Papers
Thu 24 Mar 2022
200 papers
- Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
- Token Dropping for Efficient BERT PretrainingEfficient LLM inference and serving → Early exit and edge inference
- Multitask Emotion Recognition Model with Knowledge Distillation and Task DiscriminatorKnowledge distillation → Multimodal distillation
- Probing for Labeled Dependency TreesMechanistic interpretability → Knowledge and representations inside LLMs
- Knowledge Removal in Sampling-based Bayesian InferenceLLM safety and security → Machine unlearning
- Complex Scene Image Editing by Scene Graph ComprehensionDiffusion models → Image generation, text-to-image and editing
- Continual Learning and Private UnlearningLLM safety and security → Machine unlearning
- Bellman Residual Orthogonalization for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- On the link between conscious function and general intelligence in humans and machines
- Estimating Social Influence from Observational Data
- Satellite Monitoring of Terrestrial Plastic Waste
- BASiNETEntropy: an alignment-free method for classification of biological sequences through complex networks and entropy maximization
- Rich Feature Construction for the Optimization-Generalization Dilemma
- Human Response to an AI-Based Decision Support System: A User Study on the Effects of Accuracy and Bias
- Domino: Discovering Systematic Errors with Cross-Modal Embeddings
- Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices
- Non-Parametric Stochastic Policy Gradient with Strategic Retreat for Non-Stationary Environment
- Object Memory Transformer for Object Goal Navigation
- Bi-level Doubly Variational Learning for Energy-based Latent Variable Models
- SERA: Safe and Efficient Reactive Obstacle Avoidance for Collaborative Robotic Planning in Unstructured Environments
- FedGradNorm: Personalized Federated Gradient-Normalized Multi-Task Learning
- Repairing Group-Level Errors for DNNs Using Weighted Regularization
- Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches
- CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation
- Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
- Email Summarization to Assist Users in Phishing Identification
- Statistic Selection and MCMC for Differentially Private Bayesian Estimation
- Deep reinforcement learning for optimal well control in subsurface systems with uncertain geology
- FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
- Gender and Racial Stereotype Detection in Legal Opinion Word Embeddings
- Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)
- Calibration Error for Heterogeneous Treatment Effects
- One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia
- Does human speech follow Benford's Law?
- Predicting Personas Using Mechanic Frequencies and Game State Traces
- Occluded Human Mesh Recovery
- Linking Emergent and Natural Languages via Corpus Transfer
- Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation
- CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
- Addressing Client Drift in Federated Continual Learning with Adaptive Optimization
- Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning
- NPBG++: Accelerating Neural Point-Based Graphics
- Human Gait Recognition Using Bag of Words Feature Representation Method
- Deep learning for laboratory earthquake prediction and autoregressive forecasting of fault zone stress
- SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation
- MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection
- Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos
- Tackling Online One-Class Incremental Learning by Removing Negative Contrasts
- Multi-modal Multi-label Facial Action Unit Detection with Transformer
- Mix and Match: Learning-free Controllable Text Generation using Energy Language Models
- RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers
- Learning Spatiotemporal Chaos Using Next-Generation Reservoir Computing
- Searching for fingerspelled content in American Sign Language
- Continuous-Time Audiovisual Fusion with Recurrence vs. Attention for In-The-Wild Affect Recognition
- Local optimisation of Nystr"om samples through stochastic gradient descent
- Movie Genre Classification by Language Augmentation and Shot Sampling
- Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
- A Manifold View of Adversarial Risk
- A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range
- Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
- Precipitaion Nowcasting using Deep Neural Network
- Interpretability of Neural Network With Physiological Mechanisms
- Feature Selection on Quantum Computers
- Computing Optimal Location of Microphone for Improved Speech Recognition
- EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
- Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention Transformer
- Global Tracking Transformers
- BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
- Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer
- VRNet: Learning the Rectified Virtual Corresponding Points for 3D Point Cloud Registration
- A Representation Separation Perspective to Correspondences-free Unsupervised 3D Point Cloud Registration
- Open-set Recognition via Augmentation-based Similarity Learning
- Differential Assessment of Black-Box AI Agents
- Facial Expression Recognition based on Multi-head Cross Attention Network
- SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance
- Distributionally Robust Optimization via Ball Oracle Acceleration
- Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion
- Neural Neighbor Style Transfer
- A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow
- Direct parsing to sentiment graphs
- Quantum Motion Segmentation
- Emergence of hierarchical reference systems in multi-agent communication
- Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization
- Self-supervised Video-centralised Transformer for Video Face Clustering
- On the Kullback-Leibler divergence between pairwise isotropic Gaussian-Markov random fields
- Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation
- Addressing Missing Sources with Adversarial Support-Matching
- Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking
- Physics-based Learning of Parameterized Thermodynamics from Real-time Thermography
- Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors
- Intelligent Systematic Investment Agent: an ensemble of deep learning and evolutionary strategies
- Moving Window Regression: A Novel Approach to Ordinal Regression
- Feature visualization for convolutional neural network models trained on neuroimaging data
- X-ray Dissectography Improves Lung Nodule Detection
- Egocentric Prediction of Action Target in 3D
- minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models
- Position Tracking using Likelihood Modeling of Channel Features with Gaussian Processes
- Explainable Artificial Intelligence for Exhaust Gas Temperature of Turbofan Engines
- R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning
- IA-FaceS: A Bidirectional Method for Semantic Face Editing
All 200
- A Preliminary Research on Space Situational Awareness Based on Event Cameras
- AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception
- Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction
- HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement
- Locally Asynchronous Stochastic Gradient Descent for Decentralised Deep Learning
- The Dutch Draw: Constructing a Universal Baseline for Binary Prediction Models
- Behavior Trees in Robot Control Systems
- SIFT and SURF based feature extraction for the anomaly detection
- Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction
- ACE: Towards Application-Centric Edge-Cloud Collaborative Intelligence
- SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning
- Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory
- Coarse-to-Fine Cascaded Networks with Smooth Predicting for Video Facial Expression Recognition
- Evolved Open-Endedness in Cultural Evolution: A New Dimension in Open-Ended Evolution Research
- Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning
- Benchmarking Visual Localization for Autonomous Navigation
- Facial Action Unit Recognition With Multi-models Ensembling
- Interpretable Prediction of Pulmonary Hypertension in Newborns using Echocardiograms
- Multi-modal Emotion Estimation for in-the-wild Videos
- Continuous Emotion Recognition using Visual-audio-linguistic information: A Technical Report for ABAW3
- Brain inspired neuronal silencing mechanism to enable reliable sequence identification
- CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Image
- Compound Domain Generalization via Meta-Knowledge Encoding
- Using Orientation to Distinguish Overlapping Chromosomes
- A Deep-Discrete Learning Framework for Spherical Surface Registration
- Kratt: Developing an Automatic Subject Indexing Tool for The National Library of Estonia
- Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction
- Generating Scientific Claims for Zero-Shot Scientific Fact Checking
- Learning Disentangled Representation for One-shot Progressive Face Swapping
- MERLIN -- Malware Evasion with Reinforcement LearnINg
- Is Geometry Enough for Matching in Visual Localization?
- Effective Explanations for Entity Resolution Models
- Focus-and-Detect: A Small Object Detection Framework for Aerial Images
- Analyzing Process-Aware Information System Updates Using Digital Twins of Organizations
- Extended critical regimes of deep neural networks
- Bayesian Deep Learning with Multilevel Trace-class Neural Networks
- Onto4MAT: A Swarm Shepherding Ontology for Generalised Multi-Agent Teaming
- Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings
- Personalized incentives as feedback design in generalized Nash equilibrium problems
- Transformers Meet Visual Learning Understanding: A Comprehensive Review
- Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets
- mcBERT: Momentum Contrastive Learning with BERT for Zero-Shot Slot Filling
- Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition
- Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering
- The Fixed Sub-Center: A Better Way to Capture Data Complexity
- Multitasking Framework for Unsupervised Simple Definition Generation
- TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference
- Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies
- Rubik's Cube Operator: A Plug And Play Permutation Module for Better Arranging High Dimensional Industrial Data in Deep Convolutional Processes
- Learning Dense Correspondence from Synthetic Environments
- A Rationale-Centric Framework for Human-in-the-loop Machine Learning
- WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation
- NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks
- k-Rater Reliability: The Correct Unit of Reliability for Aggregated Human Annotations
- Neural Reflectance for Shape Recovery with Shadow Handling
- Mono vs Multilingual BERT: A Case Study in Hindi and Marathi Named Entity Recognition
- Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks
- Privileged Attribution Constrained Deep Networks for Facial Expression Recognition
- Facial Expression Classification using Fusion of Deep Neural Network in Video for the 3rd ABAW3 Competition
- FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization
- Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals
- An Ensemble Approach for Facial Expression Analysis in Video
- Automatic Speech Recognition for Speech Assessment of Persian Preschool Children
- Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?
- Weakly-Supervised End-to-End CAD Retrieval to Scan Objects
- Intrinsic Bias Identification on Medical Image Datasets
- RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization
- DyRep: Bootstrapping Training with Dynamic Re-parameterization
- Multilingual CheckList: Generation and Evaluation
- Kullback-Leibler control for discrete-time nonlinear systems on continuous spaces
- Transformer Compressed Sensing via Global Image Tokens
- Beyond Fixation: Dynamic Window Visual Transformer
- Direct evaluation of progression or regression of disease burden in brain metastatic disease with Deep Neuroevolution
- Keypoints Tracking via Transformer Networks
- Multiple Emotion Descriptors Estimation at the ABAW3 Challenge
- Steganalysis of Image with Adaptively Parametric Activation
- Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection
- Learning from Label Proportions with Instance-wise Consistency
- Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation
- LHNN: Lattice Hypergraph Neural Network for VLSI Congestion Prediction
- AIMusicGuru: Music Assisted Human Pose Correction
- Sparse Instance Activation for Real-Time Instance Segmentation
- HM: Hybrid Masking for Few-Shot Segmentation
- Subjective and Objective Analysis of Streamed Gaming Videos
- On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach
- Random Forest Regression for continuous affect using Facial Action Units
- ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator
- Revisiting the Effects of Leakage on Dependency Parsing
- Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering
- Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion
- Robustness Against Weak or Invalid Instruments: Exploring Nonlinear Treatment Models with Machine Learning
- Unsupervised Simultaneous Learning for Camera Re-Localization and Depth Estimation from Video
- A Two-Stage Federated Transfer Learning Framework in Medical Images Classification on Limited Data: A COVID-19 Case Study
- A platform for causal knowledge representation and inference in industrial fault diagnosis based on cubic DUCG
- DPar2: Fast and Scalable PARAFAC2 Decomposition for Irregular Dense Tensors
- Learning the Dynamics of Autonomous Linear Systems From Multiple Trajectories
- Evaluating Distributional Distortion in Neural Language Modeling
- Classifying Cyber-Risky Clinical Notes by Employing Natural Language Processing
- Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Camera
- Are Evolutionary Algorithms Safe Optimizers?