Papers
Sat 2 Jan 2021
66 papers
- VinVL: Revisiting Visual Representations in Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
- Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channels
- Learning to Emphasize: Dataset and Shared Task Models for Selecting Emphasis in Presentation Slides
- SDA: Improving Text Generation with Self Data Augmentation
- COVID19-HPSMP: COVID-19 Adopted Hybrid and Parallel Deep Information Fusion Framework for Stock Price Movement Prediction
- Internet of Everything enabled solution for COVID-19, its new variants and future pandemics: Framework, Challenges, and Research Directions
- A Multilayer Correlated Topic Model
- Context-Aware Safe Reinforcement Learning for Non-Stationary Environments
- One-shot Representational Learning for Joint Biometric and Device Authentication
- Domain Adaptation for the Segmentation of Confidential Medical Images
- Improving DGA-Based Malicious Domain Classifiers for Malware Defense with Adversarial Machine Learning
- Regularization-based Continual Learning for Anomaly Detection in Discrete Manufacturing
- Modularity maximisation for graphons
- A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost
- Multi-stage Deep Layer Aggregation for Brain Tumor Segmentation
- Combining unsupervised and supervised learning for predicting the final stroke lesion
- If You're Happy, Then You Know It: The Logic of Happiness... and Sadness
- Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks
- A multi-modal approach towards mining social media data during natural disasters -- a case study of Hurricane Irma
- DEVI: Open-source Human-Robot Interface for Interactive Receptionist Systems
- Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models
- Data-Driven Random Access Optimization in Multi-Cell IoT Networks with NOMA
- Semantics for Robotic Mapping, Perception and Interaction: A Survey
- CryoNuSeg: A Dataset for Nuclei Instance Segmentation of Cryosectioned H&E-Stained Histological Images
- A space-indexed formulation of packing boxes into a larger box
- Refining activation downsampling with SoftPool
- Few-Shot Question Answering by Pretraining Span Selection
- Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval
- Coreference Resolution without Span Representations
- Modeling Disclosive Transparency in NLP Application Descriptions
- On the confidence of stereo matching in a deep-learning era: a quantitative evaluation
- Assessing Emoji Use in Modern Text Processing Tools
- The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translation
- Learning to Generate Task-Specific Adapters from Task Description
- KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation
- Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network
- Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
- Substructure Substitution: Structured Data Augmentation for NLP
- End-to-End Training of Neural Retrievers for Open-Domain Question Answering
- ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning
- CDLM: Cross-Document Language Modeling
- Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words
- Border basis computation with gradient-weighted normalization
- An Elo-like System for Massive Multiplayer Competitions
- Lex-BERT: Enhancing BERT based NER with lexicons
- Image-based Textile Decoding
- End-to-end Semantic Role Labeling with Neural Transition-based Model
- Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering
- VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
- Multitask Learning for Class-Imbalanced Discourse Classification
- A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition
- What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure
- Investigating Memorization of Conspiracy Theories in Text Generation
- RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge
- Non-line-of-Sight Imaging via Neural Transient Fields
- On-the-Fly Attention Modulation for Neural Generation
- Quaternion higher-order singular value decomposition and its applications in color image processing
- Measure of Strength of Evidence for Visually Observed Differences between Subpopulations
- New-Type Hoeffding's Inequalities and Application in Tail Bounds
- Video Captioning in Compressed Video
- Reinforcement Learning for Flexibility Design Problems
- Integrated Optimization of Predictive and Prescriptive Tasks
- Characterizing Fairness Over the Set of Good Models Under Selective Labels
- Multi-Image Steganography Using Deep Neural Networks
- Minimum Viable Model Estimates for Machine Learning Projects
- Modeling Fine-Grained Entity Types with Box Embeddings