Papers
Wed 18 Jan 2023
120 papers
- NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View SynthesisOffline RL and imitation learning from data → Robot manipulation imitation learning
- Joint Representation Learning for Text and 3D Point CloudMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Targeted Image Reconstruction by Sampling Pre-trained Diffusion ModelDiffusion models → Robustness, privacy and adversarial aspects
- CLIPTER: Looking at the Bigger Picture in Scene Text RecognitionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Semi-Supervised Semantic Segmentation via Gentle Teaching AssistantKnowledge distillation → Detection and dense prediction distillation
- Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual LearningKnowledge distillation → Distillation for continual learning
- Effective End-to-End Vision Language Pretraining with Semantic Visual LossMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Rapid-Motion-Track: Markerless Tracking of Fast Human Motion with Deeper Learning
- Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling
- Graph Encoder Ensemble for Simultaneous Vertex Embedding and Community Detection
- On solving decision and risk management problems subject to uncertainty
- Augmenting a Physics-Informed Neural Network for the 2D Burgers Equation by Addition of Solution Data Points
- On the limits of neural network explainability via descrambling
- Measuring uncertainty in human visual segmentation
- Federated Automatic Differentiation
- Multi-target multi-camera vehicle tracking using transformer-based camera link model and spatial-temporal information
- A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
- HCE: Improving Performance and Efficiency with Heterogeneously Compressed Neural Network Ensemble
- Temporal Motifs for Financial Networks: A Study on Mercari, JPMC, and Venmo Platforms
- Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization
- Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection
- Reconstructing Rayleigh-Benard flows out of temperature-only measurements using Physics-Informed Neural Networks
- Automated deep reinforcement learning for real-time scheduling strategy of multi-energy system integrated with post-carbon and direct-air carbon captured system
- Sequential Processing of Observations in Human Decision-Making Systems
- Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images
- Catapult Dynamics and Phase Transitions in Quadratic Nets
- Learning-Rate-Free Learning by D-Adaptation
- Learning 3D-aware Image Synthesis with Unknown Pose Distribution
- Attention2Minority: A salient instance inference-based multiple instance learning for classifying small lesions in whole slide images
- CaRE: Finding Root Causes of Configuration Issues in Highly-Configurable Robots
- Reduced-Reference Quality Assessment of Point Clouds via Content-Oriented Saliency Projection
- OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models
- Active learning for medical image segmentation with stochastic batches
- Behind the Scenes: Density Fields for Single View Reconstruction
- DDS: Decoupled Dynamic Scene-Graph Generation Network
- An investigation of the reconstruction capacity of stacked convolutional autoencoders for log-mel-spectrograms
- Non-parametric identifiability and sensitivity analysis of synthetic control models
- HMDO: Markerless Multi-view Hand Manipulation Capture with Deformable Objects
- Facial Thermal and Blood Perfusion Patterns of Human Emotions: Proof-of-Concept
- A Comparative Analysis of Bias Amplification in Graph Neural Network Approaches for Recommender Systems
- An Analysis of Loss Functions for Binary Classification and Regression
- Generative AI-empowered Effective Physical-Virtual Synchronization in the Vehicular Metaverse
- Local Learning with Neuron Groups
- Training Semantic Segmentation on Heterogeneous Datasets
- Generalisation Through Negation and Predicate Invention
- Universal Neural-Cracking-Machines: Self-Configurable Password Models from Auxiliary Data
- A novel dataset and a two-stage mitosis nuclei detection method based on hybrid anchor branch
- Performance-Preserving Event Log Sampling for Predictive Monitoring
- Development, Optimization, and Deployment of Thermal Forward Vision Systems for Advance Vehicular Applications on Edge Devices
- Physics-informed Information Field Theory for Modeling Physical Systems with Uncertainty Quantification
- Human-Timescale Adaptation in an Open-Ended Task Space
- Strong inductive biases provably prevent harmless interpolation
- How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection
- A Survey of Advanced Computer Vision Techniques for Sports
- Blur Invariants for Image Recognition
- Synthcity: facilitating innovative use cases of synthetic data in different data modalities
- Beating the Best: Improving on AlphaFold2 at Protein Structure Prediction
- Gated-ViGAT: Efficient Bottom-Up Event Recognition and Explanation Using a New Frame Selection Policy and Gating Mechanism
- Towards a Holistic Understanding of Mathematical Questions with Contrastive Pre-training
- Logic programming for deliberative robotic task planning
- Generative Adversarial Networks to infer velocity components in rotating turbulent flows
- News and Load: A Quantitative Exploration of Natural Language Processing Applications for Forecasting Day-ahead Electricity System Demand
- A Multi-Scale Framework for Out-of-Distribution Detection in Dermoscopic Images
- Online (Non-)Convex Learning via Tempered Optimism
- OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
- Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing
- Biases in Scholarly Recommender Systems: Impact, Prevalence, and Mitigation
- FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
- Curvilinear object segmentation in medical images based on ODoS filter and deep learning network
- Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy
- Discrete Latent Structure in Neural Networks
- Characterizing Structural Hardness of Logic Programs: What makes Cycles and Reachability Hard for Treewidth?
- Model-based inexact graph matching on top of CNNs for semantic scene understanding
- Temporal Perceiving Video-Language Pre-training
- DDPEN: Trajectory Optimisation With Sub Goal Generation Model
- Sharp Eyes: A Salient Object Detector Working The Same Way as Human Visual Characteristics
- Boosting Synthetic Data Generation with Effective Nonlinear Causal Discovery
- Autonomous Slalom Maneuver Based on Expert Drivers' Behavior Using Convolutional Neural Network
- DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training
- Compression of GPS Trajectories using Autoencoders
- Learning to Participate through Trading of Reward Shares
- Representing Noisy Image Without Denoising
- TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks
- HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness
- Using Topological Data Analysis to classify Encrypted Bits
- Relativistic Digital Twin: Bringing the IoT to the Future
- Towards Models that Can See and Read
- Learning Interpolations between Boltzmann Densities
- Three-dimensional reconstruction and characterization of bladder deformations
- ViT-AE++: Improving Vision Transformer Autoencoder for Self-supervised Medical Image Representations
- Dirichlet-Neumann learning algorithm for solving elliptic interface problems
- MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation
- Implicit State and Goals in QBF Encodings for Positional Games (extended version)
- KILDST: Effective Knowledge-Integrated Learning for Dialogue State Tracking using Gazetteer and Speaker Information
- Class Enhancement Losses with Pseudo Labels for Zero-shot Semantic Segmentation
- FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment
- Deep Dynamic Scene Deblurring from Optical Flow
- HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation
- Robust Knowledge Adaptation for Federated Unsupervised Person ReID
- Face Recognition in the age of CLIP & Billion image datasets
All 120
- Improve Noise Tolerance of Robust Loss via Noise-Awareness
- PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav
- PTA-Det: Point Transformer Associating Point cloud and Image for 3D Object Detection
- Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining
- Enhancing Self-Training Methods
- Reslicing Ultrasound Images for Data Augmentation and Vessel Reconstruction
- A Novel Sparse Regularizer
- Label Inference Attack against Split Learning under Regression Setting
- Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data
- Detecting and Ranking Causal Anomalies in End-to-End Complex System
- SensorX2car: Sensors-to-car calibration for autonomous driving in road scenarios
- Data thinning for convolution-closed distributions
- Multi-compartment Neuron and Population Encoding Powered Spiking Neural Network for Deep Distributional Reinforcement Learning
- A variational autoencoder-based nonnegative matrix factorisation model for deep dictionary learning
- ACQ: Improving Generative Data-free Quantization Via Attention Correction
- Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
- Tailor: Altering Skip Connections for Resource-Efficient Inference
- Efficient correlation-based discretization of continuous variables for annealing machines
- Complexity Analysis of a Countable-armed Bandit Problem
- DRIMET: Deep Registration for 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue