The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.I...The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.展开更多
This research,grounded in the theory of discourse intonation,investigates Chinese EFL learners' intonation features in interactive context.Its research findings reveal that Chinese EFL learners differ from British...This research,grounded in the theory of discourse intonation,investigates Chinese EFL learners' intonation features in interactive context.Its research findings reveal that Chinese EFL learners differ from British native speakers in their application of tone units,prominence selection and tone choice.It further points out that these intonation features are caused on the one hand by Chinese EFL learners' relatively low English proficiency level and on the other hand by their lack of awareness of the communicative and discourse function of intonation.Based on these findings,this research proposes that a discourse-based awareness-raising approach to intonation teaching in the input-poor Chinese EFL context might be of pedagogical necessity and effectiveness.展开更多
基金National Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)University Superior Discipline Construction Project of Jiangsu Province。
文摘The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.
文摘This research,grounded in the theory of discourse intonation,investigates Chinese EFL learners' intonation features in interactive context.Its research findings reveal that Chinese EFL learners differ from British native speakers in their application of tone units,prominence selection and tone choice.It further points out that these intonation features are caused on the one hand by Chinese EFL learners' relatively low English proficiency level and on the other hand by their lack of awareness of the communicative and discourse function of intonation.Based on these findings,this research proposes that a discourse-based awareness-raising approach to intonation teaching in the input-poor Chinese EFL context might be of pedagogical necessity and effectiveness.
