Papers
Thu 17 Nov 2022
195 papers
- Dynamic Conditional Imitation Learning for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- DETRDistill: A Universal Knowledge Distillation Framework for DETR-familiesKnowledge distillation → Detection and dense prediction distillation
- RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and GenerationDiffusion models → 3D, point cloud and scene generation
- Knowledge distillation for fast and accurate DNA sequence correctionKnowledge distillation → Knowledge distillation for LLMs
- On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
- InstructPix2Pix: Learning to Follow Image Editing InstructionsDiffusion models → Image generation, text-to-image and editing
- Conffusion: Confidence Intervals for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Null-text Inversion for Editing Real Images using Guided Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- DiffusionDet: Diffusion Model for Object DetectionDiffusion models → Image generation, text-to-image and editing
- D3ETR: Decoder Distillation for Detection TransformerKnowledge distillation → Detection and dense prediction distillation
- Sub-Graph Learning for Spatiotemporal Forecasting via Knowledge DistillationKnowledge distillation → Graph neural network distillation
- UPTON: Preventing Authorship Leakage from Public Text Release via Data PoisoningLLM safety and security → Membership inference attacks
- Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion ModelsDiffusion models → Audio, speech and music
- BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion ModelsDiffusion models → Audio, speech and music
- Advanced Audio Aid for Blind People
- Exploring adaptation of VideoMAE for Audio-Visual Diarization & Social @ Ego4d Looking at me Challenge
- Introduction and Exemplars of Uncertainty Decomposition
- Detecting Methane Plumes using PRISMA: Deep Learning Model and Data Augmentation
- GLAMI-1M: A Multilingual Image-Text Fashion Dataset
- Text-Aware Dual Routing Network for Visual Question Answering
- Siamese based Neural Network for Offline Writer Identification on word level data
- Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
- One Venue, Two Conferences: The Separation of Chinese and American Citation Networks
- Brain informed transfer learning for categorizing construction hazards
- Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers
- Imputation of Missing Streamflow Data at Multiple Gauging Stations in Benin Republic
- DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift
- Dynamic Interactional And Cooperative Network For Shield Machine
- Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey
- Neural Inference of Gaussian Processes for Time Series Data of Quasars
- UMFuse: Unified Multi View Fusion for Human Editing applications
- Structured Pruning Adapters
- CRAFT: Concept Recursive Activation FacTorization for Explainability
- TempNet: Temporal Attention Towards the Detection of Animal Behaviour in Videos
- Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers
- VeriCompress: A Tool to Streamline the Synthesis of Verified Robust Compressed Neural Networks from Scratch
- MelHuBERT: A simplified HuBERT on Mel spectrograms
- Professional Presentation and Projected Power: A Case Study of Implicit Gender Information in English CVs
- Entry Dependent Expert Selection in Distributed Gaussian Processes Using Multilabel Classification
- Explainability Via Causal Self-Talk
- CAPE: Corrective Actions from Precondition Errors using Large Language Models
- Contrastive Credibility Propagation for Reliable Semi-Supervised Learning
- SMS: Spiking Marching Scheme for Efficient Long Time Integration of Differential Equations
- SAR-based landslide classification pretraining leads to better segmentation
- FairMILE: Towards an Efficient Framework for Fair Graph Representation Learning
- Proceedings of the 2nd Workshop on Logic and Practice of Programming (LPOP)
- Distributed Deep Joint Source-Channel Coding over a Multiple Access Channel
- Patch-Craft Self-Supervised Training for Correlated Image Denoising
- Online Distribution Shift Detection via Recency Prediction
- Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition
- Do graph neural networks learn traditional jet substructure?
- Audio Anti-spoofing Using a Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning
- Supervised Feature Compression based on Counterfactual Analysis
- Summarizing Community-based Question-Answer Pairs
- Bayesian Optimization of 2D Echocardiography Segmentation
- Spherical convolutional neural networks can improve brain microstructure estimation from diffusion MRI data
- Reducing Hallucinations in Neural Machine Translation with Feature Attribution
- Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
- Self-Supervised Visual Representation Learning via Residual Momentum
- Data-Centric Debugging: mitigating model failures via targeted data collection
- Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detection
- Machine Learning-Assisted Recurrence Prediction for Early-Stage Non-Small-Cell Lung Cancer Patients
- ProtSi: Prototypical Siamese Network with Data Augmentation for Few-Shot Subjective Answer Evaluation
- CoLI-Machine Learning Approaches for Code-mixed Language Identification at the Word Level in Kannada-English Texts
- Latent User Intent Modeling for Sequential Recommenders
- Deep learning for Lagrangian drift simulation at the sea surface
- SPACE: Speech-driven Portrait Animation with Controllable Expression
- Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks
- Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
- Mapping Tropical Forest Cover and Deforestation with Planet NICFI Satellite Images and Deep Learning in Mato Grosso State (Brazil) from 2015 to 2021
- Machine Learned Calabi-Yau Metrics and Curvature
- CAE v2: Context Autoencoder with CLIP Target
- MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors
- ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
- SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields
- UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization
- Assessing Neural Network Robustness via Adversarial Pivotal Tuning
- Monitoring machine learning (ML)-based risk prediction algorithms in the presence of confounding medical interventions
- I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision
- Cheeger Inequalities for Directed Graphs and Hypergraphs Using Reweighted Eigenvalues
- 3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation
- DeepSense 6G: A Large-Scale Real-World Multi-Modal Sensing and Communication Dataset
- Efficient Transformers with Dynamic Token Pooling
- VeLO: Training Versatile Learned Optimizers by Scaling Up
- An Advantage Using Feature Selection with a Quantum Annealer
- Learning to Counterfactually Explain Recommendations
- Heart Abnormality Detection from Heart Sound Signals using MFCC Feature and Dual Stream Attention Based Network
- Probing for Incremental Parse States in Autoregressive Language Models
- Zero-Shot Dynamic Quantization for Transformer Inference
- Learning 4DVAR inversion directly from observations
- A Finite-Particle Convergence Rate for Stein Variational Gradient Descent
- Style Classification of Rabbinic Literature for Detection of Lost Midrash Tanhuma Material
- Sources of performance variability in deep learning-based polyp detection
- EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones
- Thermodynamics of bidirectional associative memories
- AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training
- Towards Automated Design of Bayesian Optimization via Exploratory Landscape Analysis
- Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach
- A Spreader Ranking Algorithm for Extremely Low-budget Influence Maximization in Social Networks using Community Bridge Nodes
All 195
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors
- Language Conditioned Spatial Relation Reasoning for 3D Object Grounding
- CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers
- Why Deep Learning Generalizes
- On the Sample Complexity of Two-Layer Networks: Lipschitz vs. Element-Wise Lipschitz Activation
- Predicting Human Mobility via Self-supervised Disentanglement Learning
- Cross-Modal Adapter for Vision-Language Retrieval
- AlphaSnake: Policy Iteration on a Nondeterministic NP-hard Markov Decision Process
- TrafficCAM: A Versatile Dataset for Traffic Flow Segmentation
- Introduction to Online Control
- Learning to Communicate with Intent: An Introduction
- Dynamic Pricing with Volume Discounts in Online Settings
- Validation Diagnostics for SBI algorithms based on Normalizing Flows
- NorMatch: Matching Normalizing Flows with Discriminative Classifiers for Semi-Supervised Learning
- Hypergraph Transformer for Skeleton-based Action Recognition
- Spatial Graph Convolution Neural Networks for Water Distribution Systems
- DeepVoxNet2: Yet another CNN framework
- Enabling Collagen Quantification on HE-stained Slides Through Stain Deconvolution and Restained HE-HES
- Towards Good Practices in Evaluating Transfer Adversarial Attacks
- Convolutional neural networks for medical image segmentation
- Interpretable HER2 scoring by evaluating clinical Guidelines through a weakly supervised, constrained Deep Learning Approach
- ReLER@ZJU Submission to the Ego4D Moment Queries Challenge 2022
- Optimal Design of Volt/VAR Control Rules of Inverters using Deep Learning
- UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
- A Reinforcement Learning Approach for Process Parameter Optimization in Additive Manufacturing
- Locating Hidden Exoplanets in ALMA Data Using Machine Learning
- Neural Langevin Dynamics: towards interpretable Neural Stochastic Differential Equations
- Towards Building Text-To-Speech Systems for the Next Billion Users
- Parameter-Efficient Transformer with Hybrid Axial-Attention for Medical Image Segmentation
- InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges
- Ignore Previous Prompt: Attack Techniques For Language Models
- ImLiDAR: Cross-Sensor Dynamic Message Propagation Network for 3D Object Detection
- Hey ASR System! Why Aren't You More Inclusive? Automatic Speech Recognition Systems' Bias and Proposed Bias Mitigation Techniques. A Literature Review
- Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics
- EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance
- Back-Translation-Style Data Augmentation for Mandarin Chinese Polyphone Disambiguation
- EPCS: Endpoint-based Part-aware Curve Skeleton Extraction for Low-quality Point Clouds
- ArcAid: Analysis of Archaeological Artifacts using Drawings
- Solar Power driven EV Charging Optimization with Deep Reinforcement Learning
- Parameterization of state duration in Hidden semi-Markov Models: an application in electrocardiography
- Visual Commonsense-aware Representation Network for Video Captioning
- RDRN: Recursively Defined Residual Network for Image Super-Resolution
- Progressive Tree-Structured Prototype Network for End-to-End Image Captioning
- Abstractive Summarization Guided by Latent Hierarchical Document Structure
- Consultation Checklists: Standardising the Human Evaluation of Medical Note Generation
- DeepPrivacy2: Towards Realistic Full-Body Anonymization
- Detecting Arbitrary Keypoints on Limbs and Skis with Sparse Partly Correct Segmentation Masks
- aiMotive Dataset: A Multimodal Dataset for Robust Autonomous Driving with Long-Range Perception
- Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networks
- Feature-augmented Machine Reading Comprehension with Auxiliary Tasks
- Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impaired
- Machine Learning for Software Engineering: A Tertiary Study
- DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation
- FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data
- Physics-Informed Koopman Network
- LongFNT: Long-form Speech Recognition with Factorized Neural Transducer
- Personalized Federated Learning for Multi-task Fault Diagnosis of Rotating Machinery
- Hard Exudate Segmentation Supplemented by Super-Resolution with Multi-scale Attention Fusion Module
- Learning Mixtures of Markov Chains and MDPs
- Open-Domain Conversational Question Answering with Historical Answers
- ConNER: Consistency Training for Cross-lingual Named Entity Recognition
- Data Dimension Reduction makes ML Algorithms efficient
- Transfer learning for tensor Gaussian graphical models
- Data-Efficient Autoregressive Document Retrieval for Fact Verification
- ComMU: Dataset for Combinatorial Music Generation
- Planning Irregular Object Packing via Hierarchical Reinforcement Learning
- Self-Training with Purpose Preserving Augmentation Improves Few-shot Generative Dialogue State Tracking
- Balanced Deep CCA for Bird Vocalization Detection
- 3D-QueryIS: A Query-based Framework for 3D Instance Segmentation
- Execution-based Evaluation for Data Science Code Generation Models
- CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge
- Generalizable Deepfake Detection with Phase-Based Motion Analysis
- How to Fine-Tune Vision Models with SGD
- SFPDML: Securer and Faster Privacy-Preserving Distributed Machine Learning based on MKTFHE
- Learning Domain and Pose Invariance for Thermal-to-Visible Face Recognition
- I see you: A Vehicle-Pedestrian Interaction Dataset from Traffic Surveillance Cameras
- ACon2: Adaptive Conformal Consensus for Provable Blockchain Oracles
- Inadmissibility of the corrected Akaike information criterion
- TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation
- Blurring-Sharpening Process Models for Collaborative Filtering
- Targeted Attention for Generalized- and Zero-Shot Learning
- Interpretable Dimensionality Reduction by Feature Preserving Manifold Approximation and Projection
- Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
- Language-Assisted Deep Learning for Autistic Behaviors Recognition
- Proactive Resilient Transmission and Scheduling Mechanisms for mmWave Networks
- You Only Label Once: 3D Box Adaptation from Point Cloud to Image via Semi-Supervised Learning
- Statistical Inference for Coadded Astronomical Images
- FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data
- Testing for context-dependent changes in neural encoding in naturalistic experiments
- Longitudinal thermal imaging for scalable non-residential HVAC and occupant behaviour characterization
- Variable selection for nonlinear Cox regression model via deep learning
- Permutation-Invariant Tabular Data Synthesis
- Active Learning with Expected Error Reduction
- Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning
- A Generalized Latent Factor Model Approach to Mixed-data Matrix Completion with Entrywise Consistency