Papers
Tue 29 Mar 2022
267 papers
- Fine-Grained Visual EntailmentLLM reasoning → Multimodal reasoning
- Diffusion Models for Counterfactual ExplanationsDiffusion models → Diffusion foundations and sampling
- Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual GroundingLLM reasoning → Multimodal reasoning
- ReIL: A Framework for Reinforced Intervention-based Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- A Fast Post-Training Pruning Framework for Transformers
- Worldwide city transport typology prediction with sentence-BERT based supervised learning via Wikipedia
- Artificial Intelligence Software Structured to Simulate Human Working Memory, Mental Imagery, and Mental Continuity
- Classification of NEQR Processed Classical Images using Quantum Neural Networks (QNN)
- A single Long Short-Term Memory network for enhancing the prediction of path-dependent plasticity with material heterogeneity and anisotropy
- ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion
- 4Weed Dataset: Annotated Imagery Weeds Dataset
- A Cognitive Architecture for Machine Consciousness and Artificial Superintelligence: Thought Is Structured by the Iterative Updating of Working Memory
- Bayesian optimization with known experimental and design constraints for chemistry applications
- A Derivation of Nesterov's Accelerated Gradient Algorithm from Optimal Control Theory
- Efficient Localness Transformer for Smart Sensor-Based Energy Disaggregation
- Recent improvements of ASR models in the face of adversarial attacks
- An Artificial Intelligence Browser Architecture (AIBA) For Our Kind and Others: A Voice Name System Speech implementation with two warrants, Wake Neutrality and Value Preservation of Personally Identifiable Information
- Parameter-efficient Model Adaptation for Vision Transformers
- Smooth Robust Tensor Completion for Background/Foreground Separation with Missing Pixels: Novel Algorithm with Convergence Guarantee
- A Multi-Stage Duplex Fusion ConvNet for Aerial Scene Classification
- When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation
- Zero-shot meta-learning for small-scale data from human subjects
- 4-bit Conformer with Native Quantization Aware Training for Speech Recognition
- Towards Learning Neural Representations from Shadows
- A Framework for Improving the Reliability of Black-box Variational Inference
- Self-Supervised Leaf Segmentation under Complex Lighting Conditions
- Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment
- Supervised Graph Contrastive Learning for Few-shot Node Classification
- Graph Neural Networks in IoT: A Survey
- Self-Contrastive Learning based Semi-Supervised Radio Modulation Classification
- Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
- Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approach
- Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization
- Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design
- Connections between Deep Equilibrium and Sparse Representation Models with Application to Hyperspectral Image Denoising
- Radial Autoencoders for Enhanced Anomaly Detection
- Learning to Detect Mobile Objects from LiDAR Scans Without Labels
- Proactive Image Manipulation Detection
- A deep learning model for burn depth classification using ultrasound imaging
- An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion
- Image Retrieval from Contextual Descriptions
- Indoor SLAM Using a Foot-mounted IMU and the local Magnetic Field
- On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation
- WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models
- Visualizing the Relationship Between Encoded Linguistic Information and Task Performance
- NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models
- Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics
- OdontoAI: A human-in-the-loop labeled data set and an online platform to boost research on dental panoramic radiographs
- Near-optimality for infinite-horizon restless bandits with many arms
- Neural Inertial Localization
- Topological Experience Replay
- NNLander-VeriF: A Neural Network Formal Verification Framework for Vision-Based Autonomous Aircraft Landing
- Autoregressive Co-Training for Learning Discrete Speech Representations
- VPTR: Efficient Transformers for Video Prediction
- ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment
- Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture
- An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis
- LinkBERT: Pretraining Language Models with Document Links
- StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis
- DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars
- Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data
- Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition
- CHEX: CHannel EXploration for CNN Model Compression
- Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection
- Target and Task specific Source-Free Domain Adaptive Image Segmentation
- Revisiting Neighborhood-based Link Prediction for Collaborative Filtering
- Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method
- Streaming parallel transducer beam search with fast-slow cascaded encoders
- FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering
- A Sparsity-promoting Dictionary Model for Variational Autoencoders
- Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data
- Evaluating Prompts Across Multiple Choice Tasks In a Zero-Shot Setting
- HardVis: Visual Analytics to Handle Instance Hardness Using Undersampling and Oversampling Techniques
- A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification
- Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version
- Exact Community Recovery in Correlated Stochastic Block Models
- Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey
- FlexR: Few-shot Classification with Language Embeddings for Structured Reporting of Chest X-rays
- Transformer Network-based Reinforcement Learning Method for Power Distribution Network (PDN) Optimization of High Bandwidth Memory (HBM)
- On Decoding Strategies for Neural Text Generators
- Transformer Inertial Poser: Real-time Human Motion Reconstruction from Sparse IMUs with Simultaneous Terrain Generation
- Integrative Few-Shot Learning for Classification and Segmentation
- OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction
- Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems
- Towards Everyday Virtual Reality through Eye Tracking
- Contrasting the landscape of contrastive and non-contrastive learning
- MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator
- Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage
- Improved Counting and Localization from Density Maps for Object Detection in 2D and 3D Microscopy Imaging
- Texture based Prototypical Network for Few-Shot Semantic Segmentation of Forest Cover: Generalizing for Different Geographical Regions
- Forecasting with Economic News
- EnvEdit: Environment Editing for Vision-and-Language Navigation
- Exploring Frequency Adversarial Attacks for Face Forgery Detection
- SurvCaus : Representation Balancing for Survival Causal Inference
- Nearly Minimax Algorithms for Linear Bandits with Shared Representation
- MatteFormer: Transformer-Based Image Matting via Prior-Tokens
- Consistency regularization-based Deep Polynomial Chaos Neural Network Method for Reliability Analysis
- Gaze-based Object Detection in the Wild
- Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise Distillation
- Synthesis and Execution of Communicative Robotic Movements with Generative Adversarial Networks
All 267
- NL-FCOS: Improving FCOS through Non-Local Modules for Object Detection
- Stochastic Conservative Contextual Linear Bandits
- PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision
- Classification of Hyperspectral Images Using SVM with Shape-adaptive Reconstruction and Smoothed Total Variation
- Integrating Lattice-Free MMI into End-to-End Speech Recognition
- Dynamic Latency for CTC-Based Streaming Automatic Speech Recognition With Emformer
- LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT
- Photographic Visualization of Weather Forecasts with Generative Adversarial Networks
- Angular Super-Resolution in Diffusion MRI with a 3D Recurrent Convolutional Autoencoder
- Cross-Media Scientific Research Achievements Retrieval Based on Deep Language Model
- Earnings-22: A Practical Benchmark for Accents in the Wild
- Heuristic-based Inter-training to Improve Few-shot Multi-perspective Dialog Summarization
- On Kernelized Multi-Armed Bandits with Constraints
- Discovering Governing Equations by Machine Learning implemented with Invariance
- Learning a Structured Latent Space for Unsupervised Point Cloud Completion
- Disentangling speech from surroundings with neural embeddings
- Quantum compiling with a variational instruction set for accurate and fast quantum computing
- Training Compute-Optimal Large Language Models
- Invariance Learning based on Label Hierarchy
- Image Segmentation with Adaptive Spatial Priors from Joint Registration
- ME-CapsNet: A Multi-Enhanced Capsule Networks with Routing Mechanism
- Graph Neural Networks are Dynamic Programmers
- Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search
- BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information
- OSOP: A Multi-Stage One Shot Object Pose Estimation Framework
- Treatment Learning Causal Transformer for Noisy Image Classification
- Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning
- Collision-Free Navigation using Evolutionary Symmetrical Neural Networks
- Learning neural audio features without supervision
- BELLATREX: Building Explanations through a LocaLly AccuraTe Rule EXtractor
- Achieving Guidance in Applied Machine Learning through Software Engineering Techniques
- An Unbiased Symmetric Matrix Estimator for Topology Inference under Partial Observability
- Improving the Learnability of Machine Learning APIs by Semi-Automated API Wrapping
- Neural representation of a time optimal, constant acceleration rendezvous
- Over-the-Air Federated Learning via Second-Order Optimization
- Learning Structured Gaussians to Approximate Deep Ensembles
- Representing 'how you say' with 'what you say': English corpus of focused speech and text reflecting corresponding implications
- SAR-ShipNet: SAR-Ship Detection Neural Network via Bidirectional Coordinate Attention and Multi-resolution Feature Fusion
- Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation
- Gaussian Control Barrier Functions : A Non-Parametric Paradigm to Safety
- Graph similarity learning for change-point detection in dynamic networks
- Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Lattice
- Machine Composition of Korean Music via Topological Data Analysis and Artificial Neural Network
- Protein language models trained on multiple sequence alignments learn phylogenetic relationships
- Efficient Virtual View Selection for 3D Hand Pose Estimation
- WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit
- Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus
- A Naturalistic Database of Thermal Emotional Facial Expressions and Effects of Induced Emotions on Memory
- UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal
- Eventor: An Efficient Event-Based Monocular Multi-View Stereo Accelerator on FPGA Platform
- Contextual Information Based Anomaly Detection for a Multi-Scene UAV Aerial Videos
- Clean Implicit 3D Structure from Noisy 2D STEM Images
- Long-term Video Frame Interpolation via Feature Propagation
- On Reinforcement Learning, Effect Handlers, and the State Monad
- Semantic properties of English nominal pluralization: Insights from word embeddings
- Spatiotemporal Patterns in Neurobiology: An Overview for Future Artificial Intelligence
- Quality Assurance of Generative Dialog Models in an Evolving Conversational Agent Used for Swedish Language Practice
- Deep Reinforcement Learning for Data-Driven Adaptive Scanning in Ptychography
- AutoCoMet: Smart Neural Architecture Search via Co-Regulated Shaping Reinforcement
- TransductGAN: a Transductive Adversarial Model for Novelty Detection
- Short-Term Word-Learning in a Dynamically Changing Environment
- Physics-informed deep-learning applications to experimental fluid mechanics
- Neural Face Video Compression using Multiple Views
- Learning to act: a Reinforcement Learning approach to recommend the best next activities
- Quantifying Societal Bias Amplification in Image Captioning
- Efficient Hybrid Network: Inducting Scattering Features
- Pareto Set Learning for Neural Multi-objective Combinatorial Optimization
- Category Guided Attention Network for Brain Tumor Segmentation in MRI
- Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification
- SepViT: Separable Vision Transformer
- Spoofing-Aware Speaker Verification by Multi-Level Fusion
- A Style-aware Discriminator for Controllable Image Translation
- mc-BEiT: Multi-choice Discretization for Image BERT Pre-training
- A Principles-based Ethics Assurance Argument Pattern for AI and Autonomous Systems
- Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning
- Face segmentation: A comparison between visible and thermal images
- The Inefficiency of Language Models in Scholarly Retrieval: An Experimental Walk-through
- Domain Invariant Siamese Attention Mask for Small Object Change Detection via Everyday Indoor Robot Navigation
- Self-Supervised Image Representation Learning with Geometric Set Consistency
- Nested Collaborative Learning for Long-Tailed Visual Recognition
- Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries
- Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production
- SIOD: Single Instance Annotated Per Category Per Image for Object Detection
- End-to-End Transformer Based Model for Image Captioning
- LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents
- Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis
- Task-specific Inconsistency Alignment for Domain Adaptive Object Detection
- Infrared and Visible Image Fusion via Interactive Compensatory Attention Adversarial Learning
- End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection
- AnyFace: Free-style Text-to-Face Synthesis and Manipulation
- Balanced Multimodal Learning via On-the-fly Gradient Modulation
- CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
- Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information
- Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction
- syslrn: Learning What to Monitor for Efficient Anomaly Detection
- Improving Persian Relation Extraction Models by Data Augmentation
- Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data
- Dressing in the Wild by Watching Dance Videos
- Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation
- Evolving Multi-Label Fuzzy Classifier
- Agreement or Disagreement in Noise-tolerant Mutual Learning?
- Cross-Modality High-Frequency Transformer for MR Image Super-Resolution
- In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
- Hybrid Routing Transformer for Zero-Shot Learning
- MatchNorm: Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real World
- Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes
- A Wavelet, AR and SVM based hybrid method for short-term wind speed prediction
- Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks
- Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation
- Accelerating Code Search with Deep Hashing and Code Classification
- Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching
- Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems
- Applying Syntaxunicodex2013Prosody Mapping Hypothesis and Prosodic Well-Formedness Constraints to Neural Sequence-to-Sequence Speech Synthesis
- A Multi-size Kernel based Adaptive Convolutional Neural Network for Bearing Fault Diagnosis
- Finding Structure and Causality in Linear Programs
- Sparse Image based Navigation Architecture to Mitigate the need of precise Localization in Mobile Robots
- MAT: Mask-Aware Transformer for Large Hole Image Inpainting
- Vision Transformers in Medical Computer Vision -- A Contemplative Retrospection
- Selective inference for k-means clustering
- Interactive Multi-Class Tiny-Object Detection
- Efficient Convex Optimization Requires Superlinear Memory
- Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation
- Efficient Reflectance Capture with a Deep Gated Mixture-of-Experts
- NeuraGen-A Low-Resource Neural Network based approach for Gender Classification
- Identification and classification of exfoliated graphene flakes from microscopy images using a hierarchical deep convolutional neural network
- Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation
- Analysis of EEG frequency bands for Envisioned Speech Recognition
- Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients
- Fine-tuning Image Transformers using Learnable Memory
- Semi-Supervised Image-to-Image Translation using Latent Space Mapping
- Enabling hand gesture customization on wrist-worn devices
- Best Arm Identification in Restless Markov Multi-Armed Bandits
- Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian
- Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
- AutoPoly: Predicting a Polygonal Mesh Construction Sequence from a Silhouette Image
- Zero-Query Transfer Attacks on Context-Aware Object Detectors
- Edge Detection and Deep Learning Based SETI Signal Classification Method
- SHOP: A Deep Learning Based Pipeline for near Real-Time Detection of Small Handheld Objects Present in Blurry Video
- Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation
- Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation
- Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection
- Affine Medical Image Registration with Coarse-to-Fine Vision Transformer
- Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification
- OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks
- Generalizing Few-Shot NAS with Gradient Matching
- Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASR
- SPAct: Self-supervised Privacy Preservation for Action Recognition
- Periocular Biometrics and its Relevance to Partially Masked Faces: A Survey
- SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation
- Light Field Depth Estimation via Stitched Epipolar Plane Images
- AnoDFDNet: A Deep Feature Difference Network for Anomaly Detection
- 3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow
- Coarse to Fine: Image Restoration Boosted by Multi-Scale Low-Rank Tensor Completion
- ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization
- Visualizations of Complex Sequences of Family-Infant Vocalizations Using Bag-of-Audio-Words Approach Based on Wav2vec 2.0 Features
- Long-term Visual Map Sparsification with Heterogeneous GNN
- Min-Max Similarity: A Contrastive Semi-Supervised Deep Learning Network for Surgical Tools Segmentation
- Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing
- Unified Transformer Tracker for Object Tracking
- Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth
- An Evaluation Dataset for Legal Word Embedding: A Case Study On Chinese Codex
- Self-Supervised Light Field Depth Estimation Using Epipolar Plane Images
- CAT-Net: A Cross-Slice Attention Transformer Model for Prostate Zonal Segmentation in MRI
- Practical Aspects of Zero-Shot Learning
- Learning to Synthesize Volumetric Meshes from Vision-based Tactile Imprints
- A Deep Learning Approach for Thermal Plume Prediction of Groundwater Heat Pumps
- Requirements Elicitation in Cognitive Service for Recommendation