@article{Liu_Han_Liu_Zwicker_2019, title={Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-Based Sequence to Sequence Network}, volume={33}, url={https://ojs.aaai.org/index.php/AAAI/article/view/4903}, DOI={10.1609/aaai.v33i01.33018778}, abstractNote={<p>Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to capture fine-grained contextual information in hand-crafted or explicit manners, such as the correlation between different areas in a local region, which limits the discriminative ability of learned features. To resolve this issue, we propose a novel deep learning model for 3D point clouds, named Point2Sequence, to learn 3D shape features by capturing fine-grained contextual information in a novel implicit way. Point2Sequence employs a novel sequence learning model for point clouds to capture the correlations by aggregating multi-scale areas of each local region with attention. Specifically, Point2Sequence first learns the feature of each area scale in a local region. Then, it captures the correlation between area scales in the process of aggregating all area scales using a recurrent neural network (RNN) based encoder-decoder structure, where an attention mechanism is proposed to highlight the importance of different area scales. Experimental results show that Point2Sequence achieves state-of-the-art performance in shape classification and segmentation tasks.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Liu, Xinhai and Han, Zhizhong and Liu, Yu-Shen and Zwicker, Matthias}, year={2019}, month={Jul.}, pages={8778-8785} }