DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution

OccuSeg: Occupancy-aware 3D Instance Segmentation

Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks

Hierarchical Aggregation for 3D Instance Segmentation

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

Bottom-Up and Top-Down Attention for Image Captioningand Visual Question Answering

ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences

为3D模型自动生成文本描述(ShapeCaptioner)

Self attention工作两篇

Stacked Cross Attention for Image-Text Matching

Deep Cross-Modal Projection Learning for Image-Text Matching