Papers
Tue 21 Mar 2023
244 papers
- Affordance Diffusion: Synthesizing Hand-Object InteractionsDiffusion models → Diffusion and flow policies for robotics
- Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language UnderstandingLLM reasoning → Multimodal reasoning
- SALAD: Part-Level Latent Diffusion for 3D Shape Generation and ManipulationDiffusion models → 3D, point cloud and scene generation
- Text2Motion: From Natural Language Instructions to Feasible PlansWorld models → Embodied and robot world models
- VAD: Vectorized Scene Representation for Efficient Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
- Vox-E: Text-guided Voxel Editing of 3D ObjectsDiffusion models → 3D, point cloud and scene generation
- Logical Reasoning over Natural Language as Knowledge Representation: A SurveyLLM reasoning → Reasoning benchmarks and evaluation
- 3D-CLFusion: Fast Text-to-3D Rendering with Contrastive Latent DiffusionDiffusion models → 3D, point cloud and scene generation
- CompoDiff: Versatile Composed Image Retrieval With Latent DiffusionDiffusion models → Image generation, text-to-image and editing
- Penalty-Based Imitation Learning With Cross Semantics Generation Sensor Fusion for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Improving Deep Dynamics Models for Autonomous Vehicles with Multimodal Latent Mapping of SurfacesEnd-to-end autonomous driving → Generative simulation for driving
- Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive MatricesLLM reasoning → Mathematical reasoning
- DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Deep Q-Network Based Decision Making for Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
- LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic ModelsDiffusion models → Image generation, text-to-image and editing
- Boundary UnlearningLLM safety and security → Machine unlearning
- The African Stopwords project: curating stopwords for African languages
- "Uberpr"ufung von Integrit"atsbedingungen in Deduktiven Datenbanken
- Rough Randomness and its Application
- Disentangling Domain Ontologies
- Research on Efficiency Analysis of Microservices
- Building artificial neural circuits for domain-general cognition: a primer on brain-inspired systems-level architecture
- In-depth analysis of music structure as a text network
- Optical Character Recognition and Transcription of Berber Signs from Images in a Low-Resource Language Amazigh
- Hey Dona! Can you help me with student course registration?
- Labeled Subgraph Entropy Kernel
- Fine-tuning ClimateBert transformer with ClimaText for the disclosure analysis of climate-related financial risks
- ChatGPT and a New Academic Reality: Artificial Intelligence-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing
- SignCRF: Scalable Channel-agnostic Data-driven Radio Authentication System
- Inverting the Fundamental Diagram and Forecasting Boundary Conditions: How Machine Learning Can Improve Macroscopic Models for Traffic Flow
- An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds
- DG-Trans: Dual-level Graph Transformer for Spatiotemporal Incident Impact Prediction on Traffic Networks
- Automated deep learning segmentation of high-resolution 7 T postmortem MRI for quantitative analysis of structure-pathology correlations in neurodegenerative diseases
- Pre-NeRF 360: Enriching Unbounded Appearances for Neural Radiance Fields
- LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulation
- Infrastructure-based End-to-End Learning and Prevention of Driver Failure
- A Unified Taxonomy of Deep Syntactic Relations
- Compositional 3D Scene Generation using Locally Conditioned Diffusion
- Image Reconstruction without Explicit Priors
- Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning
- Community detection in complex networks via node similarity, graph representation learning, and hierarchical clustering
- A Random Projection k Nearest Neighbours Ensemble for Classification via Extended Neighbourhood Rule
- MAGVLT: Masked Generative Vision-and-Language Transformer
- Policy Optimization for Personalized Interventions in Behavioral Health
- Analytical Conjugate Priors for Subclasses of Generalized Pareto Distributions
- Autofluorescence Bronchoscopy Video Analysis for Lesion Frame Detection
- LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception
- Black-box Backdoor Defense via Zero-shot Image Purification
- Viscoelastic Constitutive Artificial Neural Networks (vCANNs) - a framework for data-driven anisotropic nonlinear finite viscoelasticity
- Learning a Depth Covariance Function
- Neural Pre-Processing: A Learning Framework for End-to-end Brain MRI Pre-processing
- Universal Approximation Property of Hamiltonian Deep Neural Networks
- Efficient Feature Distillation for Zero-shot Annotation Object Detection
- Improving Fabrication Fidelity of Integrated Nanophotonic Devices Using Deep Learning
- Understand Legal Documents with Contextualized Large Language Models
- Monocular Visual-Inertial Depth Estimation
- Fundamentals of Generative Large Language Models and Perspectives in Cyber-Defense
- MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
- Oral-3Dv2: 3D Oral Reconstruction from Panoramic X-Ray Imaging with Implicit Neural Representation
- Physics Informed Neural Networks for Phase Locked Loop Transient Stability Assessment
- Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation
- CLSA: Contrastive Learning-based Survival Analysis for Popularity Prediction in MEC Networks
- ChatGPT for Programming Numerical Methods
- Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning
- Natural Language-Assisted Sign Language Recognition
- OmniTracker: Unifying Object Tracking by Tracking-with-Detection
- Two-shot Video Object Segmentation
- Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Play
- CC3D: Layout-Conditioned Generation of Compositional 3D Scenes
- 3D Mitochondria Instance Segmentation with Spatio-Temporal Transformers
- ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals
- Machine Learning for Brain Disorders: Transformers and Visual Transformers
- VideoXum: Cross-modal Visual and Textural Summarization of Videos
- Motion Matters: Neural Motion Transfer for Better Camera Physiological Measurement
- Large Language Models Can Be Used to Estimate the Latent Positions of Politicians
- Influencer Backdoor Attack on Semantic Segmentation
- A Novel and Optimal Spectral Method for Permutation Synchronization
- CurveCloudNet: Processing Point Clouds with 1D Structure
- Roots and Requirements for Collaborative AIs
- The Representational Status of Deep Learning Models
- Semantic Latent Space Regression of Diffusion Autoencoders for Vertebral Fracture Grading
- Wearing Masks Implies Refuting Trump?: Towards Target-specific User Stance Prediction across Events in COVID-19 and US Election 2020
- Joint Visual Grounding and Tracking with Natural Language Specification
- cTBLS: Augmenting Large Language Models with Conversational Tables
- Graph Kalman Filters
- Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
- Automatic evaluation of herding behavior in towed fishing gear using end-to-end training of CNN and attention-based networks
- NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Images
- Artificial muses: Generative Artificial Intelligence Chatbots Have Risen to Human-Level Creativity
- End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations
- ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders
- E-MLB: Multilevel Benchmark for Event-Based Camera Denoising
- Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
- Defect Detection Approaches Based on Simulated Reference Image
- Explain To Me: Salience-Based Explainability for Synthetic Face Detection Models
- NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects
- Bayesian Optimization for Function Compositions with Applications to Dynamic Pricing
- Learning A Sparse Transformer Network for Effective Image Deraining
- Studying How to Efficiently and Effectively Guide Models with Explanations
All 244
- Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
- Performance-aware Approximation of Global Channel Pruning for Multitask CNNs
- Context De-confounded Emotion Recognition
- Do intermediate feature coalitions aid explainability of black-box models?
- Efficient Decision-based Black-box Patch Attacks on Video Recognition
- Time Series Contrastive Learning with Information-Aware Augmentations
- 360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye View
- The Multiscale Surface Vision Transformer
- Non-Asymptotic Pointwise and Worst-Case Bounds for Classical Spectrum Estimators
- Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
- Large-Scale Traffic Signal Control Using Constrained Network Partition and Adaptive Deep Reinforcement Learning
- Real-time volumetric rendering of dynamic humans
- TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
- Better Understanding Differences in Attribution Methods via Systematic Evaluations
- Protective Self-Adaptive Pruning to Better Compress DNNs
- Focused and Collaborative Feedback Integration for Interactive Image Segmentation
- A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks
- Continual Learning in the Presence of Spurious Correlation
- Online Transformers with Spiking Neurons for Fast Prosthetic Hand Control
- LEAPS: End-to-End One-Step Person Search With Learnable Proposals
- Modeling Relational Patterns for Logical Query Answering over Knowledge Graphs
- CLIP-ReIdent: Contrastive Training for Player Re-Identification
- LoRCoN-LO: Long-term Recurrent Convolutional Network-based LiDAR Odometry
- Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation
- Dens-PU: PU Learning with Density-Based Positive Labeled Augmentation
- Doubly Regularized Entropic Wasserstein Barycenters
- Self-Paced Neutral Expression-Disentangled Learning for Facial Expression Recognition
- Self-supervised learning of a tailored Convolutional Auto Encoder for histopathological prostate grading
- Materials Discovery with Extreme Properties via Reinforcement Learning-Guided Combinatorial Chemistry
- CLADE: Cycle Loss Augmented Degradation Enhancement for Unpaired Super-Resolution of Anisotropic Medical Images
- The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector
- Chinese Intermediate English Learners outdid ChatGPT in deep cohesion: Evidence from English narrative writing
- Addressing Class Variable Imbalance in Federated Semi-supervised Learning
- Fighting over-fitting with quantization for learning deep neural networks on noisy labels
- CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
- Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense
- Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking
- Probabilistic Domain Adaptation for Biomedical Image Segmentation
- Exact Non-Oblivious Performance of Rademacher Random Embeddings
- Self-Sufficient Framework for Continuous Sign Language Recognition
- Reasonable Scale Machine Learning with Open-Source Metaflow
- Simulating Malaria Detection in Laboratories using Deep Learning
- LIMITR: Leveraging Local Information for Medical Image-Text Representation
- Projections of Model Spaces for Latent Graph Inference
- LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation
- Detecting Everything in the Open World: Towards Universal Object Detection
- Recommendation Systems in Libraries: an Application with Heterogeneous Data Sources
- Poisoning Attacks in Federated Edge Learning for Digital Twin 6G-enabled IoTs: An Anticipatory Study
- Beam Management Driven by Radio Environment Maps in O-RAN Architecture
- Data-efficient Large Scale Place Recognition with Graded Similarity Supervision
- Tensor networks for quantum machine learning
- Unlocking Layer-wise Relevance Propagation for Autoencoders
- DIPPM: a Deep Learning Inference Performance Predictive Model using Graph Neural Networks
- Multi-modal Prompting for Low-Shot Temporal Action Localization
- Few-shot Neural Radiance Fields Under Unconstrained Illumination
- 3D Human Mesh Estimation from Virtual Markers
- Online Learning of Wheel Odometry Correction for Mobile Robots with Attention-based Neural Network
- Task-based Generation of Optimized Projection Sets using Differentiable Ranking
- Implicit Neural Representation for Cooperative Low-light Image Enhancement
- Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion
- A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?
- Style Miner: Find Significant and Stable Explanatory Factors in Time Series with Constrained Reinforcement Learning
- Efficiently Explaining CSPs with Unsatisfiable Subset Optimization (extended algorithms and examples)
- The Open-domain Paradox for Chatbots: Common Ground as the Basis for Human-like Dialogue
- A Single-Step Multiclass SVM based on Quantum Annealing for Remote Sensing Data Classification
- On the link between generative semi-supervised learning and generative open-set recognition
- A High-Frequency Focused Network for Lightweight Single Image Super-Resolution
- Neural networks trained on synthetically generated crystals can extract structural information from ICSD powder X-ray diffractograms
- Data Augmentation For Label Enhancement
- Transcriptomics-based matching of drugs to diseases with deep learning
- Anchor Free remote sensing detector based on solving discrete polar coordinate equation
- Learning a 3D Morphable Face Reflectance Model from Low-cost Data
- SpikeCV: Open a Continuous Computer Vision Era
- Full or Weak annotations? An adaptive strategy for budget-constrained annotation campaigns
- Deep Learning Pipeline for Preprocessing and Segmenting Cardiac Magnetic Resonance of Single Ventricle Patients from an Image Registry
- ReBaR: Reference-Based Reasoning for Robust Pose Estimation from Monocular Images
- ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization
- A Survey on Class Imbalance in Federated Learning
- Universal Smoothed Score Functions for Generative Modeling
- Focus or Not: A Baseline for Anomaly Event Detection On the Open Public Places with Satellite Images
- Advanced Multi-Microscopic Views Cell Semi-supervised Segmentation
- Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization
- Mitigating climate and health impact of small-scale kiln industry using multi-spectral classifier and deep learning
- Uniform Risk Bounds for Learning with Dependent Data Sequences
- CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning
- Improving Content Retrievability in Search with Controllable Query Generation
- Are uGLAD? Time will tell!
- Manipulating Transfer Learning for Property Inference
- Visibility Constrained Wide-band Illumination Spectrum Design for Seeing-in-the-Dark
- Human Pose as Compositional Tokens
- Equiangular Basis Vectors
- Learning Context-aware Classifier for Semantic Segmentation
- An Embarrassingly Simple Approach for Wafer Feature Extraction and Defect Pattern Recognition
- BoxSnake: Polygonal Instance Segmentation with Box Supervision
- TMA: Temporal Motion Aggregation for Event-based Optical Flow
- Information-containing Adversarial Perturbation for Combating Facial Manipulation Systems
- Assessor-Guided Learning for Continual Environments
- Detecting the open-world objects with the help of the Brain
- Heterogeneous-Branch Collaborative Learning for Dialogue Generation
- Blow-up Algorithm for Sum-of-Products Polynomials and Real Log Canonical Thresholds
- HRDFuse: Monocular 360degDepth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributions
- Robust Table Structure Recognition with Dynamic Queries Enhanced Detection Transformer
- Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation
- Novel Class Discovery for 3D Point Cloud Semantic Segmentation
- Transformers in Speech Processing: A Survey
- CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation
- Convergence of variational Monte Carlo simulation and scale-invariant pre-training
- Low-complexity Deep Video Compression with A Distributed Coding Architecture
- A Review on Machine Theory of Mind
- Difficulty in chirality recognition for Transformer architectures learning chemical structures from string
- Lightweight Hybrid Video Compression Framework Using Reference-Guided Restoration Network
- SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation
- Adaptive Experimentation at Scale: A Computational Framework for Flexible Batches
- Efficient Multi-stage Inference on Tabular Data
- Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
- Feature-adjacent multi-fidelity physics-informed machine learning for partial differential equations
- BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological Measurements
- Large AI Models in Health Informatics: Applications, Challenges, and the Future
- One-to-Few Label Assignment for End-to-End Dense Detection
- Agave crop segmentation and maturity classification with deep learning data-centric strategies using very high-resolution satellite imagery
- Dynamic Healthcare Embeddings for Improving Patient Care
- Dynamics-Aware Loss for Learning with Label Noise
- Smart-Tree: Neural Medial Axis Approximation of Point Clouds for 3D Tree Skeletonization
- Dynamic Vertex Replacement Grammars
- Boosting Verified Training for Robust Image Classifications via Abstraction
- ModEFormer: Modality-Preserving Embedding for Audio-Video Synchronization using Transformers
- Emotionally Enhanced Talking Face Generation
- Texture Learning Domain Randomization for Domain Generalized Segmentation
- Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
- MSTFormer: Motion Inspired Spatial-temporal Transformer with Dynamic-aware Attention for long-term Vessel Trajectory Prediction
- Interactive Geometry Editing of Neural Radiance Fields
- Indeterminate Probability Theory
- Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images
- Counterfactually Fair Regression with Double Machine Learning
- Machine Learning Techniques for Estimating Soil Moisture from Mobile Captured Images
- PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignment
- Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
- Online Learning for Equilibrium Pricing in Markets under Incomplete Information
- Estimating Distances Between People using a Single Overhead Fisheye Camera with Application to Social-Distancing Oversight
- Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation
- STDLens: Model Hijacking-Resilient Federated Learning for Object Detection
- AI-in-the-Loop -- The impact of HMI in AI-based Application
- ADCNet: Learning from Raw Radar Data via Distillation
- Deep Learning for Video-based Person Re-Identification: A Survey