Add talk from Anita Chen

Author: dontcallmedom

Diff for: _data/talks.json

@@ -421,12 +421,16 @@
         "duration": "06:00",
       "added": "2020-08-26"
       },
-      "ac_live-encoding": {
+      "ac_encoding": {
         "title": "AI-Powered Per-Scene Live Encoding ",
         "author": "Anita Chen",
         "affiliation": "Fraunhofer FOKUS",
         "bio": "Project Manager at Fraunhofer FOKUS",
-        "abstract": "This presentation will provide an overview of utilizing machine learning methods in automating per-title encoding for Video on Demand (VoD) and live streaming in order to improve the viewing experience. It will also address the behaviors of various regression models that can predict encoding ladders in a browser in real-time, including a future outlook in terms of optimization."
+        "abstract": "This presentation will provide an overview of utilizing machine learning methods in automating per-title encoding for Video on Demand (VoD) and live streaming in order to improve the viewing experience. It will also address the behaviors of various regression models that can predict encoding ladders in a browser in real-time, including a future outlook in terms of optimization.",
+        "duration": "9:13",
+        "thumbnail": "https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckf5026qg98gu0731ugc6eaqb/thumbs/thumb-001.jpeg",
+        "video": "https://app.streamfizz.live/embed/ckf5026qg98gu0731ugc6eaqb",
+        "added": "2020-09-16"
       },
       "zc_expression": {
         "title": "A virtual character web meeting with expression enhance power by machine learning",

Diff for: _includes/related-issues/ac_encoding.html

@@ -0,0 +1 @@
+<div class=related><p>Related conversations on <a href='https://github.com/w3c/machine-learning-workshop/issues'>GitHub</a>:</p><ul><ul><li><a href='https://github.com/w3c/machine-learning-workshop/issues/new'>Open a new issue</a></li></ul></ul></div>

Diff for: _includes/talk-list3.html

@@ -1,7 +1,7 @@
 <div class="talks"><details class=talk><summary><div class="grid"><a href="talks/fast_client_side_ml_with_tensorflow_js.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdobzb8u76t007727v6c7xr0/thumbs/thumb-003.jpeg" alt="Watch Fast client-side ML with TensorFlow.js" width=200 class="tn"></a><a href="talks/fast_client_side_ml_with_tensorflow_js.html">Fast client-side ML with TensorFlow.js</a><span class="summary"> by Ann Yuan (Google) - 8 min <span></span></span></div></summary><p><a href="talks/fast_client_side_ml_with_tensorflow_js.html">8 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Ann Yuan (Google)</dd><dd>    Software Engineer for TensorFlow.js</dd><dt>Abstract</dt><dd>    This talk will present how TensorFlow.js enables ML execution in the browser utilizing web technologies such as WebGL for GPU acceleration, Web Assembly, and technical design considerations.</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/onnx_js_a_javascript_library_to_run_onnx_models_in_browsers_and_node_js.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdobtrbx74rf0772xh98cjs1/thumbs/thumb-004.jpeg" alt="Watch ONNX.js - A Javascript library to run ONNX models in browsers and Node.js" width=200 class="tn"></a><a href="talks/onnx_js_a_javascript_library_to_run_onnx_models_in_browsers_and_node_js.html">ONNX.js - A Javascript library to run ONNX models in browsers and Node.js</a><span class="summary"> by Emma Ning (Microsoft) - 14 min <span></span></span></div></summary><p><a href="talks/onnx_js_a_javascript_library_to_run_onnx_models_in_browsers_and_node_js.html">14 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Emma Ning (Microsoft)</dd><dd>    Emma Ning is a senior Product manager in AI Framework team under Microsoft Cloud + AI Group, focusing on AI model operationalization and acceleration with ONNX/ONNX Runtime for open and interoperable AI. She has more than five years of product experience in search engine taking advantage of machine learning techniques and spent more than three years exploring AI adoption among various businesses. She is passionate about bringing AI solutions to solve business problems as well as enhance product experience.</dd><dt>Abstract</dt><dd>    ONNX.js is a Javascript library for running ONNX models on browsers and on Node.js, on both CPU and GPU. Thanks to ONNX interoperability, it’s also compatible with Tensorflow and Pytroch. For running on CPU, ONNX.js adopts WebAssembly to execute the model at near-native speed and utilizes Web Workers to provide a “multi-threaded” environment, achieving very promising performance gains. For running on GPU, ONNX.js takes advantage of WebGL which is a popular standard for accessing GPU capabilities. By reducing data transfer between CPU and GPU as well as GPU processing cycles, ONNX.js further push the performance to the maximum.</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/paddle_js_machine_learning_for_the_web.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdor4rqzc9ix0772t2z9zo80/thumbs/thumb-001.jpeg" alt="Watch Paddle.js - Machine Learning for the Web" width=200 class="tn"></a><a href="talks/paddle_js_machine_learning_for_the_web.html">Paddle.js - Machine Learning for the Web</a><span class="summary"> by Ping Wu (Baidu) - 5 min <span></span></span></div></summary><p><a href="talks/paddle_js_machine_learning_for_the_web.html">5 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Ping Wu (Baidu)</dd><dd>    Architect at Baidu, Lead of Paddle.js</dd><dt>Abstract</dt><dd>    Paddle.js is a high-performance JavaScript DL framework for diverse web runtimes, which helps building a PaddlePaddle ecosystem with web community. This talk will introduce Paddle.js design principle, implementation, use scenario and future work the project would like to explore. </dd></dl></details>
-<details class=talk><summary><div class="grid"><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckf25pb70u0xk07316xa68ovz/thumbs/thumb-005.jpeg" alt="Watch ml5.js: Friendly Machine Learning for the Web" width=200 class="tn"></a><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html">ml5.js: Friendly Machine Learning for the Web</a><span class="summary"> by Yining Shi (New York University, RunwayML) - 8 min <span></span></span></div><span class=added>Added on 2020-09-14</span></summary><p><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html">8 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Yining Shi (New York University, RunwayML)</dd><dd>ml5.js contributor and adjunct professor at Interactive Telecommunications Program (ITP)</dd></dl></details>
+<details class=talk><summary><div class="grid"><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckf25pb70u0xk07316xa68ovz/thumbs/thumb-001.jpeg" alt="Watch ml5.js: Friendly Machine Learning for the Web" width=200 class="tn"></a><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html">ml5.js: Friendly Machine Learning for the Web</a><span class="summary"> by Yining Shi (New York University, RunwayML) - 8 min <span></span></span></div><span class=added>Added on 2020-09-14</span></summary><p><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html">8 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Yining Shi (New York University, RunwayML)</dd><dd>ml5.js contributor and adjunct professor at Interactive Telecommunications Program (ITP)</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/pipcook_a_front_end_oriented_dl_framework.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckev83mzuaq7g073183lhuwje/thumbs/thumb-001.jpeg" alt="Watch Pipcook, a front-end oriented DL framework" width=200 class="tn"></a><a href="talks/pipcook_a_front_end_oriented_dl_framework.html">Pipcook, a front-end oriented DL framework</a><span class="summary"> by Wenhe Eric Li (Alibaba) - 10 min <span></span></span></div><span class=added>Added on 2020-09-09</span></summary><p><a href="talks/pipcook_a_front_end_oriented_dl_framework.html">10 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Wenhe Eric Li (Alibaba)</dd><dd>ML/DL on web, contributor of ML5 & tfjs, memebr of pipcook, SDE @ Alibaba</dd><dt>Abstract</dt><dd>We are going to present a front-end oriented platform based on TensorFlow.js. We will cover what is pipcook, the design philosophy, as well as some examples & use cases in our internal community. Apart from that, we will show a brandy new solution to bridge the flourish python DL/ML environment and javascript runtime in both browsers and nodejs.</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/machine_learning_on_the_web_for_content_filtering_applications.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdo73x214sg70772y38lkixw/thumbs/thumb-003.jpeg" alt="Watch Machine Learning on the Web for content filtering applications" width=200 class="tn"></a><a href="talks/machine_learning_on_the_web_for_content_filtering_applications.html">Machine Learning on the Web for content filtering applications</a><span class="summary"> by Oleksandr Paraska (eyeo) - 11 min <span></span></span></div></summary><p><a href="talks/machine_learning_on_the_web_for_content_filtering_applications.html">11 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Oleksandr Paraska (eyeo)</dd><dd>    eyeo GmbH is the company behind Adblock plus</dd><dt>Abstract</dt><dd>    eyeo GmbH has recently deployed tensorflow.js into their product for better ad blocking functionality and has identified gaps in what the WebNN draft covers, e.g. using the DOM as input data, or primitives needed for Graph Convolutional Networks. The talk will present the relevant use case and give indications on how can it be best supported by the new standard.</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/exploring_unsupervised_image_segmentation_results.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdor4gvwc9bh0772h8h13fs2/thumbs/thumb-001.jpeg" alt="Watch Exploring unsupervised image segmentation results" width=200 class="tn"></a><a href="talks/exploring_unsupervised_image_segmentation_results.html">Exploring unsupervised image segmentation results</a><span class="summary"> by Piotr Migdal & Bartłomiej Olechno - 6 min <span></span></span></div></summary><p><a href="talks/exploring_unsupervised_image_segmentation_results.html">6 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Piotr Migdal & Bartłomiej Olechno</dd><dt>Abstract</dt><dd>    This talk will present the usage of web-based tools to interactively explore machine learning models, with the example of an interactive D3.js-based visualization to see the results of unsupervised image segmentation.</dd></dl></details>

Diff for: _includes/talk-list3_zh.html

@@ -1,7 +1,7 @@
 <div class="talks"><details class=talk><summary><div class="grid"><a href="talks/fast_client_side_ml_with_tensorflow_js.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdobzb8u76t007727v6c7xr0/thumbs/thumb-003.jpeg" alt="Watch 使用TensorFlow.js的快速客户端机器学习" width=200 class="tn"></a><a href="talks/fast_client_side_ml_with_tensorflow_js.html">使用TensorFlow.js的快速客户端机器学习</a><span class="summary"> by Ann Yuan (谷歌) - 8 min <span></span></span></div></summary><p><a href="talks/fast_client_side_ml_with_tensorflow_js.html">8 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Ann Yuan (谷歌)</dd><dd>TensorFlow.js的软件工程师</dd><dt>Abstract</dt><dd>本演讲将介绍TensorFlow.js如何利用Web技术（例如用于GPU加速的WebGL，Web汇编和技术设计注意事项）在浏览器中启用机器学习。</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/onnx_js_a_javascript_library_to_run_onnx_models_in_browsers_and_node_js.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdobtrbx74rf0772xh98cjs1/thumbs/thumb-004.jpeg" alt="Watch ONNX.js - 在浏览器和Node.js中运行ONNX模型的Javascript库" width=200 class="tn"></a><a href="talks/onnx_js_a_javascript_library_to_run_onnx_models_in_browsers_and_node_js.html">ONNX.js - 在浏览器和Node.js中运行ONNX模型的Javascript库</a><span class="summary"> by Emma Ning (微软) - 14 min <span></span></span></div></summary><p><a href="talks/onnx_js_a_javascript_library_to_run_onnx_models_in_browsers_and_node_js.html">14 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Emma Ning (微软)</dd><dd>Emma Ning 是Microsoft Cloud + AI Group旗下AI Framework团队的高级产品经理，致力于通过开放式和可互操作AI的ONNX / ONNX Runtime进行AI模型的操作和加速。她在机器学习技术方面拥有超过五年的搜索引擎产品经验，并且在探索各种业务中采用AI方面花费了超过三年的时间。她热衷于提供AI解决方案来解决业务问题并增强产品体验。</dd><dt>Abstract</dt><dd>ONNX.js是一个Javascript库，用于在CPU和GPU上的浏览器和Node.js上运行ONNX模型。得益于ONNX的互操作性，它还与Tensorflow和Pytroch兼容。为了在CPU上运行，ONNX.js采用WebAssembly来以接近本机的速度执行模型，并利用Web Workers提供“多线程”环境，从而获得非常可观的性能提升。为了在GPU上运行，ONNX.js利用WebGL的优势，WebGL是访问GPU功能的流行标准。通过减少CPU和GPU之间的数据传输以及GPU处理周期，ONNX.js进一步提高了性能。</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/paddle_js_machine_learning_for_the_web.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdor4rqzc9ix0772t2z9zo80/thumbs/thumb-001.jpeg" alt="Watch Paddle.js - Web 机器学习" width=200 class="tn"></a><a href="talks/paddle_js_machine_learning_for_the_web.html">Paddle.js - Web 机器学习</a><span class="summary"> by Ping Wu (百度) - 5 min <span></span></span></div></summary><p><a href="talks/paddle_js_machine_learning_for_the_web.html">5 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Ping Wu (百度)</dd><dd>百度架构师，Paddle.js负责人</dd><dt>Abstract</dt><dd>Paddle.js是适用于各种Web运行时的高性能JavaScript DL框架，它有助于通过Web社区构建PaddlePaddle生态系统。本演讲将介绍Paddle.js的设计原理，实现，使用场景以及该项目想要探索的未来工作。</dd></dl></details>
-<details class=talk><summary><div class="grid"><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckf25pb70u0xk07316xa68ovz/thumbs/thumb-005.jpeg" alt="Watch ml5.js: Friendly Machine Learning for the Web" width=200 class="tn"></a><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html">ml5.js: Friendly Machine Learning for the Web</a><span class="summary"> by Yining Shi (纽约大学) - 8 min <span></span></span></div><span class=added>Added on 2020-09-14</span></summary><p><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html">8 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Yining Shi (纽约大学)</dd><dd>ml5.js贡献者和交互电信项目(ITP)的兼职教授</dd></dl></details>
+<details class=talk><summary><div class="grid"><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckf25pb70u0xk07316xa68ovz/thumbs/thumb-001.jpeg" alt="Watch ml5.js: Friendly Machine Learning for the Web" width=200 class="tn"></a><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html">ml5.js: Friendly Machine Learning for the Web</a><span class="summary"> by Yining Shi (纽约大学) - 8 min <span></span></span></div><span class=added>Added on 2020-09-14</span></summary><p><a href="talks/ml5_js_friendly_machine_learning_for_the_web.html">8 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Yining Shi (纽约大学)</dd><dd>ml5.js贡献者和交互电信项目(ITP)的兼职教授</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/pipcook_a_front_end_oriented_dl_framework.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckev83mzuaq7g073183lhuwje/thumbs/thumb-001.jpeg" alt="Watch Pipcook, a front-end oriented DL framework" width=200 class="tn"></a><a href="talks/pipcook_a_front_end_oriented_dl_framework.html">Pipcook, a front-end oriented DL framework</a><span class="summary"> by Wenhe Eric Li (Alibaba) - 10 min <span></span></span></div><span class=added>Added on 2020-09-09</span></summary><p><a href="talks/pipcook_a_front_end_oriented_dl_framework.html">10 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Wenhe Eric Li (Alibaba)</dd><dd>ML/DL on web, contributor of ML5 & tfjs, memebr of pipcook, SDE @ Alibaba</dd><dt>Abstract</dt><dd>We are going to present a front-end oriented platform based on TensorFlow.js. We will cover what is pipcook, the design philosophy, as well as some examples & use cases in our internal community. Apart from that, we will show a brandy new solution to bridge the flourish python DL/ML environment and javascript runtime in both browsers and nodejs.</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/machine_learning_on_the_web_for_content_filtering_applications.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdo73x214sg70772y38lkixw/thumbs/thumb-003.jpeg" alt="Watch Web上的机器学习，用于内容过滤应用程序" width=200 class="tn"></a><a href="talks/machine_learning_on_the_web_for_content_filtering_applications.html">Web上的机器学习，用于内容过滤应用程序</a><span class="summary"> by Oleksandr Paraska (eyeo) - 11 min <span></span></span></div></summary><p><a href="talks/machine_learning_on_the_web_for_content_filtering_applications.html">11 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Oleksandr Paraska (eyeo)</dd><dd>eyeo GmbH是Adblock plus的公司</dd><dt>Abstract</dt><dd>eyeo GmbH 最近已将tensorflow.js部署到其产品中，以提供更好的广告拦截功能，并确定了WebNN草案涵盖的漏洞，例如使用DOM作为图卷积网络所需的输入数据或图元。演讲将介绍相关的用例，并说明如何通过新标准更好地支持它。</dd></dl></details>
 <details class=talk><summary><div class="grid"><a href="talks/exploring_unsupervised_image_segmentation_results.html"><img src="https://cjx1uopmt0m4q0667xmnrqpk.blob.core.windows.net/ckdor4gvwc9bh0772h8h13fs2/thumbs/thumb-001.jpeg" alt="Watch 探索无监督图像分割结果" width=200 class="tn"></a><a href="talks/exploring_unsupervised_image_segmentation_results.html">探索无监督图像分割结果</a><span class="summary"> by Piotr Migdal & Bartłomiej Olechno - 6 min <span></span></span></div></summary><p><a href="talks/exploring_unsupervised_image_segmentation_results.html">6 minutes presentation</a></p><dl><dt>Speaker</dt><dd>Piotr Migdal & Bartłomiej Olechno</dd><dt>Abstract</dt><dd>本演讲将以基于Web的工具交互式地探索机器学习模型为例，并以基于D3.js的交互式可视化为例，展示无监督图像分割的结果。</dd></dl></details>