Publications

Journal Paper:

Wen-Li Wei and Jen-Chun Lin: Bridging Actions: Generate 3D Poses and Shapes In-between Photos. to appear in IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1-18, Early Access [Website] https://mps-net.github.io/ADAM-Net/

Wen-Li Wei, Jen-Chun Lin, Tyng-Luh Liu, Hsiao-Rong Tyan, Hsin-Min Wang, and Hong-Yuan Mark Liao: Learning To Visualize Music Through Shot Sequence For Automatic Concert Video Mashup. IEEE Transactions on Multimedia, 23: 1731-1743 (2021)

Jen-Chun Lin, Wen-Li Wei, Tyng-Luh Liu, Yi-Hsuan Yang, Hsin-Min Wang, Hsiao-Rong Tyan, and Hong-Yuan Mark Liao: Coherent Deep-Net Fusion To Classify Shots in Concert Videos. IEEE Transactions on Multimedia, 20(11): 3123-3136 (2018)

Wen-Li Wei, Jen-Chun Lin, Chung-Hsien Wu: Interaction Style Recognition Based on Multi-layer Multi-view Profile Representation. IEEE Transactions on Affective Computing, 8(3): 355-368 (2017)

Chung-Hsien Wu, Jen-Chun Lin, Wen-Li Wei: Survey on Audiovisual Emotion Recognition: Databases, Features, and Data Fusion Strategies. APSIPA Transactions on Signal and Information Processing, 3(12): 1-18, (2014)  [invited paper] (2018 APSIPA Sadaoki Furui Prize Paper Award)

Wen-Li Wei, Chung-Hsien Wu, Jen-Chun Lin, Han Li: Exploiting Psychological Factors for Interaction Style Recognition in Spoken Conversation. IEEE Transactions on Audio, Speech and Language Processing, 22(3): 659-671, (2014) (on the cover of the March/April IEEE Trans. Audio, Speech and Language Processing, selected by Editor-in-Chief Li Deng) [Website]  http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6777757

Chung-Hsien Wu, Jen-Chun Lin, Wen-Li Wei: Two-Level Hierarchical Alignment for Semi-Coupled HMM-Based Audiovisual Emotion Recognition with Temporal Course. IEEE Transactions on Multimedia 15(8): 1880-1895 (2013)

Chung-Hsien Wu, Wen-Li Wei, Jen-Chun Lin, Wei-Yu Lee: Speaking Effect Removal on Emotion Recognition from Facial Expressions Based on Eigenface Conversion. IEEE Transactions on Multimedia 15(8): 1732-1744 (2013)

Jen-Chun Lin, Chung-Hsien Wu, Wen-Li Wei: Error Weighted Semi-Coupled Hidden Markov Model for Audio-Visual Emotion Recognition. IEEE Transactions on Multimedia 14(1): 142-156 (2012)

International Conference Paper: ( * authors contributed equally)

Wen-Li Wei and Jen-Chun Lin: Multi-Candidate Motion Modeling for 3D Human Pose and Shape Estimation from Monocular Video. accepted by IEEE International Conference on Multimedia and Expo (ICME), 2024 (ORAL PRESENTATION) [Website] https://seethevoice.github.io/MMPS/

Bo-Wei Tseng, Kenneth Yang, Yu-Hua Hu, Wen-Li Wei, and Jen-Chun Lin: Music-to-Dance Poses: Learning to Retrieve Dance Poses from Music. accepted by IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024 (ORAL PRESENTATION)

Huang-Ru Liao, Jen-Chun Lin, and Chun-Yi Lee: Progressive Hypothesis Transformer for 3D Human Mesh Recovery. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024

Pin-Chi Pan, Tzu-Hao Hsu, Wen-Li Wei, and Jen-Chun Lin: Global-local Awareness Network for Image Super-resolution. IEEE International Conference on Image Processing (ICIP), 2023. [Website & Code] https://panpinchi.github.io/GLA-Net/

Jen-Chun Lin and Wen-Li Wei: 3D Character Motion Authoring from Temporally-Sparse Photos. ACM SIGGRAPH Posters, Los Angeles, USA, 2023 (acceptance rate = 35.7%)

Wen-Li Wei*, Jen-Chun Lin*, Tyng-Luh Liu, and Hong-Yuan Mark Liao: Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (acceptance rate = 25.33% (2067/8161)) [Website & Code] https://mps-net.github.io/MPS-Net/

Jung Yeh, Wen-Li Wei, Duan-Yu Chen, and Jen-Chun Lin: Learning to Sharpen Partially Blurred Image via Iterative Blurred Region Mining and Recovery.  APSIPA Annual Summit and Conference (APSIPA ASC), 2022 [Website & Database] https://sites.google.com/view/ibrmr

Hsin-Min Chou, Ting-Wei Lin, Jen-Chun Lin, Ching Te Chiu, and Li Su: CCVS: A Dataset for Concert Videography Research. Late-breaking/Demo (LBD) Session of International Society of Music Information Retrieval Conference (ISMIR LBD), 2022

I-Yuan Kuo, Wen-Li Wei, and Jen-Chun Lin: Positions, Channels, and Layers: Fully Generalized Non-Local Network for Singer Identification. Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021 (acceptance rate = 21% (1692/7911)) [Website & Code] https://github.com/ian-k-1217/Fully-Generalized-Non-Local-Network

Jen-Chun Lin, Wen-Li Wei, Yen-Yu Lin, Tyng-Luh Liu, and Hong-Yuan Mark Liao: Learning From Music to Visual Storytelling of Shots: A Deep Interactive Learning Mechanism. ACM Multimedia (MM), Seattle, United States, 2020 (Full Research Paper with ORAL PRESENTATION ~9%) [Website] https://seethevoice.github.io/m2vsdil/

Jen-Chun Lin, Wen-Li Wei, Tyng-Luh Liu, C.-C. Jay Kuo, and Hong-Yuan Mark Liao: Tell Me Where It is Still Blurry: Adversarial Blurred Region Mining and Refining. ACM Multimedia (MM), Nice, France, 2019 (Full Research Paper with ORAL PRESENTATION) [Website] https://sites.google.com/site/adversarialbrmr/home

Wen-Li Wei, Jen-Chun Lin, Yen-Yu Lin, and Hong-Yuan Mark Liao: What Makes You Look Like You: Learning an Inherent Feature Representation for Person Re-Identification. IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS), Taipei, Taiwan, 2019

Wen-Li Wei, Jen-Chun Lin, Tyng-Luh Liu, Yi-Hsuan Yang, Hsin-Min Wang, Hsiao-Rong Tyan, and Hong-Yuan Mark Liao: Seethevoice: Learning from Music to Visual Storytelling of Shots, IEEE International Conference on Multimedia and Expo (ICME), San Diego, USA, 2018 (PAPER, acceptance rate = 30%) [Website] https://sites.google.com/site/music2shots/demo

Jen-Chun Lin, Wen-Li Wei, James Yang, Hsin-Min Wang, and Hong-Yuan Mark Liao: Automatic Music Video Generation Based on Simultaneous Soundtrack Recommendation and Video Editing.  ACM Multimedia (MM), Mountain View, CA USA, 2017 (Full Research Paper with ORAL PRESENTATION, ~7.5% (50/675) acceptance rate) [Website] https://sites.google.com/site/automvgeneration/ (Postdoctoral Academic Publication Award, MOST, 2017)

Wen-Li Wei, Jen-Chun Lin, Tyng-Luh Liu, Yi-Hsuan Yang, Hsin-Min Wang, Hsiao-Rong Tyan, and Hong-Yuan Mark Liao: Deep-Net Fusion to Classify Shots in Concert Videos. ICASSP, NEW ORLEANS, USA, 2017 (ORAL PRESENTATION) [DEMO Website] https://sites.google.com/site/ewdeepccm2/demo

Jen-Chun Lin, Wen-Li Wei, Hsin-Min Wang: Automatic Music Video Generation Based on Emotion-Oriented Pseudo Song Prediction and Matching. ACM Multimedia (MM), 2016 (SHORT PAPER, acceptance rate = 30%) [DEMO Website] https://sites.google.com/site/pseudosongpredictionmatching/

Jen-Chun Lin, Wen-Li Wei, Hsin-Min Wang: DEMV-matchmaker: Emotional Temporal Course Representation and Deep Similarity Matching for Automatic Music Video Generation. ICASSP, Shanghai, China, 2016 [DEMO Website] https://sites.google.com/site/demvmatchmakermosresult/

Jen-Cheng Hou, Syu-Siang Wang, Ying-Hui Lai, Jen-Chun Lin, Yu Tsao, Hsiu-Wen Chang, and Hsin-Min Wang: Audio-Visual Speech Enhancement using Deep Neural Networks. APSIPA, JEJU, KOREA, 2016

Jen-Chun Lin, Wen-Li Wei, Hsin-Min Wang: EMV-matchmaker: Emotional Temporal Course Modeling and Matching for Automatic Music Video Generation. ACM Multimedia (MM), Brisbane, Australia, 2015 (SHORT PAPER, acceptance rate = 35.2% (136/386)) [DEMO Website] https://sites.google.com/site/emvmatchmaker/home?pli=1

Chung-Hsien Wu, Jen-Chun Lin, Wei-Bin Liang, Kuan-Chun Cheng: Hierarchical Modeling of Temporal Course in Emotional Expression for Speech Emotion Recognition. The Affective Social Multimedia Computing (ASMMC) --An ACII Workshop, China, 2015 (is awarded with "Most Interesting Paper")

Jen-Chun Lin, Wen-Li Wei, Chung-Hsien Wu, Hsin-Min Wang: Emotion Recognition of Conversational Affective Speech Using Temporal Course Modeling-Based Error Weighted Cross-Correlation Model. APSIPA, Siem Reap, Cambodia, 2014

Chung-Hsien Wu, Jen-Chun Lin, Wen-Li Wei: Action Unit Reconstruction of Occluded Facial Expression. ICOT, China, 2014

Chung-Hsien Wu, Jen-Chun Lin, Wen-Li Wei, Kuan-Chun Cheng: Emotion Recognition from Multi-Modal Information. APSIPA, Taiwan, 2013

Jen-Chun Lin, Chung-Hsien Wu, Wen-Li Wei: Emotion Recognition of Conversational Affective Speech Using Temporal Course Modeling. Interspeech, Lyon, France, 2013

Jen-Chun Lin, Chung-Hsien Wu, Wen-Li Wei: Facial Action Unit Prediction under Partial Occlusion Based on Error Weighted Cross-Correlation Model. ICASSP, Vancouver, Canada, 2013

Wen-Li Wei, Chung-Hsien Wu, Jen-Chun Lin, Han Li: Interaction Style Detection Based on Fused Cross-Correlation Model in Spoken Conversation. ICASSP, Vancouver, Canada, 2013

Jen-Chun Lin, Chung-Hsien Wu, Wen-Li Wei: A Probabilistic Fusion Strategy for Audiovisual Emotion Recognition of Sparse and Noisy Data. ICOT, Taiwan, 2013

Jen-Chun Lin, Chung-Hsien Wu, Wen-Li Wei: Semi-Coupled Hidden Markov Model with State-Based Alignment Strategy for Audio-Visual Emotion Recognition. ACII (1), Memphis, USA, 2011: 185-194

Wen-Li Wei, Chung-Hsien Wu, Jen-Chun Lin: A Regression Approach to Affective Rating of Chinese Words from ANEW. ACII (2), Memphis, USA, 2011: 121-131

Jen-Chun Lin, Chung-Hsien Wu, Wen-Li Wei, Chia-Jui Liu: Audio-Visual Emotion Recognition Using Semi-Coupled HMM and Error-Weighted Classifier Combination. APSIPA, Singapore, 2010

Chih-Shan Liu, Jen-Chun Lin, Nai-Chung Yang, Chung-Ming Kuo: Motion Vector Re-estimation for Trans-coding Using Kalman Filter. IIH-MSP, Taiwan, 2007: 592-595

Domestic Conference Paper:

魏文麗, 林仁俊, 劉庭祿, 田筱榮, 廖弘源: 基於尺度不變特徵轉換之演唱會音訊校準. 台灣網際網路研討會TANET, Taiwan, 2016 (Best Paper Award)

朱家德, 林仁俊, 魏文麗, 吳宗憲: 線性融合語音與手勢辨識作為電子寵物互動遊戲之應用. 台灣網際網路研討會TANET, Taiwan, 2010

林仁俊, 魏文麗, 吳宗憲, 林瑞堂, 朱家德, 許進順: 基於強健性特徵擷取之動態手勢辨識. 全國計算機會議NCS, Taiwan, 2009

林仁俊, 魏文麗, 吳宗憲, 林瑞堂, 朱家德, 許進順: 以卡曼濾波器為基礎之動態手勢特徵重估測技術. 資訊技術應用及管理研討會ITAMC, Taiwan, 2009

林仁俊, 魏文麗, 吳宗憲, 林瑞堂, 朱家德, 許進順: 結合運動估測及膚色偵測之動態手勢偵測技術. 數位生活科技研討會-人本智慧生活科技DLT, Taiwan, 2009

Book Chapter:

Chung-Hsien Wu, Jen-Chun Lin, Wen-Li Wei: Audio-Visual Emotion Recognition Using Semi-Coupled Hidden Markov Model with State-Based Alignment Strategy. Advances in Emotion Recognition, ISBN 978-1-118-13066-7 - John Wiley & Sons., December 2014. 

Technical Report:

Chung-Hsien Wu, Jen-Chun Lin, Wen-Li Wei: An Insight into Dynamic Aspects of Speech Emotional Expression. Newsletter, APSIPA, 2014 

Patent:

C.-H. Wu, J.-C. Lin, W.-L. Wei, C.-T. Chu, R.-T. Lin, and C.-S. Hsu, “Behavior recognition system and method by combining image and speech,” Japan patent 4971413 (2012/4/13).

C.-H. Wu, J.-C. Lin, W.-L. Wei, C.-T. Chu, R.-T. Lin, and C.-S. Hsu, “Behavior recognition system and method by combining image and speech,” United States patent 8487867 (2013/7/16) .

C.-H. Wu, J.-C. Lin, W. -L. Wei, C. -T. Chu, R. -T. Lin, and C.-S. Hsu, “結合影音之行為辨識系統、辨識方法及其電腦程式產品,” Taiwan patent, I423144, Jan 11, 2014.

Work Experiences:

2020. 2 - present: Assistant Research Fellow, IIS, Academia Sinica, Taiwan.

2018. 2 - 2020. 1: Assistant Professor, EE, YZU, Taiwan.

2018. 2 - 2018. 12: Visiting Scholar, hosted by Prof. Hsin-Min Wang, IIS, Academia Sinica, Taiwan.

2014. 8 - 2018. 1: Postdoctoral Fellow, with advisor Prof. Hsin-Min Wang, IIS, Academia Sinica, Taiwan.

Honors and Awards:

2018 APSIPA Sadaoki Furui Prize Paper Award, Paper title: Survey on audiovisual emotion recognition: databases, features, and data fusion strategies.

Postdoctoral Academic Publication Award, Ministry of Science and Technology (MOST), Taiwan, 2017. (106年度博士後研究人員學術著作獎)

Outstanding Postdoctoral Fellow International Conference Travel Grant, provided by the Foundation for the Advancement of Outstanding Scholarship (傑出人才發展基金會 2017)---ACM Multimedia

Academia Sinica Postdoctoral Fellowship, Academia Sinica (2016.1 - 2017. 12)

魏文麗, 林仁俊, 劉庭祿, 田筱榮, 廖弘源: 基於尺度不變特徵轉換之演唱會音訊校準. is awarded with "Best Paper" 台灣網際網路研討會TANET, Taiwan, 2016.

Outstanding Postdoctoral Fellow International Conference Travel Grant, provided by the Foundation for the Advancement of Outstanding Scholarship (傑出人才發展基金會 2016)---ACM Multimedia

Researcher travel grant, supported by Ministry of Science and Technology (科技部), Executive Yuan, Taiwan, (2016)---ICASSP

"Hierarchical Modeling of Temporal Course in Emotional Expression for Speech Emotion Recognition" is awarded with "Most Interesting Paper" in ASMMC (2015)

Researcher travel grant, supported by Ministry of Science and Technology (科技部), Executive Yuan, Taiwan, (2015)---ACM Multimedia

Gold Award, Merry Electroacoustic Thesis Award, Taichung, Taiwan (2014)---美律電聲論文獎 金質獎

Excellent PhD Dissertation Award, IPPR (2014) 

Excellent PhD Dissertation Award, TAAI (2014) 

"Exploiting Psychological Factors for Interaction Style Recognition in Spoken Conversation" on the cover of the March/April IEEE Trans. Audio, Speech and Language Processing (2014), selected by Editor-in-Chief Li Deng

Student travel grant, supported by Ministry of Science and Technology (科技部), Executive Yuan, Taiwan, (2013)---ICASSP

Student travel grant, supported by Ministry of Science and Technology (科技部), Executive Yuan, Taiwan, (2011)---ACII

Student travel grant, supported by Ministry of Science and Technology (科技部), Executive Yuan, Taiwan, (2010)---APSIPA

Invited Talks:

Bridging Realism and Animation: 3D Human Pose and Shape Estimation, National Formosa University (NFU), The College of Electrical and Computer Engineering Seminar (2024/04)

Bridging Realism and Animation: 3D Human Pose and Shape Estimation, National Taiwan University (NTU), Data Science Degree Program (DSDP) (2023/12)

3D Human Pose and Shape Generation In-between Keyframes, Academia Sinica Open House (2023/10)

Estimating 3D Human Pose and Shape from Monocular Video, National Taiwan University (NTU), Data Science Degree Program (DSDP) (2022/12)

人工智慧於虛擬環境的結合與應用, 東吳大學 (AI科普應用教學社群) (2022/06)

Estimating 3D Human Pose and Shape from Monocular Video, ISU, CSIE (2022/01)

How We're Teaching Computers to Achieve Music Video Generation and Video Mashup, 人工智慧X資料科學START UP研討會 (2021/12)

How We're Teaching Computers to Achieve Music Video Generation and Video Mashup, ISU, CSIE (2021/06)

How We're Teaching Computers to Achieve Music Video Generation and Video Mashup, NTNU, CSIE (2021/05)

How We're Teaching Computers to Achieve Music Video Generation and Video Mashup, YZU, EE (2020/05)

Deep Learning for Multimedia Content Analysis, Chung Yuan Christian University, Department of Information and Computer Engineering (2020/3)

Deep Learning for Multimedia Content Analysis, University of Taipei, Department of Computer Science (2019/10)

人工智慧好好玩, AI暑期營隊- 元智大學 (2019/7-8)

Deep Learning for Multimedia Content Analysis, Academia Sinica, Institute of Information Science (2019/07)

Multimedia Content Analysis with Deep Learning, National Tsing Hua University (NTHU), Department of Electrical Engineering (2018/10)

人工智慧遇上多媒體, AI暑期營隊- 元智大學 (2018/7)

人工智慧(AI)及其應用科技技術交流會, 元智大學 (2018/6)

Multimedia Content Analysis with Deep Learning, National Taiwan University of Science and Technology, Department of Computer Science and Information Engineering (2017/11)

Multimedia Content Analysis with Deep Learning, Academia Sinica, Research Center for Information Technology Innovation (CITI) (2017/9)

結合手勢與語音之多模態互動式電子寵物, Workshop of Affective Computing for Interactive Game, 國立嘉義大學 (2010)

Referee for Journal:

Reviewer, Journal of Computer Vision and Image Understanding, 2014~

Reviewer, Journal of the Chinese Institute of Engineers, 2014~

Reviewer, IEEE Transactions on Systems, Man and Cybernetics: Systems, 2015~

Reviewer, IEEE Transactions on Multimedia, 2016~

Reviewer, IEEE Transactions on Audio, Speech and Language Processing, 2016~

Reviewer, Journal of  Image and Vision Computing, 2016~

Reviewer, Journal of  Displays, 2016~

Reviewer, Journal of Visual Communication and Image Representation, 2017~

Reviewer, International Journal of Machine Learning and Cybernetics, 2018~

Reviewer, ACM Transactions on Asian and Low-Resource Language Information Processing, 2018~

Reviewer, APSIPA Transactions on Signal and Information Processing, 2018~

Reviewer, ACM Computing Surveys, 2021~

Referee for Conference:

Reviewer, APSIPA, 2014.

Reviewer, ACII, 2015.

Technical Program Committee (TPC), ICOT, 2015.

Technical Program Committee (TPC), Interspeech, 2016.

Reviewer, APSIPA, 2016.

Reviewer, ICOT, 2016.

Reviewer, ICASSP, 2017.

Reviewer, Interspeech, 2017.

Reviewer, ICASSP, 2018.

Reviewer, Interspeech, 2018.

Technical Program Committee (TPC) member, ACM Multimedia, 2018.

Reviewer, ICASSP, 2019.

Reviewer, ICASSP, 2020.

Reviewer, AAAI, 2021.

Chair of JISE Special Issue, CVGIP, 2021.

Reviewer, AAAI, 2022.

Reviewer, WACV, 2022.

Reviewer, NeurIPS, 2022.

Session Chair and Reviewer, APSIPA, 2022.

Reviewer, AAAI, 2023.

Reviewer, CVPR, 2023.

Reviewer, ICML, 2023.

Reviewer, ICCV, 2023.

Reviewer, NeurIPS, 2023.

Reviewer, AAAI, 2024.

Reviewer, ICML, 2024.

Research Projects:

人類行為動作辨識. 財團法人資訊工業策進會&財團法人成大研究發展基金會 98.03.01~98.12.31

具錯誤感知及互動風格之智慧型對話機制 國科會 101.08.01~104.07.31

滿足獨居老人情緒需求的對話式多媒體互動系統設計-感心話家常 國科會 101.11.01~102.05.31

應用聲音與文字之情感互動於雲端架構之家人關懷－子計畫二：情境感知與個人化音樂推薦, 國科會 102.08.01~105.07.31

表示法學習及其在語音與音樂處理之應用, 科技部 105.08.01~108.07.31

深度學習及其在自動化影音生成之應用, 科技部  107.10.01  ~   109.09.30

透過音樂喚醒照片中的人物, 科技部  110.08.01  ~   113.07.31

基於深度學習的多媒體影音內容理解與生成 (Understanding and generation of audio-visual multimedia content with deep learning), Thematic Research Program, Academia Sinica, 111.01.01  ~   113.12.31.

Contact Information:

Email: jenchunlin@gmail.com

Motto:

莫忘初衷

Never Stop Dreaming