diff --git a/fluid/PaddleCV/video/README.md b/fluid/PaddleCV/video/README.md
index 2a7d36dba42350cab000dd8dd8e9a723153ec7a8..fcebe170f70d8e7ada165a2c72b5d105a64ecbaa 100644
--- a/fluid/PaddleCV/video/README.md
+++ b/fluid/PaddleCV/video/README.md
@@ -54,7 +54,7 @@ python train.py --model-name=AttentionCluster
         --valid-interval=1
 ```
 
-视频模型库同时提供了快速训练脚本，脚本位于`scripts/train`目录下，可通过如下命令启动训练
+视频模型库同时提供了快速训练脚本，脚本位于`scripts/train`目录下，可通过如下命令启动训练:
 
 ``` bash
 sh scripts/train/train_attention_cluster.sh
diff --git a/fluid/PaddleCV/video/models/attention_lstm/README.md b/fluid/PaddleCV/video/models/attention_lstm/README.md
index b4345fa1fc1cce3cd03c88d8da7e0bc385098342..5323550a4edafb858a67d949202be82c4bcfbdf2 100644
--- a/fluid/PaddleCV/video/models/attention_lstm/README.md
+++ b/fluid/PaddleCV/video/models/attention_lstm/README.md
@@ -18,7 +18,7 @@
 
 ## 数据准备
 
-AttentionLSTM模型使用2nd-Youtube-8M数据集，关于数据本分请参考[数据说明](../../dataset/README.md)
+AttentionLSTM模型使用2nd-Youtube-8M数据集，关于数据部分请参考[数据说明](../../dataset/README.md)
 
 ## 模型训练