add the joinus.PNG in readme

README.md

@@ -67,11 +67,11 @@ PaddleVideo is a toolset for video recognition, action localization, and spatio
           </ul>
         </ul>
       </td>
-      <td> 
+      <td>
           <li>Recognizer1D</li>
           <li>Recognizer2D</li>
           <li>Recognizer3D</li>
-          <li>Localizer</li> 
+          <li>Localizer</li>
         <HR></HR>
         <ul>Backbone
             <li>resnet</li>
@@ -112,15 +112,15 @@ PaddleVideo is a toolset for video recognition, action localization, and spatio
             <li>CenterCrop</li>
             <li>MultiCrop</li>  
           </ul>  
-        </ul> 
+        </ul>
       </td>
       <td>
         <ul><li><b>Batch</b></li>
           <ul>
             <li>Mixup</li>
             <li>Cutmix</li>  
           </ul>  
-        </ul> 
+        </ul>
         <ul><li><b>Image</b></li>
             <ul>
                 <li>Scale</li>
@@ -155,6 +155,16 @@ The chart below illustrates the performance of the video recognition models both
 - PP-TSM improves almost 3.5% Top1 accuracy from standard TSM.
 - all these models described by RED color can be obtained in the [Model Zoo](#model-zoo), and others are Pytorch results.
 
+<a name="Community"></a>
+## Community
+- Scan the QR code below with your Wechat, you can access to official technical exchange group. Look forward to your participation.
+
+<div align="center">
+<img src="./docs/images/joinus.PNG"  width = "200" height = "200" />
+</div>
+
+
+
 ## Tutorials
 
 - [Summarize of video understanding](docs/en/tutorials/summarize.md)

README_cn.md

@@ -62,11 +62,11 @@ PaddleVideo飞桨视频模型开发套件，旨在帮助开发者更好的进行
           </ul>
         </ul>
       </td>
-      <td> 
+      <td>
           <li>Recognizer1D</li>
           <li>Recognizer2D</li>
           <li>Recognizer3D</li>
-          <li>Localizer</li> 
+          <li>Localizer</li>
         <HR></HR>
         <ul>Backbone
             <li>resnet</li>
@@ -107,15 +107,15 @@ PaddleVideo飞桨视频模型开发套件，旨在帮助开发者更好的进行
             <li>CenterCrop</li>
             <li>MultiCrop</li>  
           </ul>  
-        </ul> 
+        </ul>
       </td>
       <td>
         <ul><li><b>Batch</b></li>
           <ul>
             <li>Mixup</li>
             <li>Cutmix</li>  
           </ul>  
-        </ul> 
+        </ul>
         <ul><li><b>Image</b></li>
             <ul>
                 <li>Resize</li>  
@@ -154,6 +154,15 @@ PaddleVideo飞桨视频模型开发套件，旨在帮助开发者更好的进行
 - PPTSM在TSM标准版上精度提升3.5%，预测速度也略有增加。
 - 图中红色描述的模型均可在[模型库](#模型库)中获取
 
+<a name="欢迎加入PaddleVideo技术交流群"></a>
+## 欢迎加入PaddleVideo技术交流群
+- 微信扫描二维码加入官方交流群，获得更高效的问题答疑，与各行各业开发者充分交流，期待您的加入。
+
+<div align="center">
+<img src="./docs/images/joinus.PNG"  width = "200" height = "200" />
+</div>
+
+
 ## 文档教程
 
 ### 入门教程
@@ -167,19 +176,19 @@ PaddleVideo飞桨视频模型开发套件，旨在帮助开发者更好的进行
 - [配置模块设计](docs/zh-CN/config.md)
 - [PPTSM实践](docs/zh-CN/pp-tsm.md)
 - [训练加速方案]() <sup>coming soon</sup>
-- [预测部署](docs/zh-CN/deployment.md) 
+- [预测部署](docs/zh-CN/deployment.md)
 - [自定义开发]() <sup>coming soon</sup>
 
 ### 模型库
 
 - 视频分类 [介绍](docs/zh-CN/model_zoo/README.md#视频分类)
-    - [Attention-LSTM](docs/zh-CN/model_zoo/recognition/attention_lstm.md) 
-    - [TSN](docs/zh-CN/model_zoo/recognition/tsn.md) 
+    - [Attention-LSTM](docs/zh-CN/model_zoo/recognition/attention_lstm.md)
+    - [TSN](docs/zh-CN/model_zoo/recognition/tsn.md)
     - [TSM](docs/zh-CN/model_zoo/recognition/tsm.md)
-    - [PPTSM](docs/zh-CN/model_zoo/recognition/pp-tsm.md) 
+    - [PPTSM](docs/zh-CN/model_zoo/recognition/pp-tsm.md)
     - [SlowFast](docs/zh-CN/model_zoo/recognition/slowfast.md)
 - 动作定位 [介绍](docs/zh-CN/model_zoo/README.md#动作定位)
-    - [BMN](docs/zh-CN/model_zoo/localization/bmn.md) 
+    - [BMN](docs/zh-CN/model_zoo/localization/bmn.md)
 - 时空动作检测：
     - Coming Soon!