ABSTRACT Swimming sports are treated as modern competitive sports, and athletes need to standardize and correct their posture. Therefore, the recognition of swimming postures is considered as an important section the coaches implement training plans. Usually, the recognition of swimming postures is achieved through coach observation; however, this approach is inefficient and lacks sufficient accuracy. To address this issue, a novel recognition method is proposed. In the proposed method, different swimming postures are assigned a different score via using a two‐stage scoring mechanism. The feature regions of swimming postures can be accurately identified. Following that, the assigned score is put into the Softmax layer of the proposed convolutional neural networks. Finally, 4000 images including six swimming postures are used as an experimental set. The experimental results show that the proposed method achieves 92.73% testing accuracy and 89.03% validation accuracy in the recognition of the six swimming postures, defeating against the opponents. Meanwhile, our method outperforms some competitors in terms of training efficiency. The proposed two‐stage scoring mechanism can be used for image recognition in large‐scale scenarios. Moreover, the two‐stage scoring mechanism is independently of specific scenarios in process of assigning a score value for feature regions of images. Not only that, the two‐stage scoring mechanism can replace complex network structures, so as to reduce the work of training parameters.

Recent developments in large language models (LLM) and generative AI have unleashed the astonishing capabilities of text-to-image generation systems to synthesize high-quality images that are faithful to a given reference text, known as a “prompt”. These systems have immediately received lots of attention from researchers, creators, and common users. Despite the plenty of efforts to improve the generative models, there is limited work on understanding the information needs of the users of these systems at scale. We conduct the first comprehensive analysis of large-scale prompt logs collected from multiple text-to-image generation systems. Our work is analogous to analyzing the query logs of Web search engines, a line of work that has made critical contributions to the glory of the Web search industry and research. Compared with Web search queries, text-to-image prompts are significantly longer, often organized into special structures that consist of the subject, form, and intent of the generation tasks and present unique categories of information needs. Users make more edits within creation sessions, which present remarkable exploratory patterns. There is also a considerable gap between the user-input prompts and the captions of the images included in the open training data of the generative models. Our findings provide concrete implications on how to improve text-to-image generation systems for creation purposes.

We propose an improved analysis algorithm based on learning and searching methods in the field of Big Data to optimize TCM information management. We use TF-IDF theory in document clustering to cluster the name of Chinese Medical prescripts, construct word bag model, and combine universal hash with perfect hash, in order to establish a special key-value hashing band between Chinese Medical Data and diseases.

As online platforms are striving to get more users, a critical challenge is user churn, which is especially concerning for new users. In this paper, by taking the anonymous large-scale real-world data from Snapchat as an example, we develop ClusChurn , a systematic two-step framework for interpretable new user clustering and churn prediction, based on the intuition that proper user clustering can help understand and predict user churn. Therefore, ClusChurn firstly groups new users into interpretable typical clusters, based on their activities on the platform and ego-network structures. Then we design a novel deep learning pipeline based on LSTM and attention to accurately predict user churn with very limited initial behavior data, by leveraging the correlations among users' multi- dimensional activities and the underlying user types. ClusChurn is also able to predict user types, which enables rapid reactions to different types of user churn. Extensive data analysis and experiments show that ClusChurn provides valuable insight into user behaviors, and achieves state-of-the-art churn prediction performance. The whole framework is deployed as a data analysis pipeline, delivering real-time data analysis and prediction results to multiple relevant teams for business intelligence uses. It is also general enough to be readily adopted by any online systems with user behavior data.

Modern search engines aggregate results from different verticals : webpages, news, images, video, shopping, knowledge cards, local maps, and so on. Unlike “ten blue links,” these search results are heterogeneous in nature and not even arranged in a list on the page. This revolution directly challenges the conventional “ranked list” formulation in ad hoc search. Therefore, finding proper presentation for a gallery of heterogeneous results is critical for modern search engines. We propose a novel framework that learns the optimal page presentation to render heterogeneous results onto search result page (SERP). Page presentation is broadly defined as the strategy to present a set of items on SERP, much more expressive than a ranked list. It can specify item positions, image sizes, text fonts, and any other styles as long as variations are within business and design constraints. The learned presentation is content aware, i.e., tailored to specific queries and returned results. Simulation experiments show that the framework automatically learns eye-catchy presentations for relevant results. Experiments on real data show that simple instantiations of the framework already outperform leading algorithm in federated search result presentation. It means the framework can learn its own result presentation strategy purely from data, without even knowing the “probability ranking principle.”

Crowdsourcing services make it possible to collect huge amount of annotations from less trained crowd workers in an inexpensive and efficient manner. However, unlike making binary or pairwise judgements, labeling complex structures such as ranked lists by crowd workers is subject to large variance and low efficiency, mainly due to the huge labeling space and the annotators' non-expert nature. Yet ranked lists offer the most informative knowledge for training and testing in various data mining and information retrieval tasks such as learning to rank. In this paper, we propose a novel generative model called "Thurstonian Pairwise Preference" (TPP) to infer the true ranked list out of a collection of crowdsourced pairwise annotations. The key challenges that TPP addresses are to resolve the inevitable incompleteness and inconsistency of judgements, as well as to model variable query difficulty and different labeling quality resulting from workers' domain expertise and truthfulness. Experimental results on both synthetic and real-world datasets demonstrate that TPP can effectively bind pairwise preferences of the crowd into rankings and substantially outperforms previously published methods.

Modern search engines aggregate results from different verticals: webpages, news, images, video, shopping, knowledge cards, local maps, etc. Unlike "ten blue links", these search results are heterogeneous in nature and not even arranged in a list on the page. This revolution directly challenges the conventional "ranked list" formulation in ad hoc search. Therefore, finding proper presentation for a gallery of heterogeneous results is critical for modern search engines.

Entities (e.g., person, movie or place) play an important role in real-world applications and learning entity types has attracted much attention in recent years. Most conventional automatic techniques use large corpora, such as news articles, to learn types of entities. However, such text corpora focus on general knowledge about entities in an objective way. Hence, it is difficult to satisfy those users with specific and personalized needs for an entity. Recent years have witnessed an explosive expansion in the mining of search query logs, which contain billions of entities. The word patterns and click-throughs in search logs are not found in text corpora, thus providing a complemental source for discovering entity types based on user behaviors. In this paper, we study the problem of learning entity types from search query logs and address the following challenges: (1) queries are short texts, and information related to entities is usually very sparse; (2) large amounts of irrelevant information exists in search logs, bringing noise in detecting entity types. In this paper, we first model query logs using a bipartite graph with entities and their auxiliary information, such as contextual words and clicked URLs. Then we propose a graph-based framework called ELP (Ensemble framework based on Lable Propagation) to simultaneously learn the types of both entities and auxiliary signals. In ELP, two separate strategies are designed to fix the problems of sparsity and noise in query logs. Extensive empirical studies are conducted on real search logs to evaluate the effectiveness of the proposed ELP framework.

Today's popular web search engines expand the search process beyond crawled web pages to specialized corpora ("verticals") like images, videos, news, local, sports, finance, shopping etc., each with its own specialized search engine. Search federation deals with problems of the selection of search engines to query and merging of their results into a single result set. Despite a few recent advances, the problem is still very challenging. First, due to the heterogeneous nature of different verticals, how the system merges the vertical results with the web documents to serve the user's information need is still an open problem. Moreover, the scale of the search engine and the increasing number of vertical properties requires a solution which is efficient and scaleable. In this paper, we propose a unified framework for the search federation problem. We model the search federation as a contextual bandit problem. The system uses reward as a proxy for user satisfaction. Given a query, our system predicts the expected reward for each vertical, then organizes the search result page (SERP) in a way which maximizes the total reward. Instead of relying on human judges, our system leverages implicit user feedback to learn the model. The method is efficient to implement and can be applied to verticals of different nature. We have successfully deployed the system to three different markets, and it handles multiple verticals in each market. The system is now serving hundreds of millions of queries live each day, and has improved user metrics considerably.