# AII 2023 Notes

1. [link](https://elsa-lab.github.io/AIIWorkshop_5th/?fbclid=IwAR1DjvjdXXMH7tsXikYAvYiTA34ElNuCM5Lhexlh8CojKromRAuBBVbYRRg)
2. [proposal](https://mail.google.com/mail/u/1?ui=2&ik=eb6783fea4&attid=0.1&permmsgid=msg-f:1758317648997781037&th=1866cc95f6d00e2d&view=att&disp=inline)
3. [github](https://github.com/elsa-lab/AIIWorkshop_5th)

## Lectures Day1
* 13:00 李飛飛 Prof.Fei-FeiLi {Stanford, NAE, NAM, AAAS}
* image processing | video | 3DCG | action | medical
* IMAGENET | Perceptual Loss | Bayesian Hierarchical Scene ...
* benchmark | few shot | generative model | RL ...
* [notes](https://hackmd.io/mf1aH2I0S0argO43Gq_Gtg)
* 14:00 徐宏民 Prof.WinstonHsu {NTU, MobileDrive, Nvidia}
* image processing | medical
* SHARP value for face
* XAI | Video search
* [notes](https://hackmd.io/@lmQBF86bT3yd9PIR8LXqGw/Sy5Tp39x3)
* 14:15 陳佩君 Dr.TristaChen {Microsoft, Inventec }
* image processing | audio | medical | manufacturing
* OpenCV | VRAPS: Visual Rhythm-Based Audio Playback System
* preprocess
* [notes](https://hackmd.io/tqIYMb25TIuwWp8F6tLv7Q)
* 14:30 王鈺強 Prof.Yu-ChiangFrankWang {NTU, Nvidia, AIA}
* image processing | 3DCG | video
* Baseline++ | Cross city adaptation of road scene segmenters
* small data | domain adaptation | meta laerning | cross modality
* [notes](https://hackmd.io/MmKAD6hQRpyfmxqOM0YiWA)
* 陳為超
* [notes](https://hackmd.io/03ZdKVTbTVOhuyUNcwEVOg)
* 15:00 孫民 Prof.MinSun {NCTU, Appier}
* 3DCG | security
* Make3d | Adversarial attack on Deep RL
* small data | 3d object detection | federated learning | cross modality
* [notes](https://hackmd.io/R47EfT3dRSmua-2DsVRXjg)

<iframe title="AII Day1-1" allowtransparency="true" height="150" width="100%" style="border: none; min-width: min(100%, 430px);" scrolling="no" data-name="pb-iframe-player" src="https://www.podbean.com/player-v2/?from=embed&i=xmn85-13c8ddd-pb&share=1&download=1&fonts=Arial&skin=1b1b1b&font-color=ffffff&rtl=0&logo_link=episode_page&btn-skin=60a0c8&size=150"></iframe>

* 15:30 吳毅成 Prof.I-ChenWu {NCTU, ICGA, AIA}
* game ai
* connect6 | AWS Deepracer
* game theorem | RL
* [notes](https://hackmd.io/3i4cSQF-TFqNdtmX38wt_w)
* 15:45 賴尚宏 Prof.Shang-HongLai {NTHU}
* image processing| audio processing | statistical learning | medical
* Fusing generic objectness and visual saliency for salient object detection
* xai | small data | generation
* [notes](https://hackmd.io/@lmQBF86bT3yd9PIR8LXqGw/B11NUA5e2)
* 16:00 陳煥宗 Prof.Hwann-TzongChen {NTHU}
* image processing
* Local discriminant embedding and its variants
* object detection | xai
* [notes](https://hackmd.io/i4Dsge3TRoa4tcDaMiIY_w)

* 16:15 王傑智 Prof.BobWang {NTU}
* {computer vision, computer graphics (3D), natural language processing}
* {small data, domain adaptation, transformer}
* [notes](https://hackmd.io/w7UVTMndRqadp6KBROrMbA)
* 16:30 林守德 Prof.Shou-DeLin {National Cheng Kung University}
* | Suggesion System
* {generative model, domain adaptation, reinforcement learning}
* [notes](https://hackmd.io/d9xcVkA5RAGJBQKo0JfH1w)
* 16:45 邱維辰 Prof.Wei-ChenWalonChiu
* {National Cheng Kung University}
* {computer vision, computer graphics (3D), natural language processing}
* {small data, domain adaptation, transformer}
* [notes](https://hackmd.io/qFz9eBviRka_dFYkfPFnBg)
* 17:00 李濬屹 Prof.Chun-YiLee {National Tsing Hua University} {computer vision, computer graphics (3D), self-driving car} {generative model, domain adaptation, reinforcement learning}
* [notes](https://hackmd.io/1oVdVBAJTUmhgM8KBSxlmg)
* 17:15 胡敏君 Prof.Min-ChunHu {National Taiwan Normal University} {computer vision, natural language processing, robotics} {small data, federated learning, transformer}
* [notes](https://hackmd.io/T7M73e82S9OBsWYsKpMuJQ)
* 17:30 謝秉均 Prof.Ping-ChunHsieh {National Chung Cheng University} {computer vision, signal processing, voice conversion} {domain adaptation, generative model, distributed computing}
* [notes](https://hackmd.io/vobH6GNVSYunD51eU2hy6A)
* 17:40 劉育綸 Prof.Yu-LunLiu {National Chung Cheng University} {computer vision, computer graphics (3D), natural language processing} {federated learning, transformer, parallel computing
* [notes](https://hackmd.io/nPby7BwsTkmopIfLKcGYsQ)

<iframe title="AII Day1-2" allowtransparency="true" height="150" width="100%" style="border: none; min-width: min(100%, 430px);" scrolling="no" data-name="pb-iframe-player" src="https://www.podbean.com/player-v2/?i=vwix9-13c8df6-pb&from=pb6admin&share=1&download=1&rtl=0&fonts=Arial&skin=1b1b1b&font-color=ffffff&logo_link=episode_page&btn-skin=60a0c8"></iframe>

## Lectures Day2

* 李宏毅
* 教學、人工音訊
* Unlabeld Data
* [notes](https://hackmd.io/tmkCrphjQvWAcz57oLom3Q)
* 陳緼儂
* NLP
* [notes](https://hackmd.io/pX_TlH7nTzyQ6PfPODs6Nw)
* 楊奕軒
* 音樂資訊研究、人工智慧、機器學習、自動音樂生成
* https://www.ee.ntu.edu.tw/profile1.php?id=1090726
* [notes](https://hackmd.io/ZTQgKI2ZTB65Zn1dh2nWsw)

<iframe title="AII Day2-1" allowtransparency="true" height="150" width="100%" style="border: none; min-width: min(100%, 430px);" scrolling="no" data-name="pb-iframe-player" src="https://www.podbean.com/player-v2/?i=n5f2j-13ca739-pb&from=pb6admin&share=1&download=1&rtl=0&fonts=Arial&skin=1b1b1b&font-color=ffffff&logo_link=episode_page&btn-skin=60a0c8"></iframe>

* 楊明玄
* GOogle MUSE
* [notes](https://hackmd.io/X--XswBgTWOV_9QIGYXy3Q)

這個網頁中參與Speech的講者資料如下：
- 李飛飛教授：斯坦福大學計算機科學系教授，人工智能實驗室主任，從事視覺與語言交互、自然語言理解、機器學習等領域的研究。
- 徐宏民教授：國立臺灣大學電機工程學系教授，臺灣大學AI中心副主任，從事電腦視覺、深度學習、3D重建等領域的研究。
- 陳佩君博士：台灣微軟公司資深研究員，從事生成型人工智能、自然語言處理、知識圖譜等領域的研究。
- 王鈺強教授：國立臺灣大學電機工程學系教授，臺灣大學AI中心主任，從事影像合成、影像轉換、影像增強等領域的研究。
- 陳煥宗教授：國立清華大學資訊工程學系教授，從事多視角影像處理、3D重建、動作捕捉等領域的研究。
- 李宏毅教授：國立臺灣大學電機工程學系副教授，從事語音處理、自然語言處理、深度強化學習等領域的研究。
- 陳緼儂教授：國立臺灣大學資訊管理學系副教授，從事對話界面、多模態分析、廣告推薦等領域的研究。