Shuyang Sun

TL;DR: This paper presents MMDetection, an object detection toolbox that contains a rich set of object detection and instance segmentation methods as well as related components and modules, and conducts a benchmarking study on different methods, components, and their hyper-parameters.

TL;DR: This study proposes a novel Convolutional Neural Network, called Spindle Net, based on human body region guided multi-stage feature decomposition and tree-structured competitive feature fusion, which is the first time human body structure information is considered in a CNN framework to facilitate feature learning.

TL;DR: Chen et al. as discussed by the authors proposed a Hybrid Task Cascade (HTC) framework, which interweaves the two tasks for a joint multi-stage processing and adopted a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background.

TL;DR: This work proposes a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background.

TL;DR: In this article, the optical flow guided feature (OFF) is proposed to extract spatio-temporal information, especially the temporal information between frames simultaneously, which enables the network to distill temporal information through a fast and robust approach.