Papers
Sat 12 Mar 2022
75 papers
- Enabling Multimodal Generation on CLIP via Vision-Language Knowledge DistillationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
- Wavelet Knowledge Distillation: Towards Efficient Image-to-Image TranslationKnowledge distillation → General knowledge distillation methods
- Recent Advances and New Frontiers in Spiking Neural Networks
- An Introduction to Matrix factorization and Factorization Machines in Recommendation System, and Beyond
- Generic Lithography Modeling with Dual-band Optics-Inspired Neural Networks
- Development of Decision Support System for Effective COVID-19 Management
- Enhancing crowd flow prediction in various spatial and temporal granularities
- Learning Hidden Markov Models When the Locations of Missing Observations are Unknown
- Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations
- On Information Hiding in Natural Language Systems
- A Mixed Quantization Network for Computationally Efficient Mobile Inverse Tone Mapping
- Wasserstein Adversarial Transformer for Cloud Workload Prediction
- The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning
- Adaptive Information Bottleneck Guided Joint Source and Channel Coding for Image Transmission
- TEN: Twin Embedding Networks for the Jigsaw Puzzle Problem with Eroded Boundaries
- Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?
- Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
- FiNER: Financial Numeric Entity Recognition for XBRL Tagging
- GATSBI: Generative Adversarial Training for Simulation-Based Inference
- Optimizer Amalgamation
- Unsupervised Lifelong Person Re-identification via Contrastive Rehearsal
- G3SR: Global Graph Guided Session-based Recommendation
- Towards On-Device AI and Blockchain for 6G enabled Agricultural Supply-chain Management
- A Systematic Review on Computer Vision-Based Parking Lot Management Applied on Public Datasets
- Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice
- Factored Attention and Embedding for Unstructured-view Topic-related Ultrasound Report Generation
- 3D-GIF: 3D-Controllable Object Generation via Implicit Factorized Representations
- Energy networks for state estimation with random sensors using sparse labels
- Bringing Rolling Shutter Images Alive with Dual Reversed Distortion
- Equivariant Graph Mechanics Networks with Constraints
- DATR: Domain-adaptive transformer for multi-domain landmark detection
- Deep learning-based conditional inpainting for restoration of artifact-affected 4D CT images
- Categories of Differentiable Polynomial Circuits for Machine Learning
- DFTR: Depth-supervised Fusion Transformer for Salient Object Detection
- VAFO-Loss: VAscular Feature Optimised Loss Function for Retinal Artery/Vein Segmentation
- VariabilityTrack:Multi-Object Tracking with Variable Speed Object Movement
- One-stage Video Instance Segmentation: From Frame-in Frame-out to Clip-in Clip-out
- When did you become so smart, oh wise one?! Sarcasm Explanation in Multi-modal Multi-party Dialogues
- Recurrence-in-Recurrence Networks for Video Deblurring
- Concentration Network for Reinforcement Learning of Large-Scale Multi-Agent Systems
- A Survey of Adversarial Defences and Robustness in NLP
- Kernel Proposal Network for Arbitrary Shape Text Detection
- Information retrieval for label noise document ranking by bag sampling and group-wise loss
- Transition Relation Aware Self-Attention for Session-based Recommendation
- A Proposal to Study "Is High Quality Data All We Need?"
- SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection
- A combined approach to the analysis of speech conversations in a contact center domain
- BiBERT: Accurate Fully Binarized BERT
- GRAND+: Scalable Graph Random Neural Networks
- Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting
- Differentiated Relevances Embedding for Group-based Referring Expression Comprehension
- MarkBERT: Marking Word Boundaries Improves Chinese BERT
- Varying Coefficient Linear Discriminant Analysis for Dynamic Data
- The Health Gym: Synthetic Health-Related Datasets for the Development of Reinforcement Learning Algorithms
- MDT-Net: Multi-domain Transfer by Perceptual Supervision for Unpaired Images in OCT Scan
- Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning
- Taking an Emotional Look at Video Paragraph Captioning
- EventFormer: AU Event Transformer for Facial Action Unit Event Detection
- LesionPaste: One-Shot Anomaly Detection for Medical Images
- Combining Deep Learning with Physics Based Features in Explosion-Earthquake Discrimination
- The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy
- What Makes Reading Comprehension Questions Difficult?
- Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation
- Image Style Transfer: from Artistic to Photorealistic
- PillarGrid: Deep Learning-based Cooperative Perception for 3D Object Detection from Onboard-Roadside LiDAR
- Deformable VisTR: Spatio temporal deformable attention for video instance segmentation
- Towards Equal Opportunity Fairness through Adversarial Learning
- Tensor Radiomics: Paradigm for Systematic Incorporation of Multi-Flavoured Radiomics Features
- ELLE: Efficient Lifelong Pre-training for Emerging Data
- Ensemble Semi-supervised Entity Alignment via Cycle-teaching
- MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
- Neural Topic Modeling with Deep Mutual Information Estimation
- Instance-Dependent Regret Analysis of Kernelized Bandits
- SOCKS: A Stochastic Optimal Control and Reachability Toolbox Using Kernel Methods
- Tactile-ViewGCN: Learning Shape Descriptor from Tactile Data using Graph Convolutional Network