Date
|
Topic
|
Speaker
|
Title
|
8/29
|
Paper
|
|
|
Abstract
|
|
|
8/22
|
Paper
|
|
|
Abstract
|
|
|
8/15
|
Paper
|
|
|
Abstract
|
|
|
8/8
|
Paper
|
|
|
Abstract
|
|
|
8/1
|
Paper
|
|
林伯慎老師實驗室
|
Abstract
|
|
林伯慎老師實驗室
|
7/25
|
Paper
|
|
|
Abstract
|
|
|
7/18
|
Paper
|
|
|
Abstract
|
|
|
7/11
|
Paper
|
|
|
Abstract
|
|
|
7/4
|
Paper
|
|
|
Abstract
|
|
|
6/27
|
Paper
|
|
|
Abstract
|
|
|
6/20
|
Paper
|
|
|
Abstract
|
|
|
6/13
|
Paper
|
|
|
Abstract
|
|
|
6/6
|
Paper
|
|
林伯慎老師實驗室
|
Abstract
|
|
林伯慎老師實驗室
|
5/30
|
Paper
|
|
|
Abstract
|
|
|
5/23
|
Paper
|
|
|
Abstract
|
|
|
5/16
|
Paper
|
|
|
Abstract
|
|
|
5/9
|
Paper
|
|
|
Abstract
|
|
|
5/2
|
Paper
|
|
|
Abstract
|
|
|
4/25
|
Paper
|
|
|
Abstract
|
|
|
4/18
|
Paper
|
|
Physica: Interactive Tangible Physics Simulation based on Tabletop Mobile Robots Towards Explorable Physics Education
|
Abstract
|
|
|
4/11
|
Paper
|
|
林伯慎老師實驗室
|
Abstract
|
|
林伯慎老師實驗室
|
4/4
|
Paper
|
|
清明節
|
Abstract
|
|
清明節
|
3/28
|
Paper
|
|
Poolimmersion: A Realistic Physically-Based Billiards Simulation
|
Abstract
|
|
1. CULTIVATING VISUALIZATION LITERACY FOR CHILDREN THROUGH CURIOSITY AND PLAY
2. VR Haptics at Home: Repurposing Everyday Objects and Environment for Casual and On-Demand VR Haptic Experiences
3. Augmented Math: Authoring AR-Based Explorable Explanations by Augmenting Static Math Textbooks
4. Sketched Reality: Sketching Bi-Directional Interactions Between Virtual and Physical Worlds with AR and Actuated Tangible UI
5. Xs: Interactive Scissor Mechanisms as Portable and Customizable Shape-Changing Interfaces
|
3/21
|
Paper
|
|
Collection Space Navigator: An Interactive Visualization Interface for Multidimensional Datasets
|
Abstract
|
|
1. Dynamic Modeling Based on Fuzzy Neural Network for a Billiard Robot
2. Billiards: an optimization challenge
3. Bill-EVR: An Embodied Virtual Reality Framework for Reward-and-Error-Based Motor Rehab-Learning
4. Billiards Detection and Tracking Technology Based on Artificial Intelligence Algorithm
5. Poolimmersion: A Realistic Physically-Based Billiards Simulation
|
3/14
|
Paper
|
|
HumanNeRF:Free-viewpoint Rendering of Moving People from Monocular Video
|
Abstract
|
|
1. Cross-domain Sound Recognition for Efficient Underwater Data Analysis
2. Analysis of Crime Data Visualization and Clustering: PCA + K-Means vs. Feature Extraction
3. Principal Component Analysis Visualization and State Discovery with Soil Data
4. Visualization of Topic Transitions in SNSs Using Document Embedding and Dimensionality Reduction
5. Collection Space Navigator: An Interactive Visualization Interface for Multidimensional Datasets
|
3/7
|
Paper
|
|
Image Cropping under Design Constraints
|
Abstract
|
|
1. InstanceDiffusion: Instance-level Control for Image Generation
2. Vision Transformer for NeRF-Based View Synthesis from a Single Input Image
3. You Can Run but not Hide: Improving Gait Recognition with Intrinsic Occlusion Type Awareness
4. One-Shot Synthesis of Images and Segmentation Masks
5. HumanNeRF:Free-viewpoint Rendering of Moving People from Monocular Video
|
2/29
|
Paper
|
|
CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representations
|
Abstract
|
|
1. Good View Hunting: Learning Photo Composition from Dense View Pairs
2. Deep learning for video‐based automated pain recognition in rabbits
3. CatFLW: Cat Facial Landmarks in the Wild Dataset
4. AnyFace: A Data-Centric Approach For Input-Agnostic Face Detection
5. Image Cropping under Design Constraints
|
2/22
|
Paper
|
|
Road User Position and Speed Estimation via Deep Learning from Calibrated Fisheye Videos
|
Abstract
|
|
1. Efficient Segment-Anything Model for Automatic Mask Region Extraction in Livestock Monitoring
2. Exploiting Monocular Depth Estimation for Style Harmonization in Landscape Painting
3. Investigation on Object Detection models for plant disease detection framework
4. Multiclass Support Vector Machine based Plant Leaf Diseases Identification from Color, Texture and Shape Features
5. CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representations
|
2/15
|
Paper
|
|
新年
|
Abstract
|
|
|
2/8
|
Paper
|
|
|
Abstract
|
|
1. Explainable Multimodal Emotion Reasoning (arXiv, June 2023)
2. Multimodal Emotion Recognition via Convolutional Neural Networks: Comparison of different strategies on two multimodal datasets
3. Deep learning-based vehicle speed estimation using the YOLO detector and 1D-CNN
4. FARSEC: A Reproducible Framework for Automatic Real-Time Vehicle Speed Estimation Using Traffic Cameras
5. Road User Position and Speed Estimation via Deep Learning from Calibrated Fisheye Videos
|
2/1
|
Paper
|
|
林伯慎老師實驗室
|
Abstract
|
|
林伯慎老師實驗室
|
1/25
|
Paper
|
|
Design of OpenPose-Based of Exercise Assistant System with Instructor-User Synchronization for Self-Practice Dynamic Yoga
|
Abstract
|
|
|
1/18
|
Paper
|
|
Improving the Accuracy of Lane Detection by Enhancing the Long-Range Dependence
|
Abstract
|
|
1.An OpenPose-Based Exercise and Performance Learning Assistant Design for Self-Practice Yoga
2.Deep Learning-Based Yoga Posture Recognition Using the Y_PN-MSSD Model for Yoga Practitioners
3.Real-time Yoga recognition using deep learning
4.INFINITY YOGA TUTOR : YOGA POSTURE DETECTION AND CORRECTION SYSTEM
5.Design of OpenPose-Based of Exercise Assistant System with Instructor-User Synchronization for Self-Practice Dynamic Yoga
|
1/11
|
Paper
|
|
Line Segment Matching Fusing Local Gradient Order and Non-Local Structure Information
|
Abstract
|
|
1. Lane Line Detection Based on Dynamic ROI and Adaptive Thresholding Segmentation
2. Conditional Convolutions for Instance Segmentation
3. Ultra Fast Structure-aware Deep Lane Detection
4. End-to-End Lane Marker Detection via Row-wise Classification
5. Improving the Accuracy of Lane Detection by Enhancing the Long-Range Dependence
|
1/4
|
Paper
|
|
1. Color Constancy by Deep Learning
2. FC4: Fully Convolutional Color Constancy with Confidence-weighted Pooling
3. Guiding the Illumination Estimation Using the Attention Mechanism
4. Approaching the Computational Color Constancy as a Classification Problem through Deep Learning
5. One-net: Convolutional color constancy simplified
|
Abstract
|
|
- An Enhanced Image Matching Strategy Using Binary-Stream Feature Descriptors
- Line Segment Matching: A Benchmark
- LINE SEGMENT MATCHING ALGORITHM BASED ON FEATURE GROUPING AND LBD DESCRIPTOR
- Line detection via a lightweight CNN with a Hough Layer
- Line Segment Matching Fusing Local Gradient Order and Non-Local Structure Information
|
|
NTUST Computer Graphics Multimedia Lab
|