Dynamic texture is a part of the natural scene. Dynamic texture segmentation issue is research hotspot in the field of computervision and even robot research area. This paper presents a new dynamic texture recognitio...
详细信息
The project will try to implement the system with the NI Labview DAQ-6211 capture card to make intelligent motor speed control system, expect this architecture to learn new construction methods, and can develop new ap...
详细信息
Instance-level human analysis is common in real-life scenarios and has multiple manifestations, such as human part segmentation, dense pose estimation, human-object interactions, etc. Models need to distinguish differ...
详细信息
ISBN:
(纸本)9781728132945
Instance-level human analysis is common in real-life scenarios and has multiple manifestations, such as human part segmentation, dense pose estimation, human-object interactions, etc. Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance. In this paper, we present an end-to-end pipeline for solving the instance-level human analysis, named Parsing R-CNN. It processes a set of human instances simultaneously through comprehensive considering the characteristics of region-based approach and the appearance of a human, thus allowing representing the details of instances. Parsing R-CNN is very flexible and efficient, which is applicable to many issues in human instance analysis. Our approach outperforms all state-of-the-art methods on CIHP (Crowd Instance-level Human Parsing), MHP v2.0 (Multi-Human Parsing) and DensePose-COCO datasets. Based on the proposed Parsing R-CNN, we reach the 1st place in the COCO 2018 Challenge DensePose Estimation task. Code and models are publicly available.
暂无评论