Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decoder for triplet prediction, or utilize two parallel decoders to detect individual objects and interactions separately, and compose triplets by a matching process. In contrast, we decouple the triplet prediction into human-object pair detection and interaction classification. Our main motivation is that detecting the human-object instances and classifying interactions accurately needs to learn representations that focus on different regions. To this end, we present Disentangled Transformer, where both encoder and decoder are disentangled to facilitate learning of two subtasks. To associate the predictions of disentangled decoders, we first generate a unified representation for HOI triplets with a base decoder, and then utilize it as input feature of each disentangled decoder. Extensive experiments show that our method outperforms prior work on two public HOI benchmarks by a sizeable margin. Code will be available.
BackgroundWith its immense population and as the largest developing country in the world, China has made remarkable achievements in health promotion at a relatively low cost. However, China is still faced with challenges such as changes of disease spectrum, the coming era of an aging society, and the risk of environmental pollution.Main textOn October 25, 2016, China formally passed the blueprint of “Healthy China 2030,” working towards the national goal of reaching a health standard on par with developed countries by 2030, which was also a response to realize the 2030 United Nations Sustainable Development Goals. “Healthy China 2030” is comprised of 29 chapters that cover five health areas. China is sparing no effort to transfer from being merely the most populous country, to becoming a leading nation in health education. In “Healthy China 2030,” collaborated construction and resource sharing were clearly stated as the core strategy. A shift in concentration towards coordinated development of health-based economy from a previous pursuit of rapid economic growth was also underlined. There are also several major issues, such as severely aging population, the burden of chronic diseases, the insufficiency of health expenditure, and the great demand on health protection, waiting to be dealt with during the implementation process of “Healthy China 2030”.Conclusions“Healthy China 2030” is a momentous move to enhance public health, which is also a response to the global commitments. We also need to rethink our approach to reach the living standards and maintain a better environment.
In order to improve ineffective warning prioritization of static analysis tools, various approaches have been proposed to compute a ranking score for each warning. In these approaches, an effective training set is vital in exploring which factors impact the ranking score and how. While manual approaches to build a training set can achieve high effectiveness but suffer from low efficiency (i.e., high cost), existing automatic approaches suffer from low effectiveness. In this paper, we propose an automatic approach for constructing an effective training set. In our approach, we select three categories of impact factors as input attributes of the training set, and propose a new heuristic for identifying actionable warnings to automatically label the training set. Our empirical evaluations show that the precision of the top 22 warnings for Lucene, 20 for ANT, and 6 for Spring can achieve 100% with the help of our constructed training set.
Recently many popular websites such as Twitter and Flickr expose their data through web service APIs, enabling third-party organizations to develop client applications that provide functionalities beyond what the original websites offer. These client applications should follow certain constraints in order to correctly interact with the web services. One common type of such constraints is Dependency Constraints on Parameters. Given a web service operation O and its parameters Pi, Pj,…, these constraints describe the requirement on one parameter Pi that is dependent on the conditions of some other parameter(s) Pj. For example, when requesting the Twitter operation "GET statuses/user_timeline", a user_id parameter must be provided if a screen_name parameter is not provided. Violations of such constraints can cause fatal errors or incorrect results in the client applications. However, these constraints are often not formally specified and thus not available for automatic verification of client applications. To address this issue, we propose a novel approach, called INDICATOR, to automatically infer dependency constraints on parameters for web services, via a hybrid analysis of heterogeneous web service artifacts, including the service documentation, the service SDKs, and the web services themselves. To evaluate our approach, we applied INDICA-TOR to infer dependency constraints for four popular web services. The results showed that INDICATOR effectively infers constraints with an average precision of 94.4% and recall of 95.5%.
Disruption prediction is essential for the safe operation of a large scale tokamak. Existing disruption predictors based on machine learning techniques have good prediction performance, but all these methods need large training datasets including many disruptions to develop their successful prediction capability. Future machines are unlikely to provide enough disruption samples since these cause excessive machine damage and the prediction models used are difficult to extrapolate to a machines that the predictor was not trained on. In this paper, a disruption predictor based on a deep learning and anomaly detection technique has been developed. It regards the disruption as an anomaly, and can learn on non-disruptive shots only. The model is trained to extract the hidden features of various nondisruptive shots with a convolutional neural network and a long-shot term memory (LSTM) recurrent neural network. It will predict the future trend of selected diagnostics, then using the predicted future trend and the measured signal to calculate an outlier factor to determine if a disruption is coming. It was tested with J-TEXT discharges in flat top phase and can demonstrate comparable performance to current machine learning disruption prediction techniques, without requiring a disruption data set. This could be applied to future tokamaks and reduce the dependency on disruptive experiments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.