Search for: All records

Structured chemical reaction information plays a vital role for chemists engaged in laboratory work and advanced endeavors such as computer-aided drug design. Despite the importance of extracting structured reactions from scientific literature, data annotation for this purpose is cost-prohibitive due to the significant labor required from domain experts. Consequently, the scarcity of sufficient training data poses an obstacle to the progress of related models in this domain. In this paper, we propose REACTIE, which combines two weakly supervised approaches for pre-training. Our method utilizes frequent patterns within the text as linguistic cues to identify specific characteristics of chemical reactions. Additionally, we adopt synthetic data from patent records as distant supervision to incorporate domain knowledge into the model. Experiments demonstrate that REACTIE achieves substantial improvements and outperforms all existing baselines. 

Contextual information has been widely used in many computer vision tasks. However, existing approaches design specific contextual information mechanisms for different tasks. In this work, we propose a general context learning and reasoning framework for object detection tasks with three components: local contextual labeling, contextual graph generation and spatial contextual reasoning. With simple user defined parameters, local contextual labeling automatically enlarge the small object labels to include more local contextual information. A Graph Convolutional Network learns over the generated contextual graph to build a semantic space. A general spatial relation is used in spatial contextual reasoning to optimize the detection results. All three components can be easily added and removed from a standard object detector. In addition, our approach also automates the training process to find the optimal combinations of user defined parameters. The general framework can be easily adapted to different tasks. In this paper we compare our framework with a previous multistage context learning framework specifically designed for storefront accessibility detection and a state of the art detector for pedestrian detection. Experimental results on two urban scene datasets demonstrate that our proposed general framework can achieve same performance as the specifically designed multistage framework on storefront accessibility detection, and with improved performance on pedestrian detection over the state of art detector. 

In this work, a storefront accessibility image dataset is collected from Google street view and is labeled with three main objects for storefront accessibility: doors (for store entrances), doorknobs (for accessing the entrances) and stairs (for leading to the entrances). Then MultiCLU, a new multi-stage context learning and utilization approach, is proposed with the following four stages: Context in Labeling (CIL), Context in Training (CIT), Context in Detection (CID) and Context in Evaluation (CIE). The CIL stage automatically extends the label for each knob to include more local contextual information. In the CIT stage, a deep learning method is used to project the visual information extracted by a Faster R-CNN based object detector to semantic space generated by a Graph Convolutional Network. The CID stage uses the spatial relation reasoning between categories to refine the confidence score. Finally in the CIE stage, a new loose evaluation metric for storefront accessibility, especially for knob category, is proposed to efficiently help BLV users to find estimated knob locations. Our experiment results show that the proposed MultiCLU framework can achieve significantly better performance than the baseline detector using Faster R-CNN, with +13.4% on mAP and +15.8% on recall, respectively. Our new evaluation metric also introduces a new way to evaluate storefront accessibility objects, which could benefit BLV group in real life. 

Submarine cables have become a vital component of modern infrastructure, but past submarine cable natural hazard studies have mostly focused on potential cable damage from landslides and tsunamis. A handful of studies examine the possibility of space weather effects in submarine cables. The main purpose of this study is to develop a computational model, using Python , of geomagnetic induction on submarine cables. The model is used to estimate the induced voltage in the submarine cables in response to geomagnetic disturbances. It also utilizes newly acquired knowledge from magnetotelluric studies and associated investigations of geomagnetically induced currents in power systems. We describe the Python-based software, its working principle, inputs/outputs based on synthetic geomagnetic field data, and compare its operational capabilities against analytical solutions. We present the results for different model inputs, and find: 1) the seawater layer acts as a shield in the induction process: the greater the ocean depth, the smaller the seafloor geoelectric field; and 2) the model is sensitive to the Ocean-Earth layered conductivity structure. 

Tropospheric reactive bromine (Br_y) influences the oxidation capacity of the atmosphere by acting as a sink for ozone and nitrogen oxides. Aerosol acidity plays a crucial role in Br_yabundances through acid‐catalyzed debromination from sea‐salt‐aerosol, the largest global source. Bromine concentrations in a Russian Arctic ice‐core, Akademii Nauk, show a 3.5‐fold increase from pre‐industrial (PI) to the 1970s (peak acidity, PA), and decreased by half to 1999 (present day, PD). Ice‐core acidity mirrors this trend, showing robust correlation with bromine, especially after 1940 (r = 0.9). Model simulations considering anthropogenic emission changes alone show that atmospheric acidity is the main driver of Br_ychanges, consistent with the observed relationship between acidity and bromine. The influence of atmospheric acidity on Br_yshould be considered in interpretation of ice‐core bromine trends.

 

Gatherings of thousands to millions of people frequently occur for an enormous variety of educational, social, sporting, and political events, and automated counting of these high-density crowds is useful for safety, management, and measuring significance of an event. In this work, we show that the regularly accepted labeling scheme of crowd density maps for training deep neural networks may not be the most effective one. We propose an alternative inverse k-nearest neighbor (i[Formula: see text]NN) map mechanism that, even when used directly in existing state-of-the-art network structures, shows superior performance. We also provide new network architecture mechanisms that we demonstrate in our own MUD-i[Formula: see text]NN network architecture, which uses multi-scale drop-in replacement upsampling via transposed convolutions to take full advantage of the provided i[Formula: see text]NN labeling. This upsampling combined with the i[Formula: see text]NN maps further improves crowd counting accuracy. We further analyze several variations of the i[Formula: see text]NN labeling mechanism, which apply transformations on the [Formula: see text]NN measure before generating the map, in order to consider the impact of camera perspective views, image resolutions, and the changing rates of the mapping functions. To alleviate the effects of crowd density changes in each image, we also introduce an attenuation mechanism in the i[Formula: see text]NN mapping. Experimentally, we show that inverse square root [Formula: see text]NN map variation (iR[Formula: see text]NN) provides the best performance. Discussions are provided on computational complexity, label resolutions, the gains in mapping and upsampling, and details of critical cases such as various crowd counts, uneven crowd densities, and crowd occlusions.