Multiple object detection is a key challenge in object detection. Feature extraction and occlusion handling are two key elements in multiple object detection. However, existing methods do not perform well in these aspects during detecting multiple objects. A region-based convolutional network (R-CNN) has achieved a great success in region-based feature extraction, and the part filters in a deformable part-based model (DPM) are very suitable for detecting occluded objects. In this letter, we present a framework that integrates the R-CNN and the DPM for detecting multiple objects. In addition, we propose a new filter based on the dense subgraph discovery algorithm for refining the candidate proposals generated by the DPM. Through combining these two models, we can detect each single object with high accuracy among all objects in an image, especially in the situation that objects are stayed close together. Different from the traditional methods, our framework has the capability to detect multiple objects belonging to various classes rather than only one typical class such as a person or a car. Experimental results on the PASCAL VOC dataset show that our framework achieves better performance compared to using only the R-CNN or the DPM alone in multiple object detection.

Kinetic effects resulting from the two-fluid physics play a crucial role in the fast collisionless reconnection, which is a process to explosively release massive energy stored in magnetic fields in space and astrophysical plasmas. In-situ observations in the Earth's magnetosphere provide solid consistence with theoretical models on the point that kinetic effects are required in the collisionless reconnection. However, all the observations associated with solar wind reconnection have been analyzed in the context of magnetohydrodynamics (MHD) although a lot of solar wind reconnection exhausts have been reported. Because of the absence of kinetic effects and substantial heating, whether the reconnections are still ongoing when they are detected in the solar wind remains unknown. Here, by dual-spacecraft observations, we report a solar wind reconnection with clear Hall magnetic fields. Its corresponding Alfvenic electron outflow jet, derived from the decouple between ions and electrons, is identified, showing direct evidence for kinetic effects that dominate the collisionless reconnection. The turbulence associated with the exhaust is a kind of background solar wind turbulence, implying that the reconnection generated turbulence has not much developed.