Input Query Research Articles

Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection.

The Detection Transformer (DETR) has revolutionized the design of CNN-based object detection systems, showcasing impressive performance. However, its potential in the domain of multi-frame 3D object detection remains largely unexplored. In this paper, we present STEMD, a novel end-to-end framework that enhances the DETR-like paradigm for multi-frame 3D object detection by addressing three key aspects specifically tailored for this task. First, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network, which represents queries as nodes in a graph and enables effective modeling of object interactions within a social context. To solve the problem of missing hard cases in the proposed output of the encoder in the current frame, we incorporate the output of the previous frame to initialize the query input of the decoder. Finally, it poses a challenge for the network to distinguish between the positive query and other highly similar queries that are not the best match. And similar queries are insufficiently suppressed and turn into redundant prediction boxes. To address this issue, our proposed IoU regularization term encourages similar queries to be distinct during the refinement. Through extensive experiments, we demonstrate the effectiveness of our approach in handling challenging scenarios, while incurring only a minor additional computational overhead.

SmartGraphAI: Real Time Graph Generation with AI

SmartGraphAI, an innovative web platform, is designed to revolutionize the way users generate graphs in real-time using AI and large language models (LLMs). By processing natural language queries, SmartGraphAI intelligently breaks down user requests into multiple sub-queries that retrieve relevant data from the internet. This data is then integrated into user-friendly visualizations through dynamic graphs that adapt to the user’s requirements. The platform leverages advanced LLM technology for query interpretation and utilizes web scraping APIs for real-time data extraction, ensuring that users receive up-to-date, accurate insights. The backend, built on FastAPI, manages the data flow seamlessly, while the frontend, developed with React, provides a smooth and intuitive interface for users to engage with. SmartGraphAI empowers professionals across industries to quickly transform complex data into meaningful visual insights, automating the entire process from query input to graph generation, and thus, enhancing decision-making and efficiency in data analysis. Keywords AI, Graph Generation, Real-Time, Large Language Models, Data Visualization, Web Scraping

Uncertain features exploration in temporal moment localization via language by utilizing customized temporal transformer

Temporal moment localization in videos using natural language (TMLVNL) is challenging problem in computer vision. TMLVNL aims to determine the correct moment in a lengthy, untrimmed video that corresponds to the input query. In addition to its inherent complexity, TMLVNL encounters several additional difficulties that can degrade performance, such as rare object positions, occlusions, camera focus issues, and motion blurriness. To address these issues, this study proposes a novel solution called the Temporal Ziggurat Transformer Network. First, we developed a novel method rather than relying on various combinational approaches. Second, we proposed complicated scenarios, such as unusual object postures, object occlusions, camera focus issues, and motion blurriness, by incorporating specialized blocks into our Customized Ziggurat Transformer (ZT) to thoroughly explore visual features. Third, to facilitate the understanding of visual features associated with query words, we proposed a query word-specific transformer (QWST) as a submodule of ZT. QWST integrates query word feature representations with extensively investigated visual features. Fourth, in our module named STDF, we managed query-sentence representations along with query word attributes to extract semantic context from video chunks. The moment was then localized, with its start and end borders identified using the moment localization module. Comprehensive experiments on the Charades-STA, TACos, and Activity-Netcaption datasets demonstrated that our strategy outperformed existing state-of-the-art methods.

Budget-aware Query Tuning: An AutoML Perspective

Modern database systems rely on cost-based query optimizers to come up with good execution plans for input queries. Such query optimizers rely on cost models to estimate the costs of candidate query execution plans. A cost model represents a function from a set of cost units to query execution cost, where each cost unit specifies the unit cost of executing a certain type of query processing operation (such as table scan or join). These cost units are traditionally viewed as constants, whose values only depend on the platform configuration where the database system runs on top of but are invariant for queries processed by the database system. In this paper, we challenge this classic view by thinking of these cost units as variables instead. We show that, by varying the cost-unit values one can obtain query plans that significantly outperform the default query plans returned by the query optimizer when viewing the cost units as constants. We term this cost-unit tuning process 'query tuning' (QT) and show that it is similar to the well-known hyper-parameter optimization (HPO) problem in AutoML. As a result, any state-of-the-art HPO technologies can be applied to QT. We study the QT problem in the context of anytime tuning, which is desirable in practice by constraining the total time spent on QT within a given budget-we call this problem budgetaware query tuning. We further extend our study from tuning a single query to tuning a workload with multiple queries, and we call this generalized problem budgetaware workload tuning (WT), which aims for minimizing the execution time of the entire workload. WT is more challenging as one needs to further prioritize individual query tuning within the given time budget. We propose solutions to both QT and WT and experimental evaluation using both benchmark and real workloads demonstrates the efficacy of our proposed solutions.

SAVE: Encoding spatial interactions for vision transformers

Transformers have achieved impressive performance in visual tasks. Position encoding, which equips vectors (elements of input tokens, queries, keys, or values) with sequence specificity, effectively alleviates the lack of permutation relation in transformers. In this work, we first clarify that both position encoding and additional position-specific operations will introduce positional information when participating in self-attention. On this basis, most existing position encoding methods are equivalent to special affine transformations. However, this encoding method lacks the correlation of vector content interaction. We further propose Spatial Aggregation Vector Encoding (SAVE) that employs transition matrices to recombine vectors. We design two simple yet effective modes to merge other vectors, with each one serving as an anchor. The aggregated vectors control spatial contextual connections by establishing two-dimensional relationships. Our SAVE can be plug-and-play in vision transformers, even with other position encoding methods. Comparative results on three image classification datasets show that the proposed SAVE performs comparably to current position encoding methods. Experiments on detection tasks show that the SAVE improves the downstream performance of transformer-based methods. Code is available at https://github.com/maxiao0234/SAVE.

ADCMDES: Design of an augmented cross-domain collaborative recommendation model using novel distance metric and ensemble stratification

Collaborative recommendation involves leveraging information from one entity to suggest attributes of other entities through pattern analysis. These models are invaluable for understanding data behaviour’s impact on related entities. Researchers propose various pattern recognition and correlation models, employing distance metrics like Jaccard, Cosine, etc., to estimate correlations between user queries and recommendation datasets. However, these models become less efficient as dataset size increases due to exponential correlation estimation delays. To enhance scalability while retaining recommendation quality, a new approach is introduced: ADCMDES. This novel augmented cross-domain collaborative model employs a hybrid distance metric and ensemble stratification for dataset pruning. It operates semi-supervisedly, requiring information about the entities being collaborated upon. This data is used to cluster similar collaborative entities, producing a condensed cluster with greater relevancy to user queries. Utilizing word2vec, records are transformed into features for an ensemble classification engine. The resultant model categorizes user input, directing it to the most relevant cluster. Entries within this cluster are ranked using a hybrid metric amalgamating 18 distance measures, enhancing correlation between input queries and recommendations. In testing, ADCMDES exhibited 15% better accuracy, 8% better precision, 9% better recall, and 3% lower RMSE compared to standard models across datasets. While some delay is introduced due to ensemble classification and augmented feature pooling, this doesn't considerably affect long-term recommendation performance and can be mitigated through parallel processing and redundancy reduction techniques.

Retrieving Continuous Time Event Sequences using Neural Temporal Point Processes with Learnable Hashing

Temporal sequences have become pervasive in various real-world applications such as finance, spatial mobility, health records, etc. Consequently, the volume of data generated in the form of continuous time-event sequence(s) or CTES(s) has increased exponentially in the past few years. Thus, a significant fraction of the ongoing research on CTES datasets involves designing models to address downstream tasks such as next-event prediction, long-term forecasting, sequence classification etc. The recent developments in predictive modeling using marked temporal point processes (MTPP) have enabled an accurate characterization of several real-world applications involving the CTESs. However, due to the complex nature of these CTES datasets, the task of large-scale retrieval of temporal sequences has been overlooked by the past literature. In detail, by CTES retrieval we mean that for an input query sequence, a retrieval system must return a ranked list of relevant sequences from a large corpus. To tackle this, we propose NeuroSeqRet , a first-of-its-kind framework designed specifically for end-to-end CTES retrieval. Specifically, NeuroSeqRet introduces multiple enhancements over standard retrieval frameworks and first applies a trainable unwarping function on the query sequence which makes it comparable with corpus sequences, especially when a relevant query-corpus pair has individually different attributes. Next, it feeds the unwarped query sequence and the corpus sequence into MTPP-guided neural relevance models. We develop four variants of the relevance model for different kinds of applications based on the trade-off between accuracy and efficiency. We also propose an optimization framework to learn binary sequence embeddings from the relevance scores, suitable for the locality-sensitive hashing leading to a significant speedup in returning top-K results for a given query sequence. Our experiments with several datasets show the significant accuracy boost of NeuroSeqRet beyond several baselines, as well as the efficacy of our hashing mechanism.

CoWPE: Adaptive Context Window Adjustment in LLMs for Complex Input Queries

CoWPE: Adaptive Context Window Adjustment in LLMs for Complex Input Queries

Privacy preservation network with global-aware focal loss for Interactive Personal Visual Privacy Preservation

Existing visual privacy preservation methods often encounter the challenge of over-protection, which usually fails to accurately protect a specified person in an image. This paper introduces a novel task called “Interactive Personal Visual Privacy Preservation (IPVPP)”, with the objective of safeguarding a desired individual in an image based on user-click prompts. We propose a new framework, Privacy Preservation Network (PPNet) with Global-aware Focal Loss, tailored for IPVPP task. To address the sample imbalance issue in IPVPP, we present a Global-aware Focal Loss (GFL), which introduces global and local difficulty balance weights to dynamically adjust the overall decision boundary, thereby mitigating the sample imbalance problem for better optimization of models. Furthermore, to tackle the insufficient fusion between click and visual features, we propose a Click-Image Fusion (CIF) module, which effectively emphasizes the interaction between click and image features, providing robust query inputs to the model. We finally employ generative adversarial networks to ensure the reusability of privacy images, striking a balance between privacy preservation and image value. Experimental results on the DAVIS dataset demonstrate the effectiveness of PPNet, achieving improvements measured in NoC 90, IS, SSIM, F-1, and DIR, with 0.22, 0.19, 0.009, 4.23, and 2.15 improvements, respectively.

Can ChatGPT Be a Certified Accountant? Assessing the Responses of ChatGPT for the Professional Access Exam in Portugal

Purpose: From an exploratory perspective, this paper aims to assess how well ChatGPT scores in an accounting proficiency exam in Portugal, as well as its overall understanding of the issues, purpose and context underlying the questions under assessment. Design/methodology/approach: A quasi-experimental method is used in this study. The questions from an exam by the Portuguese Order of Chartered Accountants (OCC, in the Portuguese acronym) served as input queries, while the responses (outputs) from ChatGPT were compared with those from the OCC. Findings: The findings indicate that ChatGPT’s responses were able to deduce the primary issue underlying the matters assessed, although some responses were inaccurate or imprecise. Also, the tool did not have the same score in all matters, being less accurate in those requiring more professional judgment. The findings also show that the ChatGPT did not pass the exam, although it was close to doing so. Originality: To the best of the authors’ knowledge, there is little research on ChatGPT accuracy in accounting proficiency exams, this being the first such study in Portugal. Practical implications: The findings from this research can be useful to accounting professionals to understand how ChatGPT may be used for practitioners, stressing that it could assist them and improve efficiency, but cannot, at least for now, replace the human professional. It also highlights the potential use of ChatGPT as an additional resource in the classroom, encouraging students to engage in critical thinking and facilitating open discussion with the guidance of teachers. Consequently, it can also prove beneficial for academic purposes, aiding in the learning process.

SketchCleanGAN: A generative network to enhance and correct query sketches for improving 3D CAD model retrieval systems

Given an input query, a search and retrieval system fetches relevant information from a dataset. In the Engineering domain, such a system is beneficial for tasks such as design reuse. A two-dimensional (2D) sketch is more conducive for an end user to give as a query than a three-dimensional (3D) object. Such query sketches, nevertheless, will inevitably contain defects like incomplete lines, mesh lines, overdrawn areas, missing areas, etc. Since a retrieval system’s results are only as good as the query, it is necessary to improve the query sketches.In this paper, the problem of transforming a defective CAD sketch into a defect-free sketch is addressed using Generative Adversarial Networks (GANs), which, to the best of our knowledge, has not been investigated before. We first create a dataset of 534 hand-drawn sketches by tracing the boundaries of images of CAD models. We then pair the corrected sketches with their corresponding defective sketches and use them for training a C-WGAN (Conditional Wasserstein Generative Adversarial Network), called SketchCleanGAN. We model the transformation from defective to defect-free sketch as a factorization of the defective input sketch and then translate it to the space of defect-free sketch. We propose a three-branch strategy to this problem. Ablation studies and comparisons with other state-of-the-art techniques demonstrate the efficacy of the proposed technique. Additionally, we also contribute to a dataset of around 58000 improved sketches using the proposed framework.

Stacked collaborative transformer network with contrastive learning for video moment localization

Video grounding intends to perform temporal localization in multimedia information retrieval. The temporal bounds of the target video span are determined for the given input query. A novel interactive multi-head self-attention (IMSA) transformer is proposed to localize an unseen moment in the untrimmed video for the given image. A new semantic-trained self-supervised approach is considered in this paper to perform cross-domain learning to match the image query – video segment. It normalizes the convolution function enabling efficient correlation and collecting of semantically related video segments across time based on the image query. A double hostile Contrastive learning with Gaussian distribution parameters method is advanced to learn the representations of video. The proposed approach performs dynamically on various video components to achieve exact semantic synchronization and localization among queries and video. In the proposed approach, the IMSA model localizes frames greatly compared to other approaches. Experiments on benchmark datasets show that the proposed model can significantly increase temporal grounding accuracy. The moment occurrence is identified in the video with a start and end boundary ascertains an average recall of 86.45% and a mAP of 59.3%.

Adaptive weighted multi-view subspace clustering method for recognizing urban functions from multi-source social sensing data

ABSTRACT Multi-source social sensing data provide new opportunities to identify urban functions from the perspective of human activity. The information embedded in multi-source data typically needs to be fused to obtain a comprehensive view of urban functions. Although multi-view clustering has been successfully used to fuse multi-source social sensing data, the adaptive determination of fusion weights for high-dimensional and noisy multi-source social sensing data remains challenging. Therefore, this study proposes an adaptive weighted multi-view subspace clustering (AWMSC) method. First, we use two neural networks to map multi-source data into a common latent representation and multiple specific latent representations, which serve as the query vector and input vectors of the attention mechanism, respectively. Then, the weight of each type of data is calculated based on the attention mechanism. Finally, the specific latent representations of the multi-source data are weighted and fused into a shared subspace representation, which is used as the input of the spectral clustering algorithm to obtain clustering results. AWMSC is applied to identify urban functional zones in Beijing using bus transactions, taxi trajectories, and points of interest datasets. The results show that AWMSC outperforms the typical single-view, weighted-average, and representative multi-view methods. AWMSC can obtain a comprehensive understanding of urban functional zones which may help government departments make more accurate strategic decisions.

Genie: Enhancing information management in the restaurant industry through AI-powered chatbot

In the dynamic restaurant industry, we introduce "Genie," an AI-powered chatbot, represents an advancement in customer service efficiency through technological innovation. Designed to enhance restaurant operations including order processing, reservations, and FAQs management, Genie leverages advanced Natural Language Processing (NLP) techniques. By converting input queries into word embeddings and applying a sophisticated tag classification system, Genie precisely interprets customer intents and generates accurate responses, thereby markedly improving the dining experience. Our thorough examination of various word embeddings and classifiers—Word2Vec, Glove, BERT, Gaussian Naive Bayes, XGB, Artificial Neural Networks (ANN), and Recurrent Neural Networks—revealed that the combination of Word2Vec and ANN is the most effective, achieving an impressive accuracy rate of 88.9 %. This discovery highlights Genie's capability to not only streamline restaurant operations but also enhance customer satisfaction by minimizing wait times and facilitating contactless service options. Additionally, this study enriches the understanding of AI's application in service industries and explores the potential future impact of generative AI technologies on chatbot interactions. As AI technology advances, its integration is essential for Genie to deliver increasingly personalized and dynamic customer experiences, aligning with the evolving demands of the digital era. This research emphasizes the transformative impact of AI in the restaurant industry, providing valuable insights into its practical applications and future prospects for automated customer service solutions.

Counting Answers to Unions of Conjunctive Queries: Natural Tractability Criteria and Meta-Complexity

We study the problem of counting answers to unions of conjunctive queries (UCQs) under structural restrictions on the input query. Concretely, given a class C of UCQs, the problem #UCQ (C) provides as input a UCQ Ψ ∈ C and a database D and the problem is to compute the number of answers of Ψ in D. Chen and Mengel [PODS'16] have shown that for any recursively enumerable class C, the problem #UCQ (C) is either fixed-parameter tractable or hard for one of the parameterised complexity classes W[1] or #W[1]. However, their tractability criterion is unwieldy in the sense that, given any concrete class C of UCQs, it is not easy to determine how hard it is to count answers to queries in C. Moreover, given a single specific UCQ Ψ, it is not easy to determine how hard it is to count answers to Ψ. In this work, we address the question of finding a natural tractability criterion: The combined conjunctive query of a UCQ Ψ=φ 1 ∨ ... ∨ φ l is the conjunctive query ^ Ψ = φ_1 ∧ ... ∧ φ l . We show that under natural closure properties of C, the problem #UCQ (C) is fixed-parameter tractable if and only if the combined conjunctive queries of UCQs in C, and their contracts, have bounded treewidth. A contract of a conjunctive query is an augmented structure, taking into account how the quantified variables are connected to the free variables --- if all variables are free, then a conjunctive query is equal to its contract; in this special case the criterion for fixed-parameter tractability of #UCQ (C) thus simplifies to the combined queries having bounded treewidth. Finally, we give evidence that a closure property on C is necessary for obtaining a natural tractability criterion: We show that even for a single UCQ Ψ, the meta problem of deciding whether #UCQ (Ψ) can be solved in time O(|D| d ) is NP-hard for any fixed d ≥ 1. Moreover, we prove that a known exponential-time algorithm for solving the meta problem is optimal under assumptions from fine-grained complexity theory. As a corollary of our reduction, we also establish that approximating the Weisfeiler-Leman-Dimension of a UCQ is NP-hard.

Listwise Generative Retrieval Models via a Sequential Learning Process

Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single sequence-to-sequence model is learned to directly generate a list of relevant document identifiers (docids) given a query. Existing GR models commonly employ maximum likelihood estimation (MLE) for optimization: This involves maximizing the likelihood of a single relevant docid given an input query, with the assumption that the likelihood for each docid is independent of the other docids in the list. We refer to these models as the pointwise approach in this article. While the pointwise approach has been shown to be effective in the context of GR, it is considered sub-optimal due to its disregard for the fundamental principle that ranking involves making predictions about lists. In this article, we address this limitation by introducing an alternative listwise approach, which empowers the GR model to optimize the relevance at the docid list level. Specifically, we view the generation of a ranked docid list as a sequence learning process: At each step, we learn a subset of parameters that maximizes the corresponding generation likelihood of the i th docid given the (preceding) top i -1 docids. To formalize the sequence learning process, we design a positional conditional probability for GR. To alleviate the potential impact of beam search on the generation quality during inference, we perform relevance calibration on the generation likelihood of model-generated docids according to relevance grades. We conduct extensive experiments on representative binary and multi-graded relevance datasets. Our empirical results demonstrate that our method outperforms state-of-the-art GR baselines in terms of retrieval performance.

A Novel Address-Matching Framework Based on Region Proposal

Geocoding is a fundamental component of geographic information science that plays a crucial role in various geographical studies and applications involving text data. Current mainstream geocoding methods fall into two categories: geodesic-grid prediction and address matching. However, the geodesic-grid-prediction method’s localization accuracy is hindered by the density of grid partitioning, struggling to strike a balance between prediction accuracy and grid density. Address-matching methods mainly focus on the semantics of query text. However, they tend to ignore keyword information that can be used to distinguish candidates and introduce potential interference, which reduces matching accuracy. Inspired by the human map-usage process, we propose a two-stage address-matching approach that integrates geodesic-grid prediction and text-matching models. Initially, a multi-level text-classification model is used to generate a retrieval region proposal for an input query text. Subsequently, we search for the most relevant point of interest (POI) within the region-proposal area using a semantics-based text-retrieval model. We evaluated the proposed method using POI data from the Beijing Chaoyang District. The experimental results indicate that the proposed method provides high address-matching accuracy, increasing Recall@1 by 0.55 to 1.56 percentage points and MRR@5 by 0.54 to 1.68 percentage points.

Sharing Queries with Nonequivalent User-defined Aggregate Functions

This article presents Sharing User-Defined Aggregate Function (SUDAF), a declarative framework that allows users to write User-defined Aggregate Functions (UDAFs) as mathematical expressions and use them in Structured Query Language statements. SUDAF rewrites partial aggregates of UDAFs using built-in aggregate functions and supports efficient dynamic caching and reusing of partial aggregates. Our experiments show that rewriting UDAFs using built-in functions can significantly speed up queries with UDAFs, and the proposed sharing approach can yield up to two orders of magnitude improvement in query execution time. The article studies also an extension of SUDAF to support sharing partial results between arbitrary queries with UDAFs. We show a connection with the problem of query rewriting using views and introduce a new class of rewritings, called SUDAF rewritings, which enables to use views that have aggregate functions different from the ones used in the input query. We investigate the underlying rewriting-checking and rewriting-existing problem. Our main technical result is a reduction of these problems to, respectively, rewriting-checking and rewriting-existing of the so-called aggregate candidates , a class of rewritings that has been deeply investigated in the literature.

Medical nearest-word embedding technique implemented using an unsupervised machine learning approach for Bengali language

Abstract The rapid growth of natural language processing (NLP) applications, such as text summarization, speech recognition, information extraction, and machine translation, has led to the development of structured query language (SQL) for extracting information from structured data. However, due to limited resources, converting Natural Language (NL) queries to SQL in Bengali is challenging. This article proposes an unsupervised machine learning model to find semantically Bengali closed words that can generate SQL from NL queries in Bengali. The main objective of the proposed system is to provide support in the creation of patient-oriented explanations and educational resources by simplifying intricate medical terminology. The major findings of the proposed system are as follows: The use of machine translation in the field of medicine facilitates the dissemination of healthcare information to a diverse international audience and improves the performance of entity recognition tasks, including the identification of medical conditions, drugs, or procedures within clinical notes or electronic health data. This system allows a naive user to extract health-related information from a healthcare-structured database without any knowledge of SQL. The system accepts a query and generates a response according to the query in Bengali language. Query tokenization and stop word removal are carried out in the preprocessing stage, and unsupervised machine learning techniques are implemented to process the input query sentence. Tokenized words are converted into vectors using the skip-gram model, with noise-contrastive estimation (NCE) applied to discriminate between actual and irrelevant words. Stochastic gradient descent (SGD) optimizes the model by randomly choosing a small amount of data from the dataset and using cosine similarity to measure closer words. The semantically closer words are found using an unsupervised learning method to generate the SQL.

Zero-Shot Sketch-Based Image Retrieval Using StyleGen and Stacked Siamese Neural Networks.

Sketch-based image retrieval (SBIR) refers to a sub-class of content-based image retrieval problems where the input queries are ambiguous sketches and the retrieval repository is a database of natural images. In the zero-shot setup of SBIR, the query sketches are drawn from classes that do not match any of those that were used in model building. The SBIR task is extremely challenging as it is a cross-domain retrieval problem, unlike content-based image retrieval problems because sketches and images have a huge domain gap. In this work, we propose an elegant retrieval methodology, StyleGen, for generating fake candidate images that match the domain of the repository images, thus reducing the domain gap for retrieval tasks. The retrieval methodology makes use of a two-stage neural network architecture known as the stacked Siamese network, which is known to provide outstanding retrieval performance without losing the generalizability of the approach. Experimental studies on the image sketch datasets TU-Berlin Extended and Sketchy Extended, evaluated using the mean average precision (mAP) metric, demonstrate a marked performance improvement compared to the current state-of-the-art approaches in the domain.