Blinding and blurring the multi-object tracker with adversarial perturbations.

Adversarial attack reveals a potential imperfection in deep models that they are susceptible to being tricked by imperceptible perturbations added to images. Recent deep multi-object trackers combine the functionalities of detection and association, rendering attacks on either the detector or the association component an effective means of deception. Existing attacks focus on increasing the frequency of ID switching, which greatly damages tracking stability, but is not enough to make the tracker completely ineffective. To fully explore the potential of adversarial attacks, we propose Blind-Blur Attack (BBA), a novel attack method based on spatio-temporal motion information to fool multi-object trackers. Specifically, a simple but efficient perturbation generator is trained with the blind-blur loss, simultaneously making the target invisible to the tracker and letting the background be regarded as moving targets. We take TraDeS as our main research tracker, and verify our attack method on other excellent algorithms (i.e., CenterTrack, FairMOT, and ByteTrack) on MOT-Challenge benchmark datasets (i.e., MOT16, MOT17, and MOT20). BBA attack reduced the MOTA of TraDeS and ByteTrack from 69.1 and 80.3 to -238.1 and -357.0, respectively, indicating that it is an efficient method with a high degrees of transferability.

Role of Liquid-Phase Amount in Ceramization of Silicone Rubber Composites and Its Controlling.

The reliable mechanical properties of ceramizable silicone rubber composites during pyrolysis are necessary for their application in the fire-resistant fields. The effects of liquid-phase amount on the mechanical properties of silicone rubber composites are investigated. The results show a positive correlation between the liquid-phase amount and the flexural strength of the residual products pyrolysis below 800 °C. The nano-γ-Al2O3 in the fillers reacts with liquid B2O3 to form aluminum borate above 800 °C, which consumes the liquid phase and strengthens the residual products to a certain extent. Increasing the B2O3 addition and introducing nano-γ-Al2O3 can control the liquid-phase amount in the range of 15% to 30%, which makes the composites have better residual strength and support performance. The residual strength of composites pyrolysis at 500 °C to 1000 °C is higher than 2.50 MPa, and the maximum is up to 18.7 MPa at 1000 °C.

Facile Synthesis of Core-Shell Structured SiO2@Carbon Composite Nanorods for High-Performance Lithium-Ion Batteries.

Recently, SiO2 has attracted wide attention in lithium-ion batteries owing to its high theoretical capacity and low cost. However, the utilization of SiO2 is impeded by the enormous volume expansion and low electric conductivity. Although constructing SiO2/carbon composite can significantly enhance the electrochemical performance, the skillful preparation of the well-defined SiO2/carbon composite is still a remaining challenge. Here, a facile strategy of in situ coating of polydopamine is applied to synthesis of a series of core-shell structured SiO2@carbon composite nanorods with different thicknesses of carbon shells. The carbon shell uniformly coated on the surface of SiO2 nanorods significantly suppresses the volume expansion to some extent, as well as improves the electric conductivity of SiO2. Therefore, the composite nanorods exhibit a remarkable electrochemical performance as the electrode materials of lithium-ion batteries. For instance, a high and stable reversible capacity at a current density of 100 mA g-1 reaches 690 mAh g-1 and a capacity of 344.9 mAh g-1 can be achieved even at the high current density of 1000 mA g-1. In addition, excellent capacity retention reaches 95% over 100 cycles. These SiO2@carbon composite nanorods with decent electrochemical performances hold great potential for applications in lithium-ion batteries.

Improved ion-diffusion performance by engineering an ordered mesoporous shell in hollow carbon nanospheres.

A new kind of hollow carbon nanosphere with an ordered mesoporous shell structure is prepared and demonstrated to have improved performances in practical application areas involving fast ion transport.

Automated glioma detection and segmentation using graphical models.

Glioma detection and segmentation is a challenging task for radiologists and clinicians. The research reported in this paper seeks to develop a better clinical decision support algorithm for clinicians diagnosis. This paper presents a probabilistic method for detection and segmentation between abnormal tissue regions and brain tumour (tumour core and edema) portions from Magnetic Resonance Imaging (MRI). A framework is constructed to learn structure of undirected graphical models that can represent the spatial relationships among variables and apply it to glioma segmentation. Compared with the pixel of image, the superpixel is more consistent with human visual cognition and contains less redundancy, thus, the superpixels are considered as the basic unit of structure learning and glioma segmentation scheme. ℓ1-regularization techniques are applied to learn the appropriate structure for modeling graphical models. Conditional Random Fields (CRF) are used to model the spatial interactions among image superpixel regions and their measurements. A number of features including statistics features, the combined features from the local binary pattern as well as gray level run length, curve features, and fractal features were extracted from each superpixel. The features are then passed by ℓ1-regularization to ensure a robust classification. The proposed method is compared with support vector machine and Fuzzy c-means to classify each superpixel into normal and abnormal tissue. The proposed system is tested for the presence of low grade as well as high grade glioma tumors on images collected from BRATS2013, BRATS2015 data set and Henan Provincial People's Hospital (HNPPH) data set. The experiments performed provides similarity between segmented and truth image up to 91.5% by correlation method.