Papers
Mon 4 Jul 2022
183 papers
- Discourse-Aware Graph Networks for Textual Logical ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
- Revisiting Classifier: Transferring Vision-Language Models for Video RecognitionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- WebShop: Towards Scalable Real-World Web Interaction with Grounded Language AgentsLLM agents and tool use → Web, search, and research agents
- Target-absent Human AttentionOffline RL and imitation learning from data → Robot manipulation imitation learning
- Memory Population in Continual Learning via Outlier EliminationMixture-of-experts → Mixture of LoRA experts
- Online Adaptive Personalization for Face Anti-spoofing
- NN2Rules: Extracting Rule List from Neural Networks
- Multilingual Disinformation Detection for Digital Advertising
- Attention mechanisms for physiological signal deep learning: which attention should we take?
- Building a Relation Extraction Baseline for Gene-Disease Associations: A Reproducibility Study
- Automated Classification of General Movements in Infants Using a Two-stream Spatiotemporal Fusion Network
- Refutation of Spectral Graph Theory Conjectures with Monte Carlo Search
- Factorizing Knowledge in Neural Networks
- Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models
- Automating the Design and Development of Gradient Descent Trained Expert System Networks
- AutoSpeed: A Linked Autoencoder Approach for Pulse-Echo Speed-of-Sound Imaging for Medical Ultrasound
- TT-PINN: A Tensor-Compressed Neural PDE Solver for Edge Computing
- Federated Split GANs
- Discrete Tree Flows via Tree-Structured Permutations
- Anomaly-aware multiple instance learning for rare anemia disorder classification
- Machine Learning in Access Control: A Taxonomy and Survey
- Probing via Prompting
- Are metrics measuring what they should? An evaluation of image captioning task metrics
- DEFORMER: Coupling Deformed Localized Patterns with Global Context for Robust End-to-end Speech Recognition
- How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
- Adaptive Fine-Grained Sketch-Based Image Retrieval
- A Causal Approach for Business Optimization: Application on an Online Marketplace
- BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model
- Disentangled Action Recognition with Knowledge Bases
- Do Not Take It for Granted: Comparing Open-Source Libraries for Software Development Effort Estimation
- An adaptive music generation architecture for games based on the deep learning Transformer mode
- BYHE: A Simple Framework for Boosting End-to-end Video-based Heart Rate Measurement Network
- TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
- Intelligent Exploration of Solution Spaces Exemplified by Industrial Reconfiguration Management
- Crime scene classification from skeletal trajectory analysis in surveillance settings
- Interaction Transformer for Human Reaction Generation
- Robot Vitals and Robot Health: Towards Systematically Quantifying Runtime Performance Degradation in Robots Under Adverse Conditions
- Location reference recognition from texts: A survey and comparison
- FACT: High-Dimensional Random Forests Inference
- A Cascade Model for Argument Mining in Japanese Political Discussions: the QA Lab-PoliInfo-3 Case Study
- Slice-by-slice deep learning aided oropharyngeal cancer segmentation with adaptive thresholding for spatial uncertainty on FDG PET and CT images
- Egocentric Video-Language Pretraining @ Ego4D Challenge 2022
- Breaking Feedback Loops in Recommender Systems with Causal Inference
- Beyond mAP: Towards better evaluation of instance segmentation
- Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions
- PVO: Panoptic Visual Odometry
- Recommendation Systems with Distribution-Free Reliability Guarantees
- Invariant and Transportable Representations for Anti-Causal Domain Shifts
- CRFormer: A Cross-Region Transformer for Shadow Removal
- Deep Learning for Short-term Instant Energy Consumption Forecasting in the Manufacturing Sector
- Accurate RNA 3D structure prediction using a language model-based deep learning approach
- Classification of Alzheimer's Disease Using the Convolutional Neural Network (CNN) with Transfer Learning and Weighted Loss
- LaTeRF: Label and Text Driven Object Radiance Fields
- Interpretable Fusion Analytics Framework for fMRI Connectivity: Self-Attention Mechanism and Latent Space Item-Response Model
- Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks
- Spatiotemporal Feature Learning Based on Two-Step LSTM and Transformer for CT Scans
- Quantum Neural Network Compression
- De-Biasing Generative Models using Counterfactual Methods
- Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets
- Goal-Conditioned Generators of Deep Policies
- Back to MLP: A Simple Baseline for Human Motion Prediction
- General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States
- Fidelity of Ensemble Aggregation for Saliency Map Explanations using Bayesian Optimization Techniques
- Progressive Latent Replay for efficient Generative Rehearsal
- Selectively increasing the diversity of GAN-generated samples
- High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent
- Multi-class Classification from Multiple Unlabeled Datasets with Partial Risk Regularization
- Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness
- Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)
- Masked Autoencoders in 3D Point Cloud Representation Learning
- Wild Networks: Exposure of 5G Network Infrastructures to Adversarial Examples
- VEM2L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion
- Efficient Lung Cancer Image Classification and Segmentation Algorithm Based on Improved Swin Transformer
- Variational Neural Networks
- Adaptive GLCM sampling for transformer-based COVID-19 detection on CT
- Learning state machines via efficient hashing of future traces
- Mix and Match: An Empirical Study on Training Corpus Composition for Polyglot Text-To-Speech (TTS)
- Deep Contrastive One-Class Time Series Anomaly Detection
- Physics-informed compressed sensing for PC-MRI: an inverse Navier-Stokes problem
- Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection
- Generalisable Methods for Early Prediction in Interactive Simulations for Education
- Dynamic Ranking and Translation Synchronization
- GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion
- DeepPyramid: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos
- Open-world Semantic Segmentation for LIDAR Point Clouds
- Solving the Traveling Salesperson Problem with Precedence Constraints by Deep Reinforcement Learning
- Representation Learning with Information Theory for COVID-19 Detection
- Cybersecurity Entity Alignment via Masked Graph Attention Networks
- Dynamic Contrastive Distillation for Image-Text Retrieval
- Comparing Feature Importance and Rule Extraction for Interpretability on Text Data
- A Robust Ensemble Model for Patasitic Egg Detection and Classification
- Simultaneous Contact-Rich Grasping and Locomotion via Distributed Optimization Enabling Free-Climbing for Multi-Limbed Robots
- Positive-Negative Equal Contrastive Loss for Semantic Segmentation
- Disentangling Random and Cyclic Effects in Time-Lapse Sequences
- Satellite image data downlink scheduling problem with family attribute: Model &Algorithm
- The Neural-Prediction based Acceleration Algorithm of Column Generation for Graph-Based Set Covering Problems
- Vehicle Trajectory Prediction on Highways Using Bird Eye View Representations and Deep Learning
- I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
- VECtor: A Versatile Event-Centric Benchmark for Multi-Sensor SLAM
- Using contextual sentence analysis models to recognize ESG concepts
All 183
- Large-scale Robustness Analysis of Video Action Recognition Models
- Hessian-Free Second-Order Adversarial Examples for Adversarial Learning
- Memory Efficient Patch-based Training for INR-based GANs
- BiTAT: Neural Network Binarization with Task-dependent Aggregated Transformation
- Autonomous Drug Design with Multi-Armed Bandits
- Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalography
- FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy
- Learning Disentangled Representations for Controllable Human Motion Prediction
- Exploring Lottery Ticket Hypothesis in Spiking Neural Networks
- Detection of ADHD based on Eye Movements during Natural Viewing
- Task Discrepancy Maximization for Fine-grained Few-Shot Classification
- GraphVid: It Only Takes a Few Nodes to Understand a Video
- Probabilistic forecasting for geosteering in fluvial successions using a generative adversarial network
- Towards Real-World Video Denosing: A Practical Video Denosing Dataset and Network
- Multi-scale alignment and Spatial ROI Module for COVID-19 Diagnosis
- Explore Faster Localization Learning For Scene Text Detection
- Accurate Instance-Level CAD Model Retrieval in a Large-Scale Database
- Safe Reinforcement Learning via Confidence-Based Filters
- Spectral Power Profile Optimization of Field-Deployed WDM Network by Remote Link Modeling
- Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022
- The least-control principle for local learning at equilibrium
- Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters
- DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning
- BoAT v2 -- A Web-Based Dependency Annotation Tool with Focus on Agglutinative Languages
- Computer vision application for improved product traceability in the granite manufacturing industry
- Harmonizer: Learning to Perform White-Box Image and Video Harmonization
- Vietnamese Capitalization and Punctuation Recovery Models
- Assessing the Performance of Automated Prediction and Ranking of Patient Age from Chest X-rays Against Clinicians
- NodeTrans: A Graph Transfer Learning Approach for Traffic Prediction
- Real Time Egocentric Segmentation for Video-self Avatar in Mixed Reality
- A New Index for Clustering Evaluation Based on Density Estimation
- Game State Learning via Game Scene Augmentation
- FFCNet: Fourier Transform-Based Frequency Learning and Complex Convolutional Network for Colon Disease Classification
- Solving Learn-to-Race Autonomous Racing Challenge by Planning in Latent Space
- FlowNAS: Neural Architecture Search for Optical Flow Estimation
- DiffML: End-to-end Differentiable ML Pipelines
- Positional Bias in Long-Document Ranking: Impact, Assessment, and Mitigation
- CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution
- Multi-strip observation scheduling problem for ac-tive-imaging agile earth observation satellites
- The Present and Future of Bots in Software Engineering
- Asynchronous Curriculum Experience Replay: A Deep Reinforcement Learning Approach for UAV Autonomous Motion Control in Unknown Dynamic Environments
- Three multi-objective memtic algorithms for observation scheduling problem of active-imaging AEOS
- Learning Optimal Transport Between two Empirical Distributions with Normalizing Flows
- Parametric and Multivariate Uncertainty Calibration for Regression and Object Detection
- OS-MSL: One Stage Multimodal Sequential Link Framework for Scene Segmentation and Classification
- Satellite downlink scheduling under breakpoint resume mode
- Approximate Vanishing Ideal Computations at Scale
- Incorporating functional summary information in Bayesian neural networks using a Dirichlet process likelihood approach
- Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling
- Segmentation Guided Deep HDR Deghosting
- A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
- BusiNet -- a Light and Fast Text Detection Network for Business Documents
- Masked Self-Supervision for Remaining Useful Lifetime Prediction in Machine Tools
- CAM/CAD Point Cloud Part Segmentation via Few-Shot Learning
- Solutions for Fine-grained and Long-tailed Snake Species Recognition in SnakeCLEF 2022
- Analysis of Robocode Robot Adaptive Confrontation Based on Zero-Sum Game
- Sustainable AI Processing at the Edge
- Attributed Abnormality Graph Embedding for Clinically Accurate X-Ray Report Generation
- Adversarial Pairwise Reverse Attention for Camera Performance Imbalance in Person Re-identification: New Dataset and Metrics
- Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus
- S5Mars: Semi-Supervised Learning for Mars Semantic Segmentation
- Identifying Rhythmic Patterns for Face Forgery Detection and Categorization
- Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation
- A Customized Text Sanitization Mechanism with Differential Privacy
- Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios
- Learning node embeddings via summary graphs: a brief theoretical analysis
- Learning to Rank with Small Set of Ground Truth Data
- ETF Portfolio Construction via Neural Network trained on Financial Statement Data
- Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures
- Fast Vehicle Detection and Tracking on Fisheye Traffic Monitoring Video using CNN and Bounding Box Propagation
- Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution
- An Improved Probability Propagation Algorithm for Density Peak Clustering Based on Natural Nearest Neighborhood
- Enhancing Local Feature Learning Using Diffusion for 3D Point Cloud Understanding
- TANet: Transformer-based Asymmetric Network for RGB-D Salient Object Detection
- Portuguese Man-of-War Image Classification with Convolutional Neural Networks
- How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts
- Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations
- Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
- VIP-SLAM: An Efficient Tightly-Coupled RGB-D Visual Inertial Planar SLAM
- Removing Batch Normalization Boosts Adversarial Training
- Modeling Randomly Walking Volatility with Chained Gamma Distributions
- RAF: Recursive Adversarial Attacks on Face Recognition Using Extremely Limited Queries
- ViRel: Unsupervised Visual Relations Discovery with Graph-level Analogy