Although it is well believed for years that modeling relations between objects would help object recognition, there has not been evidence that the idea is working in the deep learning era. All state-of-the-art object detection systems still rely on recognizing object instances individually, without exploiting their relations during learning.This work proposes an object relation module. It processes a set of objects simultaneously through interaction between their appearance feature and geometry, thus allowing modeling of their relations. It is lightweight and in-place. It does not require additional supervision and is easy to embed in existing networks. It is shown effective on improving object recognition and duplicate removal steps in the modern object detection pipeline. It verifies the efficacy of modeling object relations in CNN based detection. It gives rise to the first fully end-to-end object detector. Code is available at https://github.com/msracver/ Relation-Networks-for-Object-Detection.

An efficient palladium-catalyzed Heck-type reaction of fluoroalkyl halides, including perfluoroalkyl bromides, trifluoromethyl iodides, and difluoroalkyl bromides, has been developed. The reaction proceeds under mild reaction conditions with high efficiency and broad substrate scope, and provides a general and straightforward access to fluoroalkylated alkenes which are of interest in life and material sciences.

A nickel-catalyzed three-component reaction for the synthesis of difluoroalkylated compounds through tandem difluoroalkylation-arylation of enamides has been developed. The reaction tolerates a variety of arylboronic acids and widely available difluoroalkyl bromides, and even the relatively inert substrate chlorodifluoroacetate. The significant advantages of this protocol are the low-cost nickel catalyst, synthetic convenience, excellent functional-group compatibility and high reaction efficiency.