Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that ...involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in an image. When asked “What vehicle is the person riding?”, computers will need to identify the objects in an image as well as the relationships
riding(man, carriage)
and
pulling(horse, carriage)
to answer correctly that “the person is riding a horse-drawn carriage.” In this paper, we present the Visual Genome dataset to enable the modeling of such relationships. We collect dense annotations of objects, attributes, and relationships within each image to learn these models. Specifically, our dataset contains over 108K images where each image has an average of
35
objects,
26
attributes, and
21
pairwise relationships between objects. We canonicalize the objects, attributes, relationships, and noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations represent the densest and largest dataset of image descriptions, objects, attributes, relationships, and question answer pairs.
•In this work, novel nickel-organic framework nanosheets comprising Ni2+ and an organic ligand of hexamethylenetetramine (Ni-MOFs-t, where t is the solvothermal temperature) are synthesized by a ...facile one-pot solvothermal method.•The self-supported Ni-MOFs-120 nanosheets on Ni foam (Ni-MOFs-120/NF) exhibits high electrocatalytic activity toward MOR with a low potential of 1.44 V (vs RHE) at a current density of 100 mA cm−2due to structural modulation of Ni-DMAP-t.•Electrochemical measurements have also shown that the Ni-MOFs-120/NF has superior MOR stability and catalytic kinetics, which is better than currently reported Ni-based catalysts.•Under the catalysis of Ni-MOFs-120/NF, the selective conversion of methanol to formic acid was obtained.
To improve the reaction rate and the yield of high value-added product (formic acid) of electrocatalytic methanol oxidation reaction (MOR), the development of high-performance electrocatalyst is essential. In this work, novel nickel-organic framework nanosheets comprising Ni2+ and an organic ligand of hexamethylenetetramine (Ni-MOFs-t, where t is the solvothermal temperature) are synthesized by a facile one-pot solvothermal method. By structural regulation of Ni-DMAP-t, the self-supported Ni-MOFs-120 nanosheets on Ni foam (Ni-MOFs-120/NF) exhibits high electrocatalytic activity toward MOR with a low potential of 1.44 V (vs RHE) at a current density of 100 mA cm−2. Electrochemical measurement has also demonstrated that the Ni-MOFs-120/NF possesses superior stability for MOR. Particularly, the selectively conversion of methanol to formic acid was achieved under the catalysis of Ni-MOFs-120/NF. This work offers a new high-performance electrocatalytic material for the conversion of methanol to high value-added formic aci
Abstract
With the rapid development of blockchain technology, the financial and monetary (FM) blockchain fields also began to collide. Therefore, this study aims to explore the relationship between ...the two fields and efficiently evaluate the security of financial information. Firstly, this study introduces the theoretical basis of blockchain in the dynamic linkage mechanism of FM and gives the overall framework of digital currency based on blockchain. Meanwhile, the relationship between blockchain and digital finance is empirically analyzed and designed. Secondly, the framework of financial information service security assessment (ISSA) is created using blockchain technology, and the frame of security risk evaluation is verified by taking electronic invoice information as the research object. Finally, the results show that: (1) foreign exchange (forex) events and major stock index decline events have a significant impact on the return of Bitcoin (BTC) in the short term. Moreover, more than 70% of uncertainty events will make BTC’s abnormal return (AR) significantly positive; (2) Under the influence of forex uncertainty events, only one BTC’s AR is remarkably negative in short order, while the other seven times are markedly positive. In the uncertainty events of major stock indexes, only two times are significantly negative, and the other six times are positive. This indicates that uncertain events in the short run make prominent AR of BTC; the proposed blockchain-based ISSA model and assessment index are scientific, feasible, and operable.
Learning from Noisy Labels with Distillation Yuncheng Li; Jianchao Yang; Yale Song ...
2017 IEEE International Conference on Computer Vision (ICCV),
2017-Oct.
Conference Proceeding
Open access
The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, label noise has ...been treated as statistical outliers, and techniques such as importance re-weighting and bootstrapping have been proposed to alleviate the problem. According to our observation, the real-world noisy labels exhibit multimode characteristics as the true labels, rather than behaving like independent random outliers. In this work, we propose a unified distillation framework to use "side" information, including a small clean dataset and label relations in knowledge graph, to "hedge the risk" of learning from noisy labels. Unlike the traditional approaches evaluated based on simulated label noises, we propose a suite of new benchmark datasets, in Sports, Species and Artifacts domains, to evaluate the task of learning from noisy labels in the practical setting. The empirical study demonstrates the effectiveness of our proposed method in all the domains.
Finding effective and objective biomarkers to inform the diagnosis of schizophrenia is of great importance yet remains challenging. Relatively little work has been conducted on multi-biological data ...for the diagnosis of schizophrenia. In this cross-sectional study, we extracted multiple features from three types of biological data, including gut microbiota data, blood data, and electroencephalogram data. Then, an integrated framework of machine learning consisting of five classifiers, three feature selection algorithms, and four cross validation methods was used to discriminate patients with schizophrenia from healthy controls. Our results show that the support vector machine classifier without feature selection using the input features of multi-biological data achieved the best performance, with an accuracy of 91.7% and an AUC of 96.5% (p < 0.05). These results indicate that multi-biological data showed better discriminative capacity for patients with schizophrenia than single biological data. The top 5% discriminative features selected from the optimal model include the gut microbiota features (Lactobacillus, Haemophilus, and Prevotella), the blood features (superoxide dismutase level, monocyte-lymphocyte ratio, and neutrophil count), and the electroencephalogram features (nodal local efficiency, nodal efficiency, and nodal shortest path length in the temporal and frontal-parietal brain areas). The proposed integrated framework may be helpful for understanding the pathophysiology of schizophrenia and developing biomarkers for schizophrenia using multi-biological data.
Image captioning is a challenging problem owing to the complexity in understanding the image content and diverse ways of describing it in natural language. Recent advances in deep neural networks ...have substantially improved the performance of this task. Most state-of-the-art approaches follow an encoder-decoder framework, which generates captions using a sequential recurrent prediction model. However, in this paper, we introduce a novel decision-making framework for image captioning. We utilize a policy network and a value network to collaboratively generate captions. The policy network serves as a local guidance by providing the confidence of predicting the next word according to the current state. Additionally, the value network serves as a global and lookahead guidance by evaluating all possible extensions of the current state. In essence, it adjusts the goal of predicting the correct words towards the goal of generating captions similar to the ground truth captions. We train both networks using an actor-critic reinforcement learning model, with a novel reward defined by visual-semantic embedding. Extensive experiments and analyses on the Microsoft COCO dataset show that the proposed framework outperforms state-of-the-art approaches across different evaluation metrics.
Image retrieval using scene graphs Johnson, Justin; Krishna, Ranjay; Stark, Michael ...
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
06/2015
Conference Proceeding
This paper develops a novel framework for semantic image retrieval based on the notion of a scene graph. Our scene graphs represent objects ("man", "boat"), attributes of objects ("boat is white") ...and relationships between objects ("man standing on boat"). We use these scene graphs as queries to retrieve semantically related images. To this end, we design a conditional random field model that reasons about possible groundings of scene graphs to test images. The likelihoods of these groundings are used as ranking scores for retrieval. We introduce a novel dataset of 5,000 human-generated scene graphs grounded to images and use this dataset to evaluate our method for image retrieval. In particular, we evaluate retrieval using full scene graphs and small scene subgraphs, and show that our method outperforms retrieval methods that use only objects or low-level image features. In addition, we show that our full model can be used to improve object localization compared to baseline methods.
The explosion of the Internet provides us with a tremendous resource of images shared online. It also confronts vision researchers the problem of finding effective methods to navigate the vast amount ...of visual information. Semantic image understanding plays a vital role towards solving this problem. One important task in image understanding is object recognition, in particular, generic object categorization. Critical to this problem are the issues of learning and dataset. Abundant data helps to train a robust recognition system, while a good object classifier can help to collect a large amount of images. This paper presents a novel object recognition algorithm that performs automatic dataset collecting and incremental model learning simultaneously. The goal of this work is to use the tremendous resources of the web to learn robust object category models for detecting and searching for objects in real-world cluttered scenes. Humans contiguously update the knowledge of objects when new examples are observed. Our framework emulates this human learning process by iteratively accumulating model knowledge and image examples. We adapt a non-parametric latent topic model and propose an incremental learning framework. Our algorithm is capable of automatically collecting much larger object category datasets for 22 randomly selected classes from the
Caltech 101
dataset. Furthermore, our system offers not only more images in each object category but also a robust object category model and meaningful image annotation. Our experiments show that OPTIMOL is capable of collecting image datasets that are superior to the well known manually collected object datasets
Caltech 101
and LabelMe.
This study aims to determine whether caveolin‐1 (Cav‐1) participates in the process of diabetic neuropathic pain by directly regulating the expression of toll‐like receptor 4 (TLR4) and the ...subsequent phosphorylation of N‐methyl‐D‐aspartate receptor 2B subunit (NR2B) in the spinal cord. Male Sprague‐Dawley rats (120–150 g) were continuously fed with high‐fat and high‐sugar diet for 8 weeks, and received a single low‐dose of intraperitoneal streptozocin injection in preparation for the type‐II diabetes model. Then, these rats were divided into five groups according to the level of blood glucose, and the mechanical withdrawal threshold and thermal withdrawal latency values. The pain thresholds were measured at 3, 7, and 14 days after animal grouping. Then, eight rats were randomly chosen from each group and killed. Lumbar segments 4–6 of the spinal cord were removed for western blot analysis and immunofluorescence assay. Cav‐1 was persistently upregulated in the spinal cord after diabetic neuropathic pain in rats. The downregulation of Cav‐1 through the subcutaneous injection of Cav‐1 inhibitor daidzein ameliorated the pain hypersensitivity and TLR4 expression in the spinal cord in diabetic neuropathic pain (DNP) rats. Furthermore, it was found that Cav‐1 directly bound with TLR4, and the subsequent phosphorylation of NR2B in the spinal cord contributed to the modulation of DNP. These findings suggest that Cav‐1 plays a vital role in DNP processing at least in part by directly regulating the expression of TLR4, and through the subsequent phosphorylation of NR2B in the spinal cord.