Confusing Object Detection:A Survey

Confusing object detection(COD),such as glass,mirrors,and camouflaged objects,represents a burgeoning visual detection task centered on pinpointing and distinguishing concealed targets within intricate backgrounds,leveraging deep learning methodologies.Despite garnering increasing attention in computer vision,the focus of most existing works leans toward formulating task-specific solutions rather than delving into in-depth analyses of methodological structures.As of now,there is a notable absence of a comprehensive systematic review that focuses on recently proposed deep learning-based models for these specific tasks.To fill this gap,our study presents a pioneering review that covers both themodels and the publicly available benchmark datasets,while also identifying potential directions for future research in this field.The current dataset primarily focuses on single confusing object detection at the image level,with some studies extending to video-level data.We conduct an in-depth analysis of deep learning architectures,revealing that the current state-of-the-art(SOTA)COD methods demonstrate promising performance in single object detection.We also compile and provide detailed descriptions ofwidely used datasets relevant to these detection tasks.Our endeavor extends to discussing the limitations observed in current methodologies,alongside proposed solutions aimed at enhancing detection accuracy.Additionally,we deliberate on relevant applications and outline future research trajectories,aiming to catalyze advancements in the field of glass,mirror,and camouflaged object detection.

牙膏产品安全评估数据的应用性研究

重点阐述了牙膏用原料规范、食品工业(食品添加剂、调味品、新食品原料)、传统中草药等国内研究数据,以及美国化妆品成分评估、欧盟消费者安全科学委员会、食品添加剂联合专家委员会等国外机构数据在牙膏产品安全评估中的运用,并探讨了我国牙膏用品相关毒理学试验方法的适用性。本文基于国内外现行的标准、规范、指南和评估数据或结论,结合牙膏产品的使用特点,对其安全风险评估数据的应用以及牙膏产品相关的毒理学试验方法加以论述,对产品安全评估的开展具有借鉴意义。

Effects of I-EGR and Pre-Injection on Performance of Gasoline Compression Ignition(GCI)at Low-Load Condition

Gasoline compression ignition(GCI)has been considered as a promising combustion concept to yield ultralow NOX and soot emissions while maintaining high thermal efficiency.However,how to improve the low-load performance becomes an urgent issue to be solved.In this paper,a GCI engine model was built to investigate the effects of internal EGR(i-EGR)and pre-injection on in-cylinder temperature,spatial concentration of mixture and OH radical,combustion and emission characteristics,and the control strategy for improving the combustion performance was further explored.The results showed an obvious expansion of the zone with an equivalence ratio between 0.8∼1.2 is realized by higher pre-injection ratios,and the s decreases with the increase of pre-injection ratio,but increases with the increase of i-EGR ratio.The high overlap among the equivalentmixture zone,the hightemperature zone,and the OH radical-rich zone can be achieved by higher i-EGR ratio coupled with higher preinjection ratio.By increasing the pre-injection ratio,the combustion efficiency increases first and then decreases,also achieves the peak value with a pre-injection ratio of 60%and is unaffected by i-EGR.The emissions of CO,HC,NOX,and soot can also be reduced to low levels by the combination of higher i-EGR ratios and a pre-injection ratio of 60%.

Neighborhood co-occurrence modeling in 3D point cloud segmentation

A significant performance boost has been achieved in point cloud semantic segmentation by utilization of the encoder-decoder architecture and novel convolution operations for point clouds.However,co-occurrence relationships within a local region which can directly influence segmentation results are usually ignored by current works.In this paper,we propose a neighborhood co-occurrence matrix(NCM)to model local co-occurrence relationships in a point cloud.We generate target NCM and prediction NCM from semantic labels and a prediction map respectively.Then,Kullback-Leibler(KL)divergence is used to maximize the similarity between the target and prediction NCMs to learn the co-occurrence relationship.Moreover,for large scenes where the NCMs for a sampled point cloud and the whole scene differ greatly,we introduce a reverse form of KL divergence which can better handle the difference to supervise the prediction NCMs.We integrate our method into an existing backbone and conduct comprehensive experiments on three datasets:Semantic3D for outdoor space segmentation,and S3DIS and ScanNet v2 for indoor scene segmentation.Results indicate that our method can significantly improve upon the backbone and outperform many leading competitors.