 2022
233 papers
- Don't Watch Me: A Spatio-Temporal Trojan Attack on Deep-Reinforcement-Learning-Augment Autonomous DrivingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning TasksLLM reasoning → Prompting and chain-of-thought reasoning
- Retrieval-Augmented Multimodal Language ModelingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
- Person Image Synthesis via Denoising Diffusion ModelDiffusion models → 3D, point cloud and scene generation
- EDICT: Exact Diffusion Inversion via Coupled TransformationsDiffusion models → Inverse problems and image restoration
- SinDiffusion: Learning a Diffusion Model from a Single Natural ImageDiffusion models → Diffusion foundations and sampling
- Can denoising diffusion probabilistic models generate realistic astrophysical fields?Diffusion models → Inverse problems and image restoration
- X2-VLM: All-In-One Pre-trained Model For Vision-Language TasksMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT ReconstructionDiffusion models → Medical imaging and segmentation
- Interpreting Neural Networks through the Polytope LensMechanistic interpretability → Circuits and mechanistic analysis
- DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion ModelsWorld models → Video-generation world models and simulators +1
- Evaluation of MPC-based Imitation Learning for Human-like Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- Accelerating Diffusion Sampling with Classifier-based Feature DistillationDiffusion models → Diffusion foundations and sampling +1
- Knowledge Prompting for Few-shot Action RecognitionMultimodal LLMs / vision-language models → Video understanding with MLLMs
- Differentiable Fuzzy ALC: A Neural-Symbolic Representation Language for Symbol GroundingLLM reasoning → Reasoning benchmarks and evaluation
- imitation: Clean Imitation Learning ImplementationsOffline RL and imitation learning from data → Imitation learning methods
- Learning-based social coordination to improve safety and robustness of cooperative autonomous vehicles in mixed trafficEnd-to-end autonomous driving → Cooperative and V2X driving
- A Survey on Backdoor Attack and Defense in Natural Language ProcessingLLM safety and security → Backdoor and data poisoning attacks
- The purpose of qualia: What if human thinking is not (only) information processing?
- Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition
- YZR-net : Self-supervised Hidden representations Invariant to Transformations for profanity detection
- Noise-resilient approach for deep tomographic imaging
- Discovering Unsupervised Behaviours from Full-State Trajectories
- Content-Based Medical Image Retrieval with Opponent Class Adaptive Margin Loss
- Clarity: an improved gradient method for producing quality visual counterfactual explanations
- BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic
- Predicting Biomedical Interactions with Probabilistic Model Selection for Graph Neural Networks
- Average Token Delay: A Latency Metric for Simultaneous Translation
- Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networks
- Decision Diagram-Based Branch-and-Bound with Caching for Dominance and Suboptimality Detection
- Fed-TDA: Federated Tabular Data Augmentation on Non-IID Data
- Compiler Provenance Recovery for Multi-CPU Architectures Using a Centrifuge Mechanism
- Pyrocast: a Machine Learning Pipeline to Forecast Pyrocumulonimbus (PyroCb) Clouds
- Mitigating Negative Transfer in Multi-Task Learning with Exponential Moving Average Loss Weighting Strategies
- Converting OpenStreetMap Data to Road Networks for Downstream Applications
- How do Authors' Perceptions of their Papers Compare with Co-authors' Perceptions and Peer-review Decisions?
- DETRs with Collaborative Hybrid Assignments Training
- Explaining Image Classifiers with Multiscale Directional Image Representation
- Projection-free Adaptive Regret with Membership Oracles
- Dehazed Image Quality Evaluation: From Partial Discrepancy to Blind Perception
- PNI : Industrial Anomaly Detection using Position and Neighborhood Information
- Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation
- A Generic Approach for Reproducible Model Distillation
- Safe Control and Learning Using Generalized Action Governor
- β-Multivariational Autoencoder for Entangled Representation Learning in Video Frames
- Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization
- SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Masking
- Promises and Pitfalls of Threshold-based Auto-labeling
- AutoReply: Detecting Nonsense in Dialogue Introspectively with Discriminative Replies
- Transfer Learning for Contextual Multi-armed Bandits
- Efficient Exploration using Model-Based Quality-Diversity with Gradients
- SuperTran: Reference Based Video Transformer for Enhancing Low Bitrate Streams in Real Time
- ArrayFlex: A Systolic Array Architecture with Configurable Transparent Pipelining
- Deep Neural Mel-Subband Beamformer for In-car Speech Separation
- Big Earth Data and Machine Learning for Sustainable and Resilient Agriculture
- UNSAT Solver Synthesis via Monte Carlo Forest Search
- Online Federated Learning via Non-Stationary Detection and Adaptation amidst Concept Drift
- Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
- Predicting the Type and Target of Offensive Social Media Posts in Marathi
- A Novel Center-based Deep Contrastive Metric Learning Method for the Detection of Polymicrogyria in Pediatric Brain MRI
- PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices
- Contextually Aware Intelligent Control Agents for Heterogeneous Swarms
- Using conditional variational autoencoders to generate images from atmospheric Cherenkov telescopes
- Sparse Probabilistic Circuits via Pruning and Growing
- WarpPINN: Cine-MR image registration with physics-informed neural networks
- Zero NeRF: Registration with Zero Overlap
- CASSPR: Cross Attention Single Scan Place Recognition
- Smart Agriculture : A Novel Multilevel Approach for Agricultural Risk Assessment over Unstructured Data
- NLP meets psychotherapy: Using predicted client emotions and self-reported client emotions to measure emotional coherence
- Scalable and Effective Conductance-based Graph Clustering
- SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning
- Time-Aware Datasets are Adaptive Knowledgebases for the New Normal
- OpenFE: Automated Feature Generation with Expert-level Performance
- Dynamic Loss For Robust Learning
- AeDet: Azimuth-invariant Multi-view 3D Object Detection
- Instant Volumetric Head Avatars
- Touch and Go: Learning from Human-Collected Vision and Touch
- MagicPony: Learning Articulated 3D Animals in the Wild
- On the Transferability of Visual Features in Generalized Zero-Shot Learning
- Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior
- VideoMap: Supporting Video Editing Exploration, Brainstorming, and Prototyping in the Latent Space
- ModelDiff: A Framework for Comparing Learning Algorithms
- Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
- HyperTuning: Toward Adapting Large Language Models without Back-propagation
- PIC-Score: Probabilistic Interpretable Comparison Score for Optimal Matching Confidence in Single- and Multi-Biometric (Face) Recognition
- Adaptive Prototypical Networks
- The impact of moving expenses on social segregation: a simulation with RL and ABM
- A Deep Reinforcement Learning Approach to Rare Event Estimation
- A Neural-Network-Based Convex Regularizer for Inverse Problems
- A generalized machine learning framework for brittle crack problems using transfer learning and graph neural networks
- ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation
- Learning context-aware adaptive solvers to accelerate quadratic programming
- Dynamic Depth-Supervised NeRF for Multi-View RGB-D Operating Room Images
- Expansive Participatory AI: Supporting Dreaming within Inequitable Institutions
- Multi-task Learning for Camera Calibration
- Progressive Learning with Cross-Window Consistency for Semi-Supervised Semantic Segmentation
- On Narrative Information and the Distillation of Stories
- Accuracy Prediction for NAS Acceleration using Feature Selection and Extrapolation
- DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair
- A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms
All 233
- OCTET: Object-aware Counterfactual Explanations
- An Emotion-Aware Multi-Task Approach to Fake News and Rumour Detection using Transfer Learning
- Gait Recognition in Large-scale Free Environment via Single LiDAR
- Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
- Method for Determining the Similarity of Text Documents for the Kazakh language, Taking Into Account Synonyms: Extension to TF-IDF
- GDPR Compliant Collection of Therapist-Patient-Dialogues
- U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Threshold
- GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild
- The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation
- Cosmology from Galaxy Redshift Surveys with PointNet
- Understanding Sparse Feature Updates in Deep Networks using Iterative Linearisation
- A Graph-Based Method for Soccer Action Spotting Using Unsupervised Player Classification
- Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras
- Computer Vision for Transit Travel Time Prediction: An End-to-End Framework Using Roadside Urban Imagery
- A Cross-Residual Learning for Image Recognition
- Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions
- Attacking Image Splicing Detection and Localization Algorithms Using Synthetic Traces
- Generalizable Industrial Visual Anomaly Detection with Self-Induction Vision Transformer
- PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples
- Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation
- Breaking Free from Fusion Rule: A Fully Semantic-driven Infrared and Visible Image Fusion
- Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields
- BESS: Balanced Entity Sampling and Sharing for Large-Scale Knowledge Graph Completion
- Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification
- Semantic Guided Level-Category Hybrid Prediction Network for Hierarchical Image Classification
- Global k-means++: an effective relaxation of the global k-means clustering algorithm
- Causal Abstraction with Soft Interventions
- Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation
- Relation-dependent Contrastive Learning with Cluster Sampling for Inductive Relation Prediction
- VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
- SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields
- Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring
- FE-Fusion-VPR: Attention-based Multi-Scale Network Architecture for Visual Place Recognition by Fusing Frames and Events
- A Reinforcement Learning Badminton Environment for Simulating Player Tactics (Student Abstract)
- AERO: Audio Super Resolution in the Spectral Domain
- Event Transformer+. A multi-purpose solution for efficient event data processing
- A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding
- Adaptive Sparse Structure Development with Pruning and Regeneration for Spiking Neural Networks
- Where Will Players Move Next? Dynamic Graphs and Hierarchical Fusion for Movement Forecasting in Badminton
- S2-Flow: Joint Semantic and Style Editing of Facial Images
- Photonic Quantum Computing For Polymer Classification
- Distributed Resource Allocation for URLLC in IIoT Scenarios: A Multi-Armed Bandit Approach
- Ontology-aware Learning and Evaluation for Audio Tagging
- SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
- Anatomy-guided domain adaptation for 3D in-bed human pose estimation
- A Combined Approach of Process Mining and Rule-based AI for Study Planning and Monitoring in Higher Education
- Multimorbidity Content-Based Medical Image Retrieval Using Proxies
- SRTGAN: Triplet Loss based Generative Adversarial Network for Real-World Super-Resolution
- The Monocular Depth Estimation Challenge
- Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification Models
- PromptTTS: Controllable Text-to-Speech with Text Descriptions
- OLGA : An Ontology and LSTM-based approach for generating Arithmetic Word Problems (AWPs) of transfer type
- PESE: Event Structure Extraction using Pointer Network based Encoder-Decoder Architecture
- MSS-DepthNet: Depth Prediction with Multi-Step Spiking Neural Network
- Event Causality Identification with Causal News Corpus -- Shared Task 3, CASE 2022
- Reinforcement Causal Structure Learning on Order Graph
- The transport problem for non-additive measures
- Aligning Source Visual and Target Language Domains for Unpaired Video Captioning
- Uncertainty-aware Vision-based Metric Cross-view Geolocalization
- Autonomation, Not Automation: Activities and Needs of European Fact-checkers as a Basis for Designing Human-Centered AI Systems
- Coreference Resolution through a seq2seq Transition-Based System
- MGADN: A Multi-task Graph Anomaly Detection Network for Multivariate Time Series
- City-Wide Perceptions of Neighbourhood Quality using Street View Images
- Converge to the Truth: Factual Error Correction via Iterative Constrained Editing
- A Large-Scale Dataset for Biomedical Keyphrase Generation
- GAN Inversion for Image Editing via Unsupervised Domain Adaptation
- HaRiM^+: Evaluating Summary Quality with Hallucination Risk
- Flow Guidance Deformable Compensation Network for Video Frame Interpolation
- Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark
- Improving Crowded Object Detection via Copy-Paste
- Video compression dataset and benchmark of learning-based video-quality metrics
- Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections
- AdaptDHM: Adaptive Distribution Hierarchical Model for Multi-Domain CTR Prediction
- Simulating Human Gaze with Neural Visual Attention
- Linear Interpolation In Parameter Space is Good Enough for Fine-Tuned Language Models
- Online Detection Of Supply Chain Network Disruptions Using Sequential Change-Point Detection for Hawkes Processes
- Ultrasound Detection of Subquadricipital Recess Distension
- Accelerated Solutions of Coupled Phase-Field Problems using Generative Adversarial Networks
- Brain MRI-to-PET Synthesis using 3D Convolutional Attention Networks
- CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation
- Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning
- Visually Grounded Commonsense Knowledge Acquisition
- Adaptive Dynamic Filtering Network for Image Denoising
- GitFL: Adaptive Asynchronous Federated Learning using Version Control
- Boundary-aware Camouflaged Object Detection via Deformable Point Sampling
- Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images
- DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priors
- Backdoor Cleansing with Unlabeled Data
- Robustness of Physics-Informed Neural Networks to Noise in Sensor Data
- Rethinking Implicit Neural Representations for Vision Learners
- ONeRF: Unsupervised 3D Object Segmentation from Multiple Views
- Dual Prototype Attention for Unsupervised Video Object Segmentation
- FastFlow: AI for Fast Urban Wind Velocity Prediction
- Time Series Forecasting with Hypernetworks Generating Parameters in Advance
- BASM: A Bottom-up Adaptive Spatiotemporal Model for Online Food Ordering Service
- PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understanding
- ViFi-Loc: Multi-modal Pedestrian Localization using GAN with Camera-Phone Correspondences
- PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design
- Level-S2fM: Structure from Motion on Neural Level Set of Implicit Surfaces
- Variation-based Cause Effect Identification
- Deep-Learning-Based Computer Vision Approach For The Segmentation Of Ball Deliveries And Tracking In Cricket
- Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
- Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning
- Explainability of Traditional and Deep Learning Models on Longitudinal Healthcare Records
- ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - English
- Vision-based localization methods under GPS-denied conditions
- Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge
- BotSIM: An End-to-End Bot Simulation Framework for Commercial Task-Oriented Dialog Systems
- Bayesian Inversion with Neural Operator (BINO) for Modeling Subdiffusion: Forward and Inverse Problems
- Learnable Spectral Wavelets on Dynamic Graphs to Capture Global Interactions
- Pred&Guide: Labeled Target Class Prediction for Guiding Semi-Supervised Domain Adaptation
- Multi-View Neural Surface Reconstruction with Structured Light
- Predicting adverse outcomes following catheter ablation treatment for atrial fibrillation
- Transformation-Equivariant 3D Object Detection for Autonomous Driving
- Disentangled Feature Learning for Real-Time Neural Speech Coding
- Robust High-dimensional Tuning Free Multiple Testing
- Ranking Inferences Based on the Top Choice of Multiway Comparisons
- A Short Survey of Systematic Generalization
- Teach-DETR: Better Training DETR with Teachers
- UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes
- A Reinforcement Learning Approach to Optimize Available Network Bandwidth Utilization
- COVID-Net Assistant: A Deep Learning-Driven Virtual Assistant for COVID-19 Symptom Prediction and Recommendation
- Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition
- Synthetic Data for Semantic Image Segmentation of Imagery of Unmanned Spacecraft
- Decision-making with Speculative Opponent Models
- Supervised Contrastive Learning on Blended Images for Long-tailed Recognition
- Genetic Algorithm for Program Synthesis
- One Eye is All You Need: Lightweight Ensembles for Gaze Estimation with Single Encoders
- Layered-Garment Net: Generating Multiple Implicit Garment Layers from a Single Image
- Multimodal Data Augmentation for Visual-Infrared Person ReID with Corrupted Data
- Best-k Search Algorithm for Neural Text Generation
- Confidence-guided Centroids for Unsupervised Person Re-Identification
- Latent Iterative Refinement for Modular Source Separation