Papers
Fri 10 Dec 2021
159 papers
- Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognitionMixture-of-experts → Multimodal MoE models
- More Control for Free! Image Synthesis with Semantic Diffusion GuidanceDiffusion models → Image generation, text-to-image and editing
- Mask-invariant Face Recognition through Template-level Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- DistilCSE: Effective Knowledge Distillation For Contrastive Sentence EmbeddingsKnowledge distillation → Knowledge distillation for LLMs
- Copy, Right? A Testing Framework for Copyright Protection of Deep Learning ModelsLLM safety and security → Watermarking generated content and models
- Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and GenerationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Malware Classification Using Static Disassembly and Machine Learning
- AtteSTNet -- An attention and subword tokenization based approach for code-switched text hate speech detection
- LSH methods for data deduplication in a Wikipedia artificial dataset
- ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery
- Robust Information Retrieval for False Claims with Distracting Entities In Fact Extraction and Verification
- Subspace Decomposition based DNN algorithm for elliptic type multi-scale PDEs
- Learning to Learn Transferable Attack
- Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speech
- A Discriminative Channel Diversification Network for Image Classification
- Short and Long Range Relation Based Spatio-Temporal Transformer for Micro-Expression Recognition
- Faster Deep Reinforcement Learning with Slower Online Network
- Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity
- Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems
- Logical Boltzmann Machines
- Learning distributed channel access policies for networked estimation: data-driven optimization in the mean-field regime
- Quality-Aware Multimodal Biometric Recognition
- Sequence-level self-learning with multiple hypotheses
- Revisiting Consistency Regularization for Semi-Supervised Learning
- Encoding priors in the brain: a reinforcement learning model for mouse decision making
- Deep ViT Features as Dense Visual Descriptors
- Edge-Compatible Reinforcement Learning for Recommendations
- Benchmarking human visual search computational models in natural scenes: models comparison and reference datasets
- Computer-Assisted Creation of Boolean Search Rules for Text Classification in the Legal Domain
- A Label Correction Algorithm Using Prior Information for Automatic and Accurate Geospatial Object Recognition
- Guided Generative Models using Weak Supervision for Detecting Object Spatial Arrangement in Overhead Images
- TempoQR: Temporal Question Reasoning over Knowledge Graphs
- Quantum Architecture Search via Continual Reinforcement Learning
- Self-Supervised Transformers for fMRI representation
- Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications
- Edge-Enhanced Dual Discriminator Generative Adversarial Network for Fast MRI with Parallel Imaging Using Multi-view Information
- Enhancing Multi-Scale Implicit Learning in Image Super-Resolution with Integrated Positional Encoding
- Information Prebuilt Recurrent Reconstruction Network for Video Super-Resolution
- PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM Connectomics
- Using Machine Learning to Predict Air Quality Index in New Delhi
- Label, Verify, Correct: A Simple Few Shot Object Detection Method
- Deep Learning based Framework for Automatic Diagnosis of Glaucoma based on analysis of Focal Notching in the Optic Nerve Head
- On Causally Disentangled Representations
- A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis
- A Puzzle-Based Dataset for Natural Language Inference
- Learning soft interventions in complex equilibrium systems
- Neural Belief Propagation for Scene Graph Generation
- Discourse-Aware Soft Prompting for Text Generation
- Pruning Pretrained Encoders with a Multitask Objective
- Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs
- A Framework for Fairness: A Systematic Review of Existing Fair AI Solutions
- Causal Knowledge Guided Societal Event Forecasting
- Unrolling PALM for sparse semi-blind source separation
- VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling
- Federated Two-stage Learning with Sign-based Voting
- Boosting Active Learning via Improving Test Performance
- Self-attention Does Not Need O(n2) Memory
- Concept Representation Learning with Contrastive Self-Supervised Learning
- Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Support
- Neural Multi-Quantile Forecasting for Optimal Inventory Management
- A Deep Learning Based Automated Hand Hygiene Training System
- Leveraging Joint-Diagonalization in Transform-Learning NMF
- Match Your Words! A Study of Lexical Matching in Neural Information Retrieval
- Artificial Intellgence -- Application in Life Sciences and Beyond. The Upper Rhine Artificial Intelligence Symposium UR-AI 2021
- Interpretable Clustering via Multi-Polytope Machines
- Analysis and Prediction of NLP Models Via Task Embeddings
- Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms
- Fast and scalable neuroevolution deep learning architecture search for multivariate anomaly detection
- HeadNeRF: A Real-time NeRF-based Parametric Head Model
- Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks
- On Fair Selection in the Presence of Implicit and Differential Variance
- Seq-Masks: Bridging the gap between appearance and gait modeling for video-based person re-identification
- How to Avoid Trivial Solutions in Physics-Informed Neural Networks
- AAAI FSS-21: Artificial Intelligence in Government and Public Sector Proceedings
- Eigenspace Restructuring: a Principle of Space and Frequency in Neural Networks
- Interaction-Aware Sensitivity Analysis for Aerodynamic Optimization Results using Information Theory
- Comparison of Markov chains via weak Poincar'e inequalities with application to pseudo-marginal MCMC
- Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity
- PERF: Performant, Explicit Radiance Fields
- Marvin: an Innovative Omni-Directional Robotic Assistant for Domestic Environments
- Automated tabulation of clinical trial results: A joint entity and relation extraction approach with transformer-based language representations
- A Review of Indoor Millimeter Wave Device-based Localization and Device-free Sensing Technologies and Applications
- Unified field theoretical approach to deep and recurrent neuronal networks
- Discrete neural representations for explainable anomaly detection
- Towards autonomous artificial agents with an active self: modeling sense of control in situated action
- GPU-accelerated image alignment for object detection in industrial applications
- Paradigms of Computational Agency
- Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions
- Shennong: a Python toolbox for audio speech features extraction
- PACMAN: PAC-style bounds accounting for the Mismatch between Accuracy and Negative log-loss
- A Validation Tool for Designing Reinforcement Learning Environments
- DeepRLS: A Recurrent Network Architecture with Least Squares Implicit Layers for Non-blind Image Deconvolution
- BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering
- Sparse Depth Completion with Semantic Mesh Deformation Optimization
- Graph-based Generative Face Anonymisation with Pose Preservation
- How Private Is Your RL Policy? An Inverse RL Based Analysis Framework
- Network Compression via Central Filter
- Surrogate-data-enriched Physics-Aware Neural Networks
- DronePose: The identification, segmentation, and orientation detection of drones via neural networks
- Visual Transformers with Primal Object Queries for Multi-Label Image Classification
All 159
- Critical configurations for three projective views
- Modelling DDoS Attacks in IoT Networks using Machine Learning
- Autonomous Aerial Robot for High-Speed Search and Intercept Applications
- Sentiment Analysis on Brazilian Portuguese User Reviews
- Monitoring and Adapting the Physical State of a Camera for Autonomous Vehicles
- Improving the Question Answering Quality using Answer Candidate Filtering based on Natural-Language Features
- Structure-Preserving Learning Using Gaussian Processes and Variational Integrators
- Beyond Parallel Pancakes: Quasi-Polynomial Time Guarantees for Non-Spherical Gaussian Mixtures
- DEBACER: a method for slicing moderated debates
- A Reinforcement Learning-based Adaptive Control Model for Future Street Planning, An Algorithm and A Case Study
- Couplformer:Rethinking Vision Transformer with Coupling Attention Map
- Robustification of Online Graph Exploration Methods
- Predicting Physical World Destinations for Commands Given to Self-Driving Cars
- Unsupervised Editing for Counterfactual Stories
- Optimizing Edge Detection for Image Segmentation with Multicut Penalties
- Multimedia Datasets for Anomaly Detection: A Review
- Batch Label Inference and Replacement Attacks in Black-Boxed Vertical Federated Learning
- The Large Labelled Logo Dataset (L3D): A Multipurpose and Hand-Labelled Continuously Growing Dataset
- Computing Diverse Shortest Paths Efficiently: A Theoretical and Experimental Study
- A Generative Car-following Model Conditioned On Driving Styles
- Towards Full-to-Empty Room Generation with Structure-Aware Feature Encoding and Soft Semantic Region-Adaptive Normalization
- A Self-supervised Mixed-curvature Graph Neural Network
- Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks
- UNIST: Unpaired Neural Implicit Shape Translation Network
- Cross-Modal Transferable Adversarial Attacks from Images to Videos
- Rethinking the Two-Stage Framework for Grounded Situation Recognition
- Efficient Action Poisoning Attacks on Linear Contextual Bandits
- Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation
- Where is Memory Information Stored in the Brain?
- Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
- LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks
- Learning-Augmented Algorithms for Online Steiner Tree
- Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentation
- Findings on Conversation Disentanglement
- Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning
- Hyperdimensional Feature Fusion for Out-Of-Distribution Detection
- Tradeoffs Between Contrastive and Supervised Learning: An Empirical Study
- Uncertainty, Edge, and Reverse-Attention Guided Generative Adversarial Network for Automatic Building Detection in Remotely Sensed Images
- FaceFormer: Speech-Driven 3D Facial Animation with Transformers
- Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0
- Attention-based Transformation from Latent Features to Point Clouds
- Dynamic hardware system for cascade SVM classification of melanoma
- PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records
- Building Autocorrelation-Aware Representations for Fine-Scale Spatiotemporal Prediction
- Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach
- Surrogate-based cross-correlation for particle image velocimetry
- Self-Ensemling for 3D Point Cloud Domain Adaption
- Representing 3D Shapes with Probabilistic Directed Distance Fields
- Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots
- IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes
- 3D Scene Understanding at Urban Intersection using Stereo Vision and Digital Map
- LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization
- Image-to-Image Translation-based Data Augmentation for Robust EV Charging Inlet Detection
- RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit
- Long-Range Thermal 3D Perception in Low Contrast Environments
- The Many Faces of Anger: A Multicultural Video Dataset of Negative Emotions in the Wild (MFA-Wild)
- Equivariant Quantum Graph Circuits
- Semantic Construction Grammar: Bridging the NL / Logic Divide
- Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion