Date
Topic
Speaker
Title
12/31
Paper
Ann
Abstract
Mojib
12/24
Paper
林紀揚
Abstract
Ann
12/17
Paper
宋逸慈
Abstract
林紀揚
12/10
Paper
徐晟紘
Abstract
宋逸慈
12/3
Paper
Richard
與林伯慎老師實驗室Meeting(our turn)
Abstract
徐晟紘
與林伯慎老師實驗室Meeting(our turn)
11/26
Paper
徐孟辰
Abstract
Richard
11/19
Paper
陳凱呈
Abstract
徐孟辰
11/12
Paper
潘玟蓁
Abstract
陳凱呈
11/5
Paper
X
與林伯慎老師實驗室Meeting
Abstract
X
與林伯慎老師實驗室Meeting
10/29
Paper
Enrico
Abstract
潘玟蓁
10/22
Paper
林怡伶
Abstract
Enrico
10/15
Paper
葉三吉
Research on lip detection based on Opencv(2011 International Conference on Transportation, Mechanical, and Electrical Engineering(TMEE))
Abstract
林怡伶
10/8
Paper
李一峯
與林伯慎老師實驗室Meeting(our turn)
Learning to See Through Obstructions (Computer Vision And Pattern Recognition 2020)
Abstract
葉三吉
與林伯慎老師實驗室Meeting(our turn)
Object Image Relighting through Patch MAtch Warping and Color Transfer(Accepted to 2016 International Conference on Virtual Reality and Visualization)
Deep Single-Image Portrait Relighting(2019 IEEE/CVF International Conference on Computer Vision(ICCV))
Implementation of Linear Structuring Element in OpenCV for Blood Vessel Segmentation form Color Fundus Images(Published in 2019: 10th International COnference on COmputin, Communication and Networking Technologies(ICCCNT))
Development of Android Application for Gender, Age and Face Recognition Using OpenCV(MIPRO 2019, May 20-24, 2019, Opatija Croatia)
Research on lip detection based on Opencv(2011 International Conference on Transportation, Mechanical, and Electrical Engineering(TMEE))
10/1
Paper
X
中秋節放假
Abstract
X
中秋節放假
9/24
Paper
Mojib
Abstract
李一峯
CNN-generated images are surprisingly easy to spot… for now (Accepted to CVPR 2020)
Deep Image Matting (Computer Vision And Pattern Recognition 2017)
Background Matting: The World is Your Green Screen (Computer Vision And Pattern Recognition 2020)
“Double-DIP”: Unsupervised Image Decomposition via Coupled-Imaged-Priors (Computer Vision And Pattern Recognition 2019)
Learning to See Through Obstructions (Computer Vision And Pattern Recognition 2020)
9/17
Paper
老師上課
老師上課
Abstract
老師上課
老師上課
9/10
Paper
鄭元棓
Depth-Aware Video Frame Interpolation (CVPR 2019)
Abstract
Mojib
9/3
Paper
X
與林伯慎老師實驗室Meeting
Abstract
X
與林伯慎老師實驗室Meeting
8/27
Paper
Richard
A simple yet effective baseline for 3d human pose estimation
J. Martinez, R. Hossain, J. Romero and J. J. Little
2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 2659-2668
Abstract
鄭元培
A machine learning approach to predict the winner in StarCraft based on influence maps (Entertainment Computing 2017)
Playing first-person shooter games with machine learning techniques and methods using the VizDoom Game-AI research platform (Entertainment Computing 2020)
3D Photography using Context-aware Layered Depth Inpainting (CVPR 2020)
Interactive Video Stylization Using Few-Shot Patch-Based Training (CVPR 2020)
Depth-Aware Video Frame Interpolation (CVPR 2019)
8/20
Paper
徐晟紘
Deep Learning Towards Mobile Applications(IEEE 2018)
Abstract
Richard
1. Deeper Depth Prediction with Fully Convolutional Residual Networks
I. Laina, C. Rupprecht, V. Belagiannis, F. Tombari and N. Navab
2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, 2016, pp. 239-248
IEEE 2016
2. Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
Eigen, David & Puhrsch, Christian & Fergus, Rob.
Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2December 2014 Pages 2366–2374
3. Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
Jonathan Tompson, Arjun Jain, et al
Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 1 December 2014 Pages 1799–1807
4. Learning Human Pose Estimation Features with Convolutional Networks
Arjun Jain, Jonathan Tompson, et al
ICLR 2014 conference Apr 14 - 16, 2014, Banff, Canada
5. A simple yet effective baseline for 3d human pose estimation
J. Martinez, R. Hossain, J. Romero and J. J. Little
2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017, pp. 2659-2668
8/13
Paper
徐孟辰
Generating Long Sequences with Sparse Transformers
Abstract
徐晟紘
1.Acoustic event detection in real life recordings(IEEE 2010)
2.Automatic bird sound detection in long real-field recordings Applcations and tools(2014 Applied Acousticcs)
3.Bird detection in audio A survey and a challenge(IEEE 2016)
4.Bird Sound Recognition Using a Convolutional Neural Network(IEEE 2018)
5.Deep Learning Towards Mobile Applications(IEEE 2018)
8/6
Paper
陳凱呈
與林伯慎老師實驗室Meeting(our turn)
SVM-based Soccer Video Summarization System(2011 Third World Congress on Nature and Biologically Inspired Computing)
Abstract
徐孟辰
與林伯慎老師實驗室Meeting(our turn)
1.Transformers: State-of-the-Art Natural Language Processing
2.SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing
3.Language Models are Few-Shot Learners
4.Revisiting Pre-Trained Models for Chinese Natural Language Processing
5.Generating Long Sequences with Sparse Transformers
7/30
Paper
潘玟蓁
Object Detection in Equirectangular Panorama (2018 International Conference on Pattern Recognition)
Abstract
陳凱呈
1.Shot Type and Replay Detection for Soccer Video Parsing(2012 IEEE International Symposium on Multimedia)
2.Soccer Video Summarization based on Cinematography and Motion Analysis(2014 IEEE 16th International Workshop on Multimedia Signal Processing (MMSP))
3.Automatic analysis of broadcast football videos using contextual priors(Signal, Image and Video Processing volume 11, pages171–178(2017))
4.Highlight Ranking for Sports Video Browsing (MULTIMEDIA '2005: Proceedings of the 13th annual ACM international conference on Multimedia Pages 519–522)
5.SVM-based Soccer Video Summarization System(2011 Third World Congress on Nature and Biologically Inspired Computing)
7/23
Paper
Enrico
5. GPU-Based Parallel Particle Swarm Optimization Methods for Graph Drawing (Discrete Dynamics in Nature and Society Volume 2017)
Abstract
潘玟蓁
1. Multiple Object Detection in 360◦ Videos for Robust Tracking (2019 International Conference on Pattern Recognition and Machine Intelligence)
2. Diminishing unwanted objects based on object detection using deep learning and image inpainting (2018 International Workshop on Advanced Image Technology)
3. Assessing Individual Dietary Intake in Food Sharing Scenarios with a 360 Camera and Deep Learning (2019 IEEE International Conference on Wearable and Implantable Body Sensor Networks)
4. Object Detection on Panoramic Images Based on Deep Learning (2017 International Conference on Control, Automation and Robotics)
5. Object Detection in Equirectangular Panorama (2018 International Conference on Pattern Recognition)
7/16
Paper
林怡伶
SSD: Single Shot MultiBox Detector (ECCV 2016)
Abstract
Enrico
1. An Algorithm for Drawing General Undirected Graph (Information Processing Letters 31 1989)
2. Graph Layout Using a Genetic Algorithm (Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks IEEE 2000)
3. TimGA: A Genetic Algorithm for Drawing Undirected Graphs (Divulgaciones Matematicas Vol 9 no. 2 2001)
4. Drawing Undirected Graphs with Genetic Algorithms (ICNC 2005: Advances in Natural Computation)
5. GPU-Based Parallel Particle Swarm Optimization Methods for Graph Drawing (Discrete Dynamics in Nature and Society Volume 2017)
7/9
Paper
X
CGW
Abstract
X
CGW
7/2
Paper
X
與林伯慎老師實驗室Meeting
Abstract
X
與林伯慎老師實驗室Meeting
6/25
Paper
X
Dragon Boat Festival 端午節
Abstract
X
Dragon Boat Festival 端午節
6/18
Paper
X
Special Topic
Abstract
X
Special Topic
6/11
Paper
X
老師上課
Abstract
X
老師上課
6/4
Paper
李一峯
與林伯慎老師實驗室Meeting(our turn)
Abstract
林怡伶
1.Photographic Tone Reproduction for Digital Images(ACM Transactions on Graphics, 2002)
2.Brightness Calculation in Digital Image Processing(Society for Imaging Science and Technology, 2007)
3.The Beauty of Capturing Faces: Rating the Quality of Digital Portraits(Computer Vision and Pattern Recognition, 2015)
4.Human Iris Segmentation for Iris Recognition in Unconstrained Environments(International Journal of Computer Science Issues, 2012)
5.SSD: Single Shot MultiBox Detector (ECCV 2016)
5/28
Paper
Mojib
Image Inpainting by Hyperbolic Selection of Pixels for Two-Dimensional Bicubic Interpolations(2018 IEEE Iranian Conference on Electrical Engineering (ICEE))
Abstract
李一峯
1.One Pixel Attack for Fooling Deep Neural Networks(IEEE Transactions on Evolutionary Computation, 2019)
2.Adversarial Policies: Attacking Deep Reinforcement Learning(Under review as a conference paper at ICLR 2020)
3.An Ensemble of VGG Networks for Video-Based Facial Expression Recognition(2018 First Asian Conference on Affective Computing and Intelligent Interaction (ACII Asia))
4.Learning Rich Features for Image Manipulation Detection(2018 Conference on Computer Vision and Pattern Recognition)
5.Image Inpainting for Irregular Holes Using Partial Convolutions(2019 European Conference on Computer Vision (ECCV))
5/21
Paper
Richard
DeepPose: Human Pose Estimation via Deep Neural Networks(2014 IEEE Conference on Computer Vision and Pattern Recognition)
Abstract
Mojib
1.Object Removal by Exemplar-Based Inpainting(2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Proceeding)
2.Semi automatic image inpainting using partial JSEG segmentation(2017 IEEE International Conference on Inventive Systems and Control (ICISC))
3.Robust exemplar based image and video inpainting for object removal and region filling(2017 IEEE International Conference on Intelligent Computing and Control (I2C2))
4.Image Inpainting Based on Image Mapping and Object Removal Using Semi-Automatic Method(2018 IEEE International Conference On Advances in Communication and Computing Technology (ICACCT))
5.RIBBONS: Rapid Inpainting Based on Browsing of Neighborhood Statistics(2018 IEEE Iranian Conference on Electrical Engineering (ICEE))
5/14
Paper
徐孟辰
3D human pose estimation in video with temporal convolutions and semi-supervised training(IEEE CVPR, 2019)
Abstract
Richard
1.Helmet Violation Processing Using Deep Learning(2018 IEEE International Workshop on Advanced Image Technology (IWAIT))
2.Detection of Motorcyclists without Helmet in Videos using Convolutional Neural Network(2017 IEEE International Joint Conference on Neural Networks (IJCNN))
3.An Efficient Helmet Detection for MVD using Deep learning(Proceedings of the Third International Conference on Trends in Electronics and Informatics (ICOEI 2019),IEEE)
4.Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition(Proceedings of the 9th ACM International Conference on PErvasive Technologies Related to Assistive Environments,2016)
5.DeepPose: Human Pose Estimation via Deep Neural Networks(2014 IEEE Conference on Computer Vision and Pattern Recognition)
5/7
Paper
X
與林伯慎老師實驗室Meeting
Abstract
X
與林伯慎老師實驗室Meeting
4/30
Paper
高宜芳
Cross-View Image Matching for Geo-localization in Urban Environments (2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR))
Abstract
徐孟辰
1. OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields (IEEE PAMI 2019)
2. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition(AAAI CVPR, 2018)
3. DensePose: Dense Human Pose Estimation In The Wild(IEEE CVPR, 2018)
4. LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images(IEEE PAMI, 2019)
5. 3D human pose estimation in video with temporal convolutions and semi-supervised training(IEEE CVPR, 2019)
4/23
Paper
鄭鈴錡
A Probabilistic Model for Component-Based Shape Synthesis(ACM Transactions on Graphics (TOG), 2011)
Abstract
高宜芳
1. Vision Based Campus Guide System On Intelligent Mobile Phone (2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW))
2. Building Extraction Based on Hue Cluster Analysis in Complex Scene (2009 2nd International Congress on Image and Signal Processing)
3. Extraction building based on adaptive detection algorithm of key points (2011 19th International Conference on Geoinformatics)
4. Single Image Depth Estimation Using Deep Adversarial Training (2019 IEEE International Conference on Image Processing (ICIP))
5. Cross-View Image Matching for Geo-localization in Urban Environments (2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR))
4/16
Paper
盧立恩
Speaker Diarization With Region Proposal Network (2020 International Conference on Acoustics, Speech, and Signal Processing)
Abstract
鄭鈴錡
1.The Trimmed Iterative Closest Point Algorithm(International Conference on Pattern Recognition, 2002)
2.Filling holes in complex surfaces using volumetric diffusion(First International Symposium on 3D Data Processing Visualization and Transmission, 2002)
3.Optimal boundaries for Poisson mesh merging(ACM Symposium on Solid and Physical Modeling, 2007)
4.Drag, Drop, and Clone: An Interactive Interface for Surface Composition(Technical Report CSRG-611, Department of Computer Science, 2010)
5.A Probabilistic Model for Component-Based Shape Synthesis(ACM Transactions on Graphics (TOG), 2011)
4/9
Paper
Adawiyah
與林伯慎老師實驗室Meeting(our turn)
Large-Scale Bird Sound Classification using Convolutional Neural Networks (2017, Conference and Labs of the Evaluation Forum (CLEF))
Abstract
盧立恩
與林伯慎老師實驗室Meeting(our turn)
1.Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks (Audio and Speech Processing, IEEE 2016)
2.Comparison of Scene Change Detection Algorithms for Videos (2015 Fifth International Conference on Advanced Computing & Communication Technologies, IEEE 2015)
3.Linkage Based Face Clustering via Graph Convolution Network (2019 Conference on Computer Vision and Pattern Recognition)
4.Self-Supervised Learning For Audio-visual Speaker Diarization (2020 Electrical Engineering and Systems Science)
5.Speaker Diarization With Region Proposal Network (2020 International Conference on Acoustics, Speech, and Signal Processing)
4/2
Paper
X
Holiday
Abstract
X
Holiday
3/26
Paper
陳凱呈
Soccer Video Summarization using Deep Learning(2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR))
Abstract
Adawiyah
1.Convolutional Neural Networks for Large-Scale Bird Song Classification in Noisy Environment (2016 Conference and Labs of the Evaluation Forum (CLEF) South America)
2.Simultaneous Segmentation and Classification of Bird Song using CNN (2017 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP))
3.Bird Sound Classification using Convolutional Neural Networks (2019, Conference and Labs of the Evaluation Forum (CLEF), Lugano, Switzerland)
4.Audio-based Bird Species Identification with Deep Convolutional Neural Networks (2018, Conference and Labs of the Evaluation Forum (CLEF))
5.Large-Scale Bird Sound Classification using Convolutional Neural Networks (2017, Conference and Labs of the Evaluation Forum (CLEF))
3/19
Paper
潘玟蓁
AR interior designer: Automatic furniture arrangement using spatial and functional relationships(2014 International Conference on Virtual Systems & Multimedia)
Abstract
陳凱呈
1.Automatic Broadcast Soccer Video Analysis, Player Detection, and Tracking Based on Color Histogram(2013 Intelligent Technologies and Engineering Systems pp 123-130)
2.A Decision Tree-based Multimodal Data Mining Framework for Soccer Goal Detection(2004 IEEE International Conference on Multimedia and Expo (ICME))
3.ALGORITHMS AND SYSTEM FOR SEGMENTATION AND STRUCTURE ANALYSIS IN SOCCER VIDEO(IEEE International Conference on Multimedia and Expo, 2001. ICME 2001)
4.An SVM-Based Soccer Video Shot Classification Scheme Using Projection Histograms (Advances in Multimedia Information Processing - PCM 2008)
5.Soccer Video Summarization using Deep Learning(2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR))
3/12
Paper
Enrico
Dynamic Drawing of Clustered Graphs (IEEE 2014)
Abstract
潘玟蓁
1.Integrating YOLO Object Detection with Augmented Reality for iOS Apps(2018 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference)
2.AR DeepCalorieCam V2: Food Calorie Estimation with CNN and AR-based Actual Size Estimation(Proceedings of the 24th ACM Symposium on Virtual Reality Software and Technology, 2018)
3.Detecting hand-palm orientation and hand shapes for sign language gesture recognition using 3D images(2012 Western New York Image Processing Workshop)
4.Camera Pose Navigation using Augmented Reality(2010 IEEE International Symposium on Mixed and Augmented Reality)
5.AR interior designer: Automatic furniture arrangement using spatial and functional relationships(2014 International Conference on Virtual Systems & Multimedia)
3/5
Paper
X
與林伯慎老師實驗室Meeting
Abstract
X
與林伯慎老師實驗室Meeting
2/27
Paper
林怡伶
Super-Identity Convolutional Neural Network for Face Hallucination(ECCV, 2018)
Abstract
Enrico
1.Cluster Busting in Anchored Graph Drawing (Proceedings of the 1992 Conference of the Centre for Advanced Studies on Collaborative Research)
2.Laplacian-based Dynamic Graph Visualization (IEEE 2015)
3.The Mental Map and Memorability in Dynamic Graphs (IEEE 2012)
4.Interactive Visualization of Evolving Force-Directed Graphs (DUXU 2013)
5.Dynamic Drawing of Clustered Graphs (IEEE 2014)
2/20
Paper
侯尊堯
Generalized Dynamic Time Warping:Unleashing the Warping Power Hidden in Point-Wise Distances(2018 IEEE 34th International Conference on Data Engineering)
Abstract
林怡伶
1.Lens Distortion Correction Using Ideal Image Coordinates(Transactions on Consumer Electronics, 2009 IEEE)
2.Identifiable Images of Bystanders Extracted from Corneal Reflections(PLoS ONE, 2013)
3.Estimating Focused Object using Corneal Surface Image for Eye-based Interaction(Journal of Eye Movement Research , 2014)
4.Image Location Estimation of Well-known Places from Multi-source based Information(IEEE Transactions on Image Processing, 2015)
5.Super-Identity Convolutional Neural Network for Face Hallucination(ECCV, 2018)
2/13
Paper
Luckman
Video Face Clustering with Unknown Number of Clusters(Proceedings of the IEEE International Conference on Computer Vision, 2019)
Abstract
侯尊堯
1.Objective Distortion Measure for Binary Text Image Based on Edge Line Segment Similarity(2007 IEEE Transactions on Image Processing)
2.Hidden Images(2011 Proceedings of the ACM SIGGRAPH/ Eurographics Symposium on Non-Photorealistic Animation and Rendering(NPAR))
3.Structure Importance-Aware Hidden Images(2019 IEEE 11th International Conference on Advanced Infocomm Technology)
4.A Hybrid Time Series Matching Algorithm Based on Feature-Points and DTW(2016 IEEE 9th International Symposium on Computational Intelligence and Design)
5.Generalized Dynamic Time Warping:Unleashing the Warping Power Hidden in Point-Wise Distances(2018 IEEE 34th International Conference on Data Engineering)
2/6
Paper
李一峯
與林伯慎老師實驗室Meeting(our turn)
Live Face De-Identification in Video(Proceedings of IEEE International Conference on Computer Vision 2019)
Abstract
Luckman
與林伯慎老師實驗室Meeting(our turn)
1.Deep clustering with convolutional autoencoders(International conference on neural information processing. 2017)
2.Overcoming catastrophic forgetting in neural networks(arXiv:1612.00796v2 [cs.LG] 25 january 2017)
3.Deep Mutual Learning(Computer Vision and Pattern Recognition Conference 2017)
4.Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree(Artificial intelligence and statistics, 2016)
5.Video Face Clustering with Unknown Number of Clusters(Proceedings of the IEEE International Conference on Computer Vision, 2019)
1/30
Paper
Mojib
“Ready Player One”: Enhancing Omnidirectional Treadmills for Use in Virtual Environments(2019 IEEE Conference on Virtual Reality and 3D User Interfaces (VR))
Abstract
李一峯
1.A complexity approach for identifying aesthetic composite landscapes(Third International Conference, EvoMUSART 2014)
2.Hand Gesture Recognition Using Kinect(Proceedings of 2012 IEEE 3rd International Conference on Software Engineering and Service Science)
3.VGGFace2:A dataset for recognising faces across pose and age(Proceedings of 13th IEEE International Conference on Automatic Face and Gesture Recognition, 2018)
4.On face segmentation, face swapping, and face perception(Proceedings of 13th IEEE International Conference on Automatic Face and Gesture Recognition, 2018)
5.Live Face De-Identification in Video(Proceedings of IEEE International Conference on Computer Vision 2019)
1/23
Paper
X
Chinese New Year 春假
Abstract
X
Chinese New Year 春假
1/16
Paper
X
老師上課
Abstract
X
老師上課
1/9
Paper
X
Special Topic
Abstract
X
Special Topic
1/2
Paper
X
與林伯慎老師實驗室Meeting
Abstract
X
與林伯慎老師實驗室Meeting
NTUST Computer Graphics Multimedia Lab