Convolutional Neural Network (CNN) based in-loop filter in video coding has demonstrated its superiority in benefiting coding efficiency and enhancing visual quality. In this paper, we develop a lightweight CNN-based in-loop filter for AVS3 encoder. The proposed network consists of several residual blocks with two attention branches, namely Dual Attention Network (DAN). The added channel attention branch and spatial attention branch can take advantage of the correlation between channels and pixels, improving the quality of reconstructed frames. In addition, by analyzing the inter prediction reference structure, we propose a temporal hierarchical deployment strategy to incorporate DAN into AVS3 video encoder. Therefore reconstructed frames with different distortions and referenced levels can be enhanced according to their temporal layer. Experiments prove the effectiveness of our strategy and results show our method achieves up to 6.57% and on average 3.64% BD-rate reduction on Y component under Random Access configuration.