Multiple Queries Research Articles

Leakage-Suppressed Range Query Scheme for Structured Data in IoT

The structured data collected by the Internet of Things can be encrypted for protecting the user’s privacy. Range query can be used to get the expected data with some specific attributes among the encrypted data, that is, given the upper and lower limits <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(x, y)$</tex-math></inline-formula> of a certain attribute, the range query will get all the records whose corresponding attribute values are in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(x, y)$</tex-math></inline-formula> . However, in the structured encryption scheme with range query, there is a certain amount of information leakage, which will lead to the so-called inference attacks, i.e., the attacker can obtain the user’s attribute values. To hide attribute values and their relationship, this article transformed the problem of the numerical comparison between two attribute values into the problem of the intersection of two sets. By using the Bloom filter, the elements in the attribute value collection are recorded and determined whether the intersection of the two sets is empty. This ensures that our scheme effectively resists inference attacks. Besides, by multiplying the endpoints of the range interval by a large number, we gave an improved scheme to hide the user’s search pattern. In the query process, our scheme will not leak the upper and lower limits of the range value and will not leak the relationship between the attribute value and the range interval. This will prevent the attacker from inducing the relationship of attribute values by multiple range queries. Finally, we conducted a simulation evaluation of the scheme by using the published novel coronavirus pneumonia data, and the results show that our scheme has a better performance than the existing schemes.

LoCoMOBO: A Local Constrained Multiobjective Bayesian Optimization for Analog Circuit Sizing

A local constrained multiobjective Bayesian optimization (LoCoMOBO) method is introduced to address automatic sizing and tradeoff exploration for analog and RF integrated circuits (ICs). LoCoMOBO applies to constrained optimization problems utilizing multiple Gaussian process (GP) models that approximate the objective and constraint functions locally in the search space. It searches for potential pareto optimal solutions within trust regions of the search space using only a few time-consuming simulations. The trust regions are adaptively updated during the optimization process based on feasibility and hypervolume metrics. In contrast to mainstream Bayesian optimization approaches, LoCoMOBO uses a new acquisition function that can provide multiple query points, therefore allowing for parallel execution of costly simulations. GP inference is also enhanced by using GPU acceleration in order to handle highly constrained problems that require large sample budgets. Combined with a framework for schematic parametrization and simulator calls, LoCoMOBO provides improved performance tradeoffs and sizing results on three real-world circuit examples, while reducing the total runtime up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times 43$ </tex-math></inline-formula> times compared to state-of-the-art methods.

ZQBA: A Zero-Query, Boosted Ambush Adversarial Attack on Image Retrieval

Content Based Image Retrieval (CBIR) Systems have been employed in a wide variety of critical applications such as intellectual property management [47], facial recognition [46], and inappropriate content detection [48]. Most CBIRs are vulnerable to adversarial attacks, where small, imperceptible perturbations to input images cause system failure. In this paper, we propose a zero-query, black-box adversarial attack method that simulates an attack setting where the attacker has no knowledge about the CBIR model architecture and is unable to make multiple queries. The proposed method uses an ensemblebased approach, generating one perturbation for an input image that severely hinders the ability of six different CBIR models. Our approach is successfully able to disrupt the relevance of our target image retrieval models with a 65% decrease in Mean Average Precision (mAP) as compared to state-of-the-art UAP [18]. We hope our method serves as a baseline for the evaluation of robustness for future image retrieval research.

Decentralized Personal Data Marketplaces: How Participation in a DAO Can Support the Production of Citizen-Generated Data.

Big Tech companies operating in a data-driven economy offer services that rely on their users’ personal data and usually store this personal information in “data silos” that prevent transparency about their use and opportunities for data sharing for public interest. In this paper, we present a solution that promotes the development of decentralized personal data marketplaces, exploiting the use of Distributed Ledger Technologies (DLTs), Decentralized File Storages (DFS) and smart contracts for storing personal data and managing access control in a decentralized way. Moreover, we focus on the issue of a lack of efficient decentralized mechanisms in DLTs and DFSs for querying a certain type of data. For this reason, we propose the use of a hypercube-structured Distributed Hash Table (DHT) on top of DLTs, organized for efficient processing of multiple keyword-based queries on the ledger data. We test our approach with the implementation of a use case regarding the creation of citizen-generated data based on direct participation and the involvement of a Decentralized Autonomous Organization (DAO). The performance evaluation demonstrates the viability of our approach for decentralized data searches, distributed authorization mechanisms and smart contract exploitation.

Overlook: Differentially Private Exploratory Visualization for Big Data

Data exploration systems that provide differential privacy must manage a privacy budget that measures the amount of privacy lost across multiple queries. One effective strategy to manage the privacy budget is to compute a one-time private synopsis of the data, to which users can make an unlimited number of queries. However, existing systems using synopses are built for offline use cases, where a set of queries is known ahead of time and the system carefully optimizes a synopsis for it. The synopses that these systems build are costly to compute and may also be costly to store.&#x0D; We introduce Overlook, a system that enables private data exploration at interactive latencies for both data analysts and data curators. The key idea in Overlook is virtual synopsis that can be evaluated \emph{incrementally}, without extra space storage or expensive precomputation. Overlook simply executes queries using an existing engine, such as a SQL DBMS, and adds noise to their results. Because Overlook's synopses do not require costly precomputation or storage, data curators can also use Overlook to explore the impact of privacy parameters interactively. Overlook offers a rich visual query interface based on the open source Hillview system. Overlook achieves accuracy comparable to existing synopsis-based systems, while offering better performance and removing the need for extra storage.

Hardware-Algorithm Codesign for Fast and Energy Efficient Approximate String Matching on FPGA for Computational Biology.

Myers bit-vector algorithm for approximate string matching (ASM) is a dynamic programming based approach that takes advantage of bit-parallel operations. It is one of the fastest algorithms to find the edit distance between two strings. In computational biology, ASM is used at various stages of the computational pipeline, including proteomics and genomics. The computationally intensive nature of the underlying algorithms for ASM operating on the large volume of data necessitates the acceleration of these algorithms. In this paper, we propose a novel ASM architecture based on Myers bit-vector algorithm for parallel searching of multiple query patterns in the biological databases. The proposed parallel architecture uses multiple processing engines and hardware/software codesign for an accelerated and energy-efficient design of ASM algorithm on hardware. In comparison with related literature, the proposed design achieves 22× better performance with a demonstrative energy efficiency of ∼500×109 cell updates per joule.

Privacy Analysis of Query-Set-Size Control

The publication of user data for statistical analysis and research can be extremely beneficial for both academic and commercial uses, such as statistical research and recommendation systems. To maintain user privacy when such a publication occurs many databases employ anonymization techniques, either on the query results or the data itself. In this article, we examine and analyze the privacy offered when using the query-set-size control method for aggregate queries over a data structures representing various topologies. We focus on the mathematical queries of minimum, maximum, median, and average and show some query types that may be used to extract hidden information. We prove some combinations of these queries will maintain a measurable level of privacy even when using multiple queries. We offer a privacy probability measure, indicating the probability of an attacker to obtain information defined as sensitive by utilizing legitimate queries over such a system. Our results are mathematically proven and backed by simulations using vehicular network data based on the TAPASCologne project.

Query complexity of unitary operation discrimination

Discrimination of unitary operations is fundamental in quantum computation and information. A lot of quantum algorithms including the well-known Deutsch–Jozsa algorithm, Simon’s algorithm, and Grover’s algorithm can essentially be regarded as discriminating among individual, or sets of unitary operations (oracle operators). The problem of discriminating between two unitary operations U and V can be described as: Given X∈{U,V}, determine which one X is. If X is given with multiple copies, then one can design an adaptive procedure that takes multiple queries to X to output the identification result of X. In this paper, we consider the problem: How many queries are required for achieving a desired failure probability ϵ of discrimination between U and V. We prove in a uniform framework: (i) if U and V are discriminated with bound error ϵ , then the number of queries T must satisfy T≥21−4ϵ(1−ϵ)Θ(U†V), and (ii) if they are discriminated with one-sided error ϵ, then there is T≥21−ϵ2Θ(U†V), where ⌈k⌉ denotes the minimum integer not less than k and Θ(W) denotes the length of the smallest arc containing all the eigenvalues of W on the unit circle.

A Research &amp; Development Model of Resource Mapping for Livelihood Planning

The envisioned R&amp;D Model of Resource Mapping for Livelihood Planning is based on the experience gained in a survey-based research work on resource mapping for livelihood planning, conducted in the backward district of Purulia (West Bengal, India) in 2018-20. The research work identified some parameters and attributes associated in the villagelevel resource mapping work, and highlighted the scope of the application of information technology in the work process through analysis of geo-referenced data – to render an extra edge in real time analysis. The research work produced a combined database having 67 baselevel attributes, containing spatial and non-spatial data of the area of study comprising of 606 mouzas. It was felt that such database, when powered with GIS-enabled search engine and WebGIS infrastructure, may generate huge volume of strategic just-in-time information, which when linked with e-governance mechanism of the government, may help promote livelihood at the village level through optimal utilization of resources. Technological tools like Geographical Information System (GIS) and Remote Sensing Data Analysis help us to develop spatially connected databases. Such database when combined with strategic non-spatial data-sets may produce a combined database, which once made up to village level, can provide a tremendous boost in the planning and monitoring of activities of social projects of the governments and NGOs, as well as may provide efficient and quality service to the entrepreneurs by way of providing just-in-time information. In livelihood resource mapping work, criteria analysis of resource mapping data can help in extracting relevant information in super-imposed form from multi-layered datasets, through multiple object-based inter-related queries. Four case studies are illustrated in this paper that offer examples of the ways to generate criteria maps for strategic information (along with its dataset) from combined database of GIS, in response to multi-level queries. Such criteria maps provide information on the existing and other socio-economic conditions of the region. Thousands of such multi-level queries may generate numerous Resource Planning Maps and Participatory Planning Maps, useful for livelihood planning and its implementation. Livelihood planning and its implementation at the grass-root level need collaborative efforts at various levels – both the government and non-government institutions may join hands in the fields of survey works, compilation of combined databases, analysis of the data, generating strategic information for livelihood planning, and most important, in the task of livelihood cluster development works at the grass-root level. A participative planning roadmap is given in the concluding note.

Wukong+G: Fast and Concurrent RDF Query Processing Using RDMA-Assisted GPU Graph Exploration

RDF graph has been increasingly used to store and represent information shared over the Web, including social graphs and knowledge bases. With the increasing scale of RDF graphs and the concurrency level of SPARQL queries, current RDF systems are confronted with inefficient concurrent query processing on massive data parallelism. The situation becomes more severe in the face of data-intensive queries (aka heavy query), which usually lead to suboptimal response time (latency) as well as throughput collapse. In this article, we present Wukong+G, the first graph-based distributed RDF query processing system that efficiently exploits the hybrid parallelism of CPU and GPU. Wukong+G is made fast and concurrent with four key designs. First, Wukong+G tames massive random memory accesses in graph exploration by efficiently mapping data between CPU and GPU for latency hiding, including a set of techniques like query-aware prefetching, pattern-aware pipelining and fine-grained swapping. Second, Wukong+G scales up by introducing a GPU-friendly RDF store to support RDF graphs exceeding GPU memory size, by using techniques like predicate-based grouping, pairwise caching and look-ahead replacing to narrow the gap between host and device memory scale. Third, Wukong+G scales out through a communication layer that decouples the transferring process for query metadata and intermediate results, and further leverages both native and GPUDirect RDMA to enable efficient communication on a CPU/GPU cluster. Finally, Wukong+G simultaneously runs multiple queries on a single GPU to improve overall throughput and fully exploits hardware heterogeneity (CPU/GPU) by scheduling a single query on CPU and GPU adaptively. We have implemented Wukong+G by extending a state-of-the-art distributed RDF store (i.e., Wukong) with distributed GPU support. Evaluation on a heterogeneous CPU/GPU cluster with RDMA-capable network shows that Wukong+G outperforms Wukong by up to 9.0× (from 2.3×) and scales well on 10 GPU cards for heavy queries. Wukong+G can also improve both latency and throughput by more than one order of magnitude when facing hybrid workloads.

Measles: Global Indicators and Progress on the road for Achieving and Sustaining Virus Eradication: A Review

Measles morbillivirus is regarded as one of the most influential contagious virus in the timeline of human history. Before the classification of this virus and formulation of early vaccines in the starting 1960s, it was responsible for killing 0.1 – 10 % of every birth cohort. While live-attenuated samples of measles morbillivirus have considerably mitigated fatality rate around 99% in developed states, - 1 million fatalities are nevertheless occurring on yearly basis in the developing states, and multiple queries are awaiting response regarding immune-pathogenesis of measles, the vaccines and correlates of immunity itself. This study analyzes the considerable influence of vaccination uptake brought upon the reduction of measles disease burden all over the world, the foundation of effective vaccines along with their effectiveness and safety profiles, worldwide scenario of vaccination, the economic potential of investment in effective vaccines, the multiple impediments observed in control of measles in modern years, along with the major issues that have to be tackled for achieving a planet free from measles.

SOIT: Segmenting Objects with Instance-Aware Transformers

This paper presents an end-to-end instance segmentation framework, termed SOIT, that Segments Objects with Instance-aware Transformers. Inspired by DETR, our method views instance segmentation as a direct set prediction problem and effectively removes the need for many hand-crafted components like RoI cropping, one-to-many label assignment, and non-maximum suppression (NMS). In SOIT, multiple queries are learned to directly reason a set of object embeddings of semantic category, bounding-box location, and pixel-wise mask in parallel under the global image context. The class and bounding-box can be easily embedded by a fixed-length vector. The pixel-wise mask, especially, is embedded by a group of parameters to construct a lightweight instance-aware transformer. Afterward, a full-resolution mask is produced by the instance-aware transformer without involving any RoI-based operation. Overall, SOIT introduces a simple single-stage instance segmentation framework that is both RoI- and NMS-free. Experimental results on the MS COCO dataset demonstrate that SOIT outperforms state-of-the-art instance segmentation approaches significantly. Moreover, the joint learning of multiple tasks in a unified query embedding can also substantially improve the detection performance. Code is available at https://github.com/yuxiaodongHRI/SOIT.

UR-tree: a spatial index structure for handling multiple point selection queries

uR-tree: a spatial index structure for handling multiple point selection queries

Joint Transcriptome and Metabolome Analysis Prevails the Biological Mechanisms Underlying the Pro-Survival Fight in In Vitro Heat-Stressed Granulosa Cells.

Simple SummaryThis study integrates the differentially expressed genes and important metabolites found in the transcriptome and metabolome analyses of in vitro acute heat-stressed bovine granulosa cells. Proteins and vitamin B catabolism were the most; tryptophan, proline, pyridoxine, and riboflavin (downregulated metabolites in heat stress) were enriched in many joint pathways. Genes AOX1, PYGM, NOS2, and SLC16A3 (all upregulated metabolites in heat stress) were found to have central roles in metabolic changes in response to heat stress. The negative effects of acute heat stress can be attributed to oxidative stress-driven changes at the inflammation metabolism nexus.Previous studies reported the physical, transcriptome, and metabolome changes in in vitro acute heat-stressed (38 °C versus 43 °C for 2 h) bovine granulosa cells. Granulosa cells exhibited transient proliferation senescence, oxidative stress, an increased rate of apoptosis, and a decline in steroidogenic activity. In this study, we performed a joint integration and network analysis of metabolomic and transcriptomic data to further narrow down and elucidate the role of differentially expressed genes, important metabolites, and relevant cellular and metabolic pathways in acute heat-stressed granulosa cells. Among the significant (raw p-value < 0.05) metabolic pathways where metabolites and genes converged, this study found vitamin B6 metabolism, glycine, serine and threonine metabolism, phenylalanine metabolism, arginine biosynthesis, tryptophan metabolism, arginine and proline metabolism, histidine metabolism, and glyoxylate and dicarboxylate metabolism. Important significant convergent biological pathways included ABC transporters and protein digestion and absorption, while functional signaling pathways included cAMP, mTOR, and AMPK signaling pathways together with the ovarian steroidogenesis pathway. Among the cancer pathways, the most important pathway was the central carbon metabolism in cancer. Through multiple analysis queries, progesterone, serotonin, citric acid, pyridoxal, L-lysine, succinic acid, L-glutamine, L-leucine, L-threonine, L-tyrosine, vitamin B6, choline, and CYP1B1, MAOB, VEGFA, WNT11, AOX1, ADCY2, ICAM1, PYGM, SLC2A4, SLC16A3, HSD11B2, and NOS2 appeared to be important enriched metabolites and genes, respectively. These genes, metabolites, and metabolic, cellular, and cell signaling pathways comprehensively elucidate the mechanisms underlying the intricate fight between death and survival in acute heat-stressed bovine granulosa cells and essentially help further our understanding (and will help the future quest) of research in this direction.

Utilizing Google trends to monitor coronavirus vaccine interest and hesitancies

IntroductionVaccine hesitancy remains a serious challenge for ending the coronavirus disease 2019 (COVID-19) pandemic. Digital media has played an immense role in the spread of information during the pandemic. One method to gauge public interest in COVID-19 related information is to examine patterns of online search queries. MethodsGoogle Trends (GT) was used to analyze results for search terms relating to COVID-19 vaccine misinformation, information, and accessibility from October 1st, 2020 to May 27th, 2021. GT allows you to compare multiple queries at one time. The resultant relative search volumes (RSVs)range from 0 to 100. The search term andpoint in time on the graph that has the greatest search volume is given a score of 100 and all other terms and times are given values relative to that maximum. Search interest peaks were analyzed by subgroups (misinformation, information seeking, and access seeking) and across key time points throughout the pandemic. ResultsGT analysis revealed that search interest related to vaccine misinformation, general information, and access seeking changed in relation to events taking place throughout the pandemic. The most commonly searched terms in each subgroup were: “Covid vaccine infertility”, “Covid vaccine side effects”, and “Covid vaccine appointment”. Searches related to misinformation peaked in December 2020. Search terms in the general information category peaked in April 2021. RSVs for access seeking terms peaked in March 2021 and have decreased since April 2021. ConclusionMisinformation RSVs were highest after FDA authorization and have multiple repeated spikes after subsequent vaccine announcements. General information seeking terms peaked concurrently with increased vaccination uptake in the United States. Search interest has decreased with wider vaccine availability, despite many individuals in the United States remaining unvaccinated. GT can be used to monitor trends in public attitudes and misinformation regarding COVID-19 vaccines and further target education.

A Review on the Observed Climate Change in Europe and Its Impacts on Viticulture

The European climate is changing displaying profound impacts on agriculture, thus strongly reaching the scientific community’s attention. In this review, the compilation of selected scientific research on the agroclimatic conditions’ changes and their impact on the productivity parameters (phenology timing, product quality and quantity) of grapevines and on the spatiotemporal characteristics of the viticultural areas are attempted for the first time. For this purpose, a thorough investigation through multiple search queries was conducted for the period (2005–2021). Overall, increasing (decreasing) trends in critical temperature (precipitation) parameters are the reality of the recent past with visible impacts on viticulture. The observed climate warming already enforces emerging phenomena related to the modification of the developmental rate (earlier phenological events, shortening of phenological intervals, lengthening of the growing season, earlier harvest), the alteration of product quality, the heterogeneous effects on grapevine yield and the emergence of new cool-climate viticulture areas highlighting the cultivation’s rebirth in the northern and central parts of the continent. The vulnerability of the wine-growing ecosystem urges the integration of innovative and sustainable solutions for confronting the impacts of climate change and safeguarding the production (quantity and quality) capacity of viticultural systems in Europe under a continuously changing environment.

Stream Processing of Shortest Path Query in Dynamic Road Networks

Shortest path query in road network is pervasive in various location-based services nowadays. As the business expands, the scalability issue becomes severer and more servers are deployed to cope with it. Moreover, as the traffic condition keeps changing over time, the existing index-based approaches can hardly adapt to the real-life dynamic environment. Therefore, batch shortest path algorithms have been proposed recently to answer a set of queries together using shareable computation. Besides, they can also work in a highly dynamic environment as no index is needed. However, the existing batch algorithms either assume the batch queries are finely decomposed or just process them without differentiation, resulting in poor query efficiency. In this work, we assume the traffic condition is stable over a short period and treat the issued queries within that period as a stream of query sets. Specifically, we first propose three query set decomposition methods to cluster one query set into multiple query subsets: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Zigzag</i> that considers the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1-N</i> shared computation; <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Co-Clustering</i> that considers the source and target's spatial locality; and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Search-Space-Aware</i> that further incorporates search space estimation. After that, we propose two batch algorithms that take advantage of the previously decomposed query sets for efficient query answering: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R2R</i> that finds a set of approximate shortest paths from one region to another with bounded error; and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Local Cache</i> that improves the existing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Global Cache</i> with higher cache hit ratio. Finally, we design three efficient stream processing methods for intra-batch shared computation. The experiments on a large real-world query sets verify the effectiveness and efficiency of our decomposition methods compared with the state-of-the-art batch algorithms.

To share or not to share vector registers?

Query execution techniques in database systems constantly adapt to novel hardware features to achieve high query performance, in particular for analytical queries. In recent years, vectorization based on the Single Instruction Multiple Data parallel paradigm has been established as a state-of-the-art approach to increase single-query performance. However, since concurrent analytical queries running in parallel often access the same columns and perform a same set of vectorized operations, data accesses and computations among different queries may be executed redundantly. Various techniques have already been proposed to avoid such redundancy, ranging from concurrent scans via the construction of materialized views to applying multiple query optimization techniques. Continuing this line of research, we investigate the opportunity of sharing vector registers for concurrently running queries in analytical scenarios in this paper. In particular, our novel sharing approach relies on processing data elements of different queries together within a single vector register. As we are going to show, sharing vector registers to optimize the execution of concurrent analytical queries can be very beneficial in single-threaded as well as multi-thread environments. Therefore, we demonstrate the feasibility and applicability of such a novel work sharing strategy and thus open up a wide spectrum of future research opportunities.

Random walk-based algorithm for distance-aware influence maximization on multiple query locations

The problem with distance-aware influence maximization on multiple query locations (DIM-MQL) is selecting a group of nodes in the network to influence the nodes in the widest range possible near multiple query locations. A random walk-based algorithm for the DIM-MQL problem is presented. To accelerate query processing in real-time, our method involves offline and online processing. Offline processing conducts computations that are independent of the queries, and online processing answers queries in real-time. For offline processing, an algorithm is presented to estimate the upper and lower bounds of the influence spreading of the nodes based on a set of anchor points. We propose an algorithm to sample the influence spreading paths and estimate the influence spreading of the nodes. The number of samples required is analyzed and estimated. Based on the random walk approach, an algorithm is proposed to select anchor points by partitioning the nodes into groups. An algorithm is presented for seed selection in online processing. Based on the spreading bounds obtained in offline processing, a pruning technique is employed to accelerate query processing. Our empirical results show that the proposed algorithm can obtain a larger distance-aware influence spreading than other approaches.

A novel multilabel video retrieval method using multiple video queries and deep hash codes

AbstractMost videos consist of multiple clips. Namely, videos usually have multiple spatio‐temporal information. However, existing video datasets are of single video clips. Additionally, content‐based video retrieval methods have been implemented based on a single query clip. However, a single query may not be sufficient for better expressing intention concerning the query. Besides, it narrows the capability to search for multiple semantics. How to deal with retrieving videos having multiple clips has not been adequately investigated. This study proposes a novel multilabel video retrieval method that utilizes multiple video clips as queries. Whatever the number of queries, it transforms a multi‐query video retrieval into a single‐query video retrieval. The method is independent of both the video features and distance metric types. However, we propose a deep video hashing method to achieve speed and efficiency. Experiments performed on three prepared multilabel video datasets have proven the effectiveness of the proposed method. The source codes of the study are public.