Search

Generic multiple object tracking aims to recover the trajectories for generic moving objects of the same category. This task relies on the ability of effectively extracting representative features of the target objects. To this end, we propose a novel prototype learning based model, PLGMOT, that can explore the template features of an exemplar object and extend to more objects to acquire their prototype. Their prototype features can be continuously updated during the video, in favor of generalization to all the target objects with different appearances. More importantly, on the public benchmark GMOT-40, our method achieves more than 14% advantage over the state-of-the-art methods, with less than 0.5% of the training data that is not even completely annotated in the form of bounding boxes, thanks to our proposed point-to-box label refinement training algorithm and hierarchical motion-aware association algorithm. • A prototype learning based generic multi-object detector. • A point-to-box label refinement training algorithm. • A hierarchical motion-aware association algorithm for tracking. • Extensive experiments demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we present an approach that utilizes multiple exemplar agent-based motion models (AMMs) to extract motion features (representing crowd behaviors) from the captured crowd trajectories. In the exemplar-based framework, we propose an iterative optimization algorithm to measure the correlation between any exemplar AMM and the trajectory data. It is based on the Extended Kalman Smoother and KL-divergence. In addition, based on the proposed correlation measure, we introduce the novel individual feature, in combination with the holistic feature, to describe crowd motions. Our results show that the proposed features perform well in classifying real-world crowd scenes. [ABSTRACT FROM AUTHOR]

Examines the precipitation in the Nickel-Titanium-Niobium alloy during annealing in China. Use of XRD, TEM, and energy dispersive X-ray on the precipitation process of Ni-Ti-Nb specimens; Occurrence of diffusional transformation on heat treatment; Level of temperature of precipitation.

Semantic segmentation is one of the directions in image research. It aims to obtain the contours of objects of interest, facilitating subsequent engineering tasks such as measurement and feature selection. However, existing segmentation methods still lack precision in class edge, particularly in multi-class mixed region. To this end, we present the Feature Enhancement Network (FE-Net), a novel approach that leverages edge label and pixel-wise weights to enhance segmentation performance in complex backgrounds. Firstly, we propose a Smart Edge Head (SE-Head) to process shallow-level information from the backbone network. It is combined with the FCN-Head and SepASPP-Head, located at deeper layers, to form a transitional structure where the loss weights gradually transition from edge labels to semantic labels and a mixed loss is also designed to support this structure. Additionally, we propose a pixel-wise weight evaluation method, a pixel-wise weight block, and a feature enhancement loss to improve training effectiveness in multi-class regions. FE-Net achieves significant performance improvements over baselines on publicly datasets Pascal VOC2012, SBD, and ATR, with best mIoU enhancements of 15.19%, 1.42% and 3.51%, respectively. Furthermore, experiments conducted on Pole&Hole match dataset from our laboratory environment demonstrate the superior effectiveness of FE-Net in segmenting defined key pixels. [ABSTRACT FROM AUTHOR]

Domain Generalization (DG) aims to generalize a model trained on multiple source domains to an unseen target domain. The source domains always require precise annotations, which can be cumbersome or even infeasible to obtain in practice due to the vast amount of data involved. Web data, namely web-crawled images, offers an opportunity to access large amounts of unlabeled images with rich style information, which can be leveraged to improve DG. From this perspective, we introduce a novel paradigm of DG, termed as Semi-Supervised Domain Generalization (SSDG) , to explore how the labeled and unlabeled source domains can interact, and establish two settings, including the close-set and open-set SSDG. The close-set SSDG is based on existing public DG datasets, while the open-set SSDG, built on the newly-collected web-crawled datasets, presents a novel yet realistic challenge that pushes the limits of current technologies. A natural approach of SSDG is to transfer knowledge from labeled data to unlabeled data via pseudo labeling, and train the model on both labeled and pseudo-labeled data for generalization. Since there are conflicting goals between domain-oriented pseudo labeling and out-of-domain generalization, we develop a pseudo labeling phase and a generalization phase independently for SSDG. Unfortunately, due to the large domain gap, the pseudo labels provided in the pseudo labeling phase inevitably contain noise, which has negative affect on the subsequent generalization phase. Therefore, to improve the quality of pseudo labels and further enhance generalizability, we propose a cyclic learning framework to encourage a positive feedback between these two phases, utilizing an evolving intermediate domain that bridges the labeled and unlabeled domains in a curriculum learning manner. Extensive experiments are conducted to validate the effectiveness of our method. It is worth highlighting that web-crawled images can promote domain generalization as demonstrated by the experimental results. • Developing the close-set and open-set semi-supervised domain generalization (SSDG). • Constructing two web-crawled datasets are for the open-set SSDG. • Establishing strong baselines for SSDG using existing deep learning methods. • Proposing a framework with evolving intermediate domain for SSDG. • The framework outperforms the strong baselines in both close-set and open-set SSDG. [ABSTRACT FROM AUTHOR]

Sulfated derivatives of galactomannan from locust bean gum (LBG) with the degree of substitution (DS) of 0.34–1.07 were synthesized using chlorosulfonic acid/pyridine (CSA/Py) method. Box–Behnken design (BBD) of response surface methodology (RSM) was employed to optimize the reaction conditions. Results of FT-IR and X-ray photoelectron spectroscopy (XPS) indicated that SO 3 H groups were widely present in sulfated LBG (SLBG). 13 C NMR result revealed that sulfation had occurred and C-6 substitution was predominant in SLBG. All sulfated samples showed a decrease in M w and more broad molar mass distribution in size exclusion chromatography combined with laser light scattering (SEC-LLS) analysis. Results of M W – 〈 S 2 〉 z 1 / 2 showed a decrease in fractal dimension ( d f ) value. Laser light scattering results also showed a conformation transition from a compact chain conformation of branched clusters to a random coil conformation of SLBG. Compared to LBG and SLBG with low DS and molecular weight, SLBG 2 exhibited an internal structure of random coil with a DS of 1.07. DS and molecular weight had great influence on its conformation in aqueous solution. Our results confirmed that the degradation of polysaccharide and SO 3 H groups improved significantly the stiffness of the chains due to the electrostatic effect. [ABSTRACT FROM AUTHOR]

With NH3·H2O, NH3·H2O-NH4HCO3 buffer solution and NaOH solution as coprecipitation agents, NiO–ZrO2, anode powder of solid oxide fuel cell, was synthesized by coprecipitation methods. Composition accuracy was analyzed by comparing the original composition with the mass of the eventually obtained powder. It was shown that cubic NiO and cubic YSZ with a cascade powder distribution were obtained after the powder was calcined for 1h at different temperatures. Composition analysis of the powder synthesized with NH3·H2O as coprecipitation agent showed that NiO–YSZ powder greatly deviated from the original composition due to the loss of Ni2+ in the form of [Ni(NH3)4]2+. When NH3·H2O–NH4HCO3 buffer solution was used, productive output of nickel was increased. The loss of nickel can be totally avoided and better control of the powder composition could be realized when NaOH was used as coprecipitation agent. [Copyright &y& Elsevier]

• Deep compression of these deterministic models has been proposed in last few years to reduce the number of connections and nodes, while remaining the classification accuracy of these models. This paper is the first attempt to combine deep probabilistic graphical networks (PGNs) and deep compression techniques together to derive sparse versions of the deep probabilistic models. • The developed pruning approach is a layer-by-layer and pre-pruning one. That is, the final PGNs grow in a layer-by-layer and compressed manner. It is very efficient in redundancy reduction. The whole pruning only takes a few seconds to conduct, while other complex methods take much more time to select sparse architectures or conduct model compression, such as regularization and low-rank factorization approaches. These model compression techniques are more time-consuming compared with pruning due to the complexity of regularization and factorization. • The correctness and efficiency of the proposed compression approach are evaluated by a number of PGNs with different datasets. It can be used to compress trained PGNs to achieve a lightweight network which can be embedded in on-chip memory of small mobile devices. It is also flexible to implement and can be generalized to other deep PGNs. Probabilistic Graphical Models (PGMs) are important and active research areas in machine learning and artificial intelligence. The well-known representatives of PGMs include Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Deep Boltzmann Machines (DBMs), and their variants. These PGMs open a new dimension of machine learning and directly lead to the revival of deep learning since 2006. Compared with deep deterministic models, such as deep convolutional neural networks (CNNs), PGMs are more flexible, robust and powerful for both unsupervised and supervised learning problems. As the generative models on the one hand, PGMs have the good capability of generating samples after extracting informative features of input data. On the other hand, they also can provide a good initialization of hierarchical structures for supervised learning. The PGMs with deep structures are called deep Probabilistic Graphical Networks (PGNs) due to their hierarchical structures and close relationships with deep neural networks. There are a large number of CNN-based deep deterministic networks proposed for computer vision tasks. However, these deep deterministic models are shown to possess extremely large number of model parameters, and have serious redundancy problems. Therefore, deep compression of these deterministic models have been proposed in the last few years to reduce the number of connections and nodes, while preserving the classification accuracy. This paper is the first attempt to combine deep PGNs and deep compression techniques together to derive sparse versions of the deep probabilistic models. We firstly examine that whether deep PGNs have serious problem of parameter redundancy, and compress them if necessary. From the experimental results on MNIST, Fashion-MNIST and CIFAR-10 dataset, deep PGNs can be compressed by at least 50% of their parameters through a deep pruning and retraining approach, while keeping their capabilities in both generative and discriminative tasks. [ABSTRACT FROM AUTHOR]