Current methods for skeleton-based human action recognition usually work with complete skeletons. However, in real scenarios, it is inevitable to capture incomplete or noisy skeletons, which could ...significantly deteriorate the performance of current methods when some informative joints are occluded or disturbed. To improve the robustness of action recognition models, a multi-stream graph convolutional network (GCN) is proposed to explore sufficient discriminative features spreading over all skeleton joints, so that the distributed redundant representation reduces the sensitivity of the action models to non-standard skeletons. Concretely, the backbone GCN is extended by a series of ordered streams which is responsible for learning discriminative features from the joints less activated by preceding streams. Here, the activation degrees of skeleton joints of each GCN stream are measured by the class activation maps (CAM), and only the information from the unactivated joints will be passed to the next stream, by which rich features over all active joints are obtained. Thus, the proposed method is termed richly activated GCN (RA-GCN). Compared to the state-of-the-art (SOTA) methods, the RA-GCN achieves comparable performance on the standard NTU RGB+D 60 and 120 datasets. More crucially, on the synthetic occlusion and jittering datasets, the performance deterioration due to the occluded and disturbed joints can be significantly alleviated by utilizing the proposed RA-GCN.
Renal cell carcinoma (RCC) is the most common form of kidney cancer, with a high recurrence rate and metastasis capacity. Circular RNAs (circRNAs) have been suggested to act as the critical regulator ...in several diseases. This study is designed to investigate the role of circCSNK1G3 on RCC progression. We observed a highly expression of circCSNK1G3 in RCC tissues compared with normal tissues. The aberrantly circCSNK1G3 promoted the tumour growth and metastasis in RCC. In the subsequent mechanism investigation, we discovered that the tumour‐promoting effects of circCSNK1G3 were, at least partly, achieved by up‐regulating miR‐181b. Increased miR‐181b inhibits several tumour suppressor gene, including CYLD, LATS2, NDRG2 and TIMP3. Furthermore, the decreased TIMP3 leads to the enhanced epithelial to mesenchymal transition (EMT) process, thus promoting the cancer metastasis. In conclusion, we identified the oncogenic role of circCSNK1G3 in RCC progression and demonstrated the regulatory role of circCSNK1G3 induced miR‐181b expression, which leads to TIMP3‐mediated EMT process, thus resulting in tumour growth and metastasis in RCC. This study reveals the promise of circCSNK1G3 to be developed as a potential diagnostic and prognostic biomarker in the clinic. And the roles of circCSNK1G3 in cancer research deserve further investigation.
One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art (SOTA) models for ...this task tends to be exceedingly sophisticated and over-parameterized. The low efficiency in model training and inference has increased the validation costs of model architectures in large-scale datasets. To address the above issue, recent advanced separable convolutional layers are embedded into an early fused Multiple Input Branches (MIB) network, constructing an efficient Graph Convolutional Network (GCN) baseline for skeleton-based action recognition. In addition, based on such the baseline, we design a compound scaling strategy to expand the model's width and depth synchronously, and eventually obtain a family of efficient GCN baselines with high accuracies and small amounts of trainable parameters, termed EfficientGCN-Bx, where "x" denotes the scaling coefficient. On two large-scale datasets, i.e. , NTU RGB+D 60 and 120, the proposed EfficientGCN-B4 baseline outperforms other SOTA methods, e.g. , achieving 92.1% accuracy on the cross-subject benchmark of NTU 60 dataset, while being 5.82× smaller and 5.85× faster than MS-G3D, which is one of the SOTA methods. The source code in PyTorch version and the pretrained models are available at https://github.com/yfsong0709/EfficientGCNv1 .
The problem of domain generalization is to learn from multiple training domains, and extract a domain-agnostic model that can then be applied to an unseen domain. Domain generalization (DG) has a ...clear motivation in contexts where there are target domains with distinct characteristics, yet sparse data for training. For example recognition in sketch images, which are distinctly more abstract and rarer than photos. Nevertheless, DG methods have primarily been evaluated on photo-only benchmarks focusing on alleviating the dataset bias where both problems of domain distinctiveness and data sparsity can be minimal. We argue that these benchmarks are overly straightforward, and show that simple deep learning baselines perform surprisingly well on them. In this paper, we make two main contributions: Firstly, we build upon the favorable domain shift-robust properties of deep learning methods, and develop a low-rank parameterized CNN model for end-to-end DG learning. Secondly, we develop a DG benchmark dataset covering photo, sketch, cartoon and painting domains. This is both more practically relevant, and harder (bigger domain shift) than existing benchmarks. The results show that our method outperforms existing DG alternatives, and our dataset provides a more significant DG challenge to drive future research.
The key to solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed ...specifically to learn part-level discriminate feature representations. In this paper, we show that it is possible to cultivate subtle details without the need for overly complicated network designs or training mechanisms - a single loss is all it takes. The main trick lies with how we delve into individual feature channels early on, as opposed to the convention of starting from a consolidated feature map. The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component. The discriminality component forces all feature channels belonging to the same class to be discriminative, through a novel channel-wise attention mechanism. The diversity component additionally constraints channels so that they become mutually exclusive across the spatial dimension. The end result is therefore a set of feature channels, each of which reflects different locally discriminative regions for a specific class. The MC-Loss can be trained end-to-end, without the need for any bounding-box/part annotations, and yields highly discriminative regions during inference. Experimental results show our MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets (CUB-Birds, FGVC-Aircraft, Flowers-102, and Stanford Cars). Ablative studies further demonstrate the superiority of the MC-Loss when compared with other recently proposed general-purpose losses for visual classification, on two different base networks. Codes are available at: https://github.com/dongliangchang/Mutual-Channel-Loss.
Unconventional shale reservoirs have greatly contributed to the recent surge in petroleum production in the United States and are expected to lead the US oil production to a historical high in 2018. ...The complexity of the rocks and fluids in these reservoirs presents a significant challenge to the traditional approaches to the evaluation of geological formations due to the low porosity, permeability, complex lithology and fluid composition. NMR has emerged as the key measurement for evaluating these reservoirs, for quantifying their petrophysical parameters, fluid properties, and determining productivity. Measurement of the T
/T
ratio by 2D NMR has been found to be critical for identifying the fluid composition of kerogen, bitumen, light/heavy oils, gases and brine in these formations. This paper will first provide a brief review of the theories of relaxation, measurement methods, and data inversion techniques and then will discuss several examples of applications of these NMR methods for understanding various aspects of the unconventional reservoirs. At the end, we will briefly discuss a few other topics, which are still in their developmental stages, such as solid state NMR, and their potential applications for shale rock evaluation.
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA ...targets analyzing visual objects from subordinate categories, e.g., species of birds or models of cars. The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem. Capitalizing on advances in deep learning, in recent years we have witnessed remarkable progress in deep learning powered FGIA. In this paper we present a systematic survey of these advances, where we attempt to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas - fine-grained image recognition and fine-grained image retrieval. In addition, we also review other key issues of FGIA, such as publicly available benchmark datasets and related domain-specific applications. We conclude by highlighting several research directions and open problems which need further exploration from the community.
Display omitted
Porous media are ubiquitous in our environment and their application is extremely broad. The common connection between these diverse materials is the importance of the microstructure ...(μm to mm scale) in determining the physical, chemical and biological functions and properties. Magnetic resonance and its imaging modality have been essential for noninvasive characterization of these materials, in the development of catalysts, understanding cement hydration, fluid transport in rocks and soil, geological prospecting, and characterization of tissue properties for medical diagnosis. The past two decades have witnessed significant development of MRPM that couples advances in physics, chemistry and engineering with a broad range of applications. This article will summarize key advances in basic physics and methodology, examine their limitations and envision future R&D directions.
We propose a deep learning approach to free-hand sketch recognition that achieves state-of-the-art performance, significantly surpassing that of humans. Our superior performance is a result of ...modelling and exploiting the unique characteristics of free-hand sketches, i.e., consisting of an ordered set of strokes but lacking visual cues such as colour and texture, being highly iconic and abstract, and exhibiting extremely large appearance variations due to different levels of abstraction and deformation. Specifically, our deep neural network, termed Sketch-a-Net has the following novel components: (i) we propose a network architecture designed for sketch rather than natural photo statistics. (ii) Two novel data augmentation strategies are developed which exploit the unique sketch-domain properties to modify and synthesise sketch training data at multiple abstraction levels. Based on this idea we are able to both significantly increase the volume and diversity of sketches for training, and address the challenge of varying levels of sketching detail commonplace in free-hand sketches. (iii) We explore different network ensemble fusion strategies, including a re-purposed joint Bayesian scheme, to further improve recognition performance. We show that state-of-the-art deep networks specifically engineered for photos of natural objects fail to perform well on sketch recognition, regardless whether they are trained using photos or sketches. Furthermore, through visualising the learned filters, we offer useful insights in to where the superior performance of our network comes from.