# Meeting Paper List ## 2025 1/15 學姐報論文 --- 2/19 軒名 * Predicting EF value from chest x-rays and 12-lead ecgs thrugh a two stage multimodal imaging model --- 2/26 振庭 * Deep Learning for Satellite Image Time Series Analysis: A Review * ViTs for SITS: Vision Transformers for Satellite Image Time Series * Gated Revisited: Deep Multi-layer RNNs That Can Be Trained --- 3/5 哲嘉 * DETRs Beat YOLOs on Real-time Object Detection --- 3/12 兆偉 * FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction * Federated Learning in Computer Vision * Communication-Efficient Learning of Deep Networks from Decentralized Data --- 3/19 明翰 * AI integration in construction safety: Current state, challenges, and future opportunities in text, vision, and audio based applications * Separable Self and Mixed Attention Transformers for Efficient Object Tracking * YOLOv12: Attention-Centric Real-Time Object Detectors * Transformers without Normalization --- 3/26 卓均 * Data Structures for Computing Unique Palindromes in Static and Non-static Strings 4/2 4/9 4/16 4/23 哲嘉 * Deep Learning-Based Localization and Detection of Malpositioned Endotracheal Tube on Portable Supine Chest Radiographs in Intensive and Emergency Medicine: A Multicenter Retrospective Study * RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision * VarifocalNet: An IoU-aware Dense Object Detector 5/7 兆偉 5/14 明翰 * DiffCR: A Fast Conditional Diffusion Framework for Cloud Removal from Optical Satellite Images * NT-Net: A Semantic Segmentation Network for Extracting Lake Water Bodies From Optical Remote Sensing Images Based on Transformer * SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images <br> <br> <br> <br> <br> <br> <br> --- ## 2024 10/23 * Swin Transformer: Hierarchical Vision Transformer using Shifted Windows --- 10/30 明翰 - [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models ](https://arxiv.org/abs/2109.10282) --- 11/27 明翰 - [CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model](https://arxiv.org/pdf/2305.14014) - [DTrOCR: Decoder-only Transformer for Optical Character Recognition ](https://arxiv.org/pdf/2308.15996) --- 12/4 * Masked-attention Mask Transformer for Universal Image Segmentation --- 12/11 * Detecting Endotracheal Tube and Carina on Portable Supine Chest Radiographs Using One-Stage Detector with a Coarse-to-Fine Attention --- 12/18 學長報論文 --- 12/25 * Interpreting CLIP's Image Representation via Text-Based Decomposition