• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Books
  • 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
May 14, 2026
Resource Race and Green Transition: Three Unexpected Conclusions from Foresight Centres Research on Climate and Poverty
Beneath the surface of green energy—which most people associate with solar panels, electric vehicles, and reduced CO2 emissions—lies a complex web of geopolitical interests, international inequality, and resource constraints. Researchers from the Laboratory for Science and Technology Studies (LST) at the HSE ISSEK Foresight Centre have published a series of articles in leading international journals on hidden and overt conflicts surrounding critically important metals and minerals, as well as related processes in the energy sector.
May 13, 2026
Immersion in Second Language Environment Influences Bilinguals Perception of Emotions
Researchers at the Cognitive Health and Intelligence Centre at the HSE Institute for Cognitive Neuroscience have discovered how bilingual individuals process emotional words in their native (first) and non-native (second) languages. It was found that the link between word meaning and bodily sensations is weaker in a second language than in a first language. However, the more a person is immersed in a language environment, the smaller this difference becomes. The article has been published in Language, Cognition and Neuroscience.
May 12, 2026
‘Any Real-Economy Company Can Use Our Products
The HSE Centre for Financial Research and Data Analytics combines fundamental and applied work, including in areas unique to Russia such as the connection between sentiment in the media and social networks and financial markets. The HSE News Service spoke with the centre’s director, Professor Tamara Teplova, about its work.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings

Springer, 2018.
Under the general editorship: V. Ferrari, M. Hebert, C. Sminchisescu, Y. Weiss

The sixteen-volume set comprising the LNCS volumes 11205-11220 constitutes the refereed proceedings of the 15th European Conference on Computer Vision, ECCV 2018, held in Munich, Germany, in September 2018.

The 776 revised papers presented were carefully reviewed and selected from 2439 submissions. The papers are organized in topical sections on learning for vision; computational photography; human analysis; human sensing; stereo and reconstruction; optimization; matching and recognition; video attention; and poster sessions.

Chapters
Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors
Babenko A., Baranchuk D., Malkov Y., , in: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings.: Springer, 2018. P. 1–15.
This work addresses the problem of billion-scale nearest neighbor search. The state-of-the-art retrieval systems for billion-scale databases are currently based on the inverted multi-index, the recently proposed generalization of the inverted index structure. The multi-index provides a very fine-grained partition of the feature space that allows extracting concise and accurate short-lists of candidates for the ...
Added: October 30, 2018
Priority areas: IT and mathematics
Language: English
DOI
Text on another site
Keywords: semanticsneural networkslearning algorithmscomputer visionface recognitionimage segmentationsensorsobject detectionartificial intelligenceimage codingimage reconstructionimaging systemsobject recognitionsensor networksimage processing
15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings
Similar publications
MinMAE calibration method for convolutional neural network quantization
Vasilev A., Kapitanov A., Solovyev Roman A. et al., PeerJ Computer Science 2026 Vol. 12 Article 3724
This article introduces MinMAE, a novel activation calibration method for Post-Training Quantization (PTQ) that significantly reduces accuracy loss in Convolutional Neural Networks (CNN). Motivated by the need for high-fidelity quantization without costly retraining, MinMAE directly minimizes the Mean Absolute Error (MAE) between original and dequantized activations, making it robust to outliers that degrade standard methods. ...
Added: May 3, 2026
Правовой режим объектов, созданных искусственным интеллектом: обзор зарубежной практики
Kirsanova E., Pakshin P., Право и экономика 2026 № 3 (456) С. 26–34
The article examines the legal regime of intellectual property created by artificial intelligence. Changes to the existing legal framework towards recognizing artificial intelligence as a legal entity would violate the rationale and fundamental principles of the intellectual property rights system. This article provides an overview of different views on the rationale for granting copyright to ...
Added: April 28, 2026
Natural hazard database from Internet publications: text mining with a large language model
Derkacheva A., Sakirkina M., Kraev G. et al., /. 2026.
Comprehensive data on natural hazards and their consequences are crucial for effective for risk assessment, adaptation planning, and emergency response. However, many countries face challenges with fragmented, inconsistent, and inaccessible data, particularly regarding local-scale events. To address this data gap in Russia, we developed an end-to-end processing pipeline that scrapes news from various online sources, ...
Added: April 28, 2026
Intelligent Interfaces and Systems for Human-Computer Interaction
Karpov A., Dvoynikova A., Ryumina E., , in: Lecture Notes in Networks and SystemsVol. 776.: Springer, 2023. P. 3–13.
Abstract. The paper presents a brief review of intelligent interfaces and systems of human-machine interaction. To date, few intelligent interfaces and systems are used in various areas of industry. All the systems of human-machine interaction can be divided into intelligent synthesis and analysis systems. Intelligent synthesis implies the presentation of information from the system to ...
Added: April 25, 2026
Ising models on the hydrogen peroxide and other lattices
Qin X., Deng Y., Shchur L. et al., / Series arXiv "math". 2026. No. 2603.02962.
We perform a Monte Carlo analysis of the Ising model on many three-dimensional lattices. By means of finite-size scaling we obtain the critical points and determine the scaling dimensions. As expected, the critical exponents agree with the three-dimensional Ising universality class for all models. The irrelevant field, as revealed by the correction-to-scaling amplitudes, appears to ...
Added: April 20, 2026
Algorithmic overlaps as thermodynamic variables: from local to cluster Monte Carlo dynamics in critical phenomena
Pilé I., Deng Y., Shchur L., / Series arXiv "math". 2026. No. 2604.10254.
We investigate the spatial overlap of successive spin configurations in Markov chain Monte Carlo simulations using the local Metropolis algorithm and the Svendsen-Wang and Wolff cluster algorithms. We examine the dynamics of these algorithms for two models in different universality classes: the Ising model and the Potts model with three components. The overlap of two ...
Added: April 20, 2026
Investigation of Image Reconstruction Methods for Real-Time Rendering Enhancement: A Case Study in Unity
Belov A. V., Semichasnov I., Matanov K. et al., , in: 2026 ElCon Conference of Young Researchers in Computing & Processing, and Information Security (ElCon-CP).: IEEE, 2026. Ch. 1 P. 4–10.
This paper presents a comparative study of real-time image reconstruction methods implemented in the Unity High Definition Render Pipeline (HDRP). The spatial method CAS and the temporal methods TAAU and FSR 2 are examined. Experiments are conducted at target resolutions of 1920×1080 and 2560×1440 with rendering scales s = 0.67 and s = 0.5 across ...
Added: April 6, 2026
Проблемы семантики и прагматики языковых единиц разных уровней в эпоху больших языковых данных. Сборник трудов Международной научной конференции, посвященной памяти доктора филологических наук, профессора Ольги Павловны Ермаковой
Калуга: ФБГОУ ВПО "Калужский государственный университет им. К.Э.Циолковского", 2025.
В настоящем сборнике представлены доклады ученых-лингвистов из разных стран (России, Беларуси, Молдовы, КНР) по итогам Международной научной конференции, посвященной памяти доктора филологических наук, профессора Ольги Павловны Ермаковой, «Проблемы семантики и прагматики языковых единиц разных уровней в эпоху больших языковых данных», которая проходила на базе Калужского госуниверситета 28 - 30 июня 2025 года и была посвящена ...
Added: April 3, 2026
Using predefined vector systems to speed up neural network multimillion class classification
Gabdullin N., Androsov I., / Series Computer Science "arxiv.org". 2026.
Label prediction in neural networks (NNs) has O(n) complexity proportional to the number of classes. This holds true for classification using fully connected layers and cosine similarity with some set of class prototypes. In this paper we show that if NN latent space (LS) geometry is known and possesses specific properties, label prediction complexity can ...
Added: April 2, 2026
Replacing Criterion of Creativity with Criterion of Investment for Results Created by Artificial Intelligence
Pakshin P., Legal Issues in the Digital Age 2026 Vol. 7 No. 1 P. 32–48
Artificial intelligence plays a significant role in automation, minimizing human intervention in fields such as medicine, art, and law. Despite the historically close relationship between art and technology, generative AI has expanded the potential for creative activity. A significant catalyst for this process has been the proliferation of pre-trained AI systems, which have accelerated the ...
Added: March 31, 2026
HoTPP benchmark: Are we good at the long horizon events forecasting?
Karpukhin I., Shipilov F., Savchenko A., Neurocomputing 2026 Vol. 672 Article 132771
Forecasting multiple future events within a given time horizon is essential for applications in finance, retail, social networks, and healthcare. This problem is typically addressed using Marked Temporal Point Processes (MTPP), which provide a principled framework for modeling both event timing and event labels. While most existing research focuses on predicting only the next event, forecasting distant future ...
Added: February 25, 2026
Textual metaphtonymy as opposed to lexical metaphtonymy
Trofimova N., Pesina S., Vinogradova S. et al., Brazilian Journal of Education, Technology and Society - BRAJETS 2025 Vol. 17 No. 3 P. 126–136
n this article, we have proposed to differentiate textual and lexical metaphtonymy as different phenomena. We have considered the phenomenon of metaphtonymy at the level of text, a chain of words the length of a sentence, a phrase, and a separate meaning. We propose to reserve the term “metaphtonymy” for cases when we are talking ...
Added: February 22, 2026
Когнитивные исследования языка
Тамбов: Тамбовский государственный университет им. Г.Р. Державина, 2025.
"Cognitive Studies of Language" is a leading scientific field and periodical studying language as a cognitive mechanism, a tool for conceptualizing and categorizing the world, storing and processing information. It analyzes the relationship between language, consciousness, and mental processes, including conceptual analysis, frame semantics, and modeling, drawing on the work of Russian and international experts. The ...
Added: February 22, 2026
Определение фолликулярного резерва яичников по данным ультразвукового исследования на основе методов машинного обучения
Moshkin A., Лапутин Ф. А., Сидоров И. В., DIGITAL DIAGNOSTICS 2024 Т. 5 № S1 С. 40–42
BACKGROUND: Ovarian reserve reflects a woman's ability to successfully realize reproductive function. The assessment of ovarian reserve is an urgent task for clinical practice [1] and is important in scientific research. The use of computerized diagnostic image processing methods can accelerate and facilitate the performance of routine tasks in clinical practice. Their use in retrospective ...
Added: February 21, 2026
Multioxide combinatorial libraries: fusing synthetic approaches and additive technologies for highly orthogonal electronic noses
Gohel V. R., Chetyrkina M. R., Gaev A. et al., Lab on a Chip - Miniaturisation for Chemistry and Biology 2024
Added: February 10, 2026
Activation of Wet-Pulled Carbon Nanotube Fibers for Electrochemical Detection of Dopamine
Dmitrieva V. A., Fedorov F. S., Chetyrkina M. R. et al., Journal of Analysis and Testing 2025 Vol. 9 P. 399–404
Carbon nanotube fibers (CNTFs) fabricated using a novel “wet-pulling” technique were evaluated for electrochemical detection of dopamine (DA). To enhance the sensitivity, we employed an electrochemical oxidation pretreatment and twisting of CNTFs and investigated the performance by cyclic voltammetry (CV) and chronoamperometry (CA). The synergetic effect of twisting and pre-oxidation boosted the sensitivity of modified ...
Added: February 10, 2026
Monitoring of meat quality and change-point detection by a sensor array and profiling of bacterial communities
Chetyrkina M. R., Analytica Chimica Acta 2024
Added: February 10, 2026
On the Use of Metaheuristics of Different Classes and an Island Model for Image Steganography
Anna Melman, Mikhail Alexandrov, Oleg Evsutin, , in: 2025 XIХ International Symposium on Problems of Redundancy in Information and Control Systems (Redundancy), 5-7 Nov. 2025.: IEEE, 2025. P. 1–6.
Digital steganography protects the privacy of data by hiding them in some digital containers, such as images. Protection of confidential messages by hiding them in digital images faces the problem of balancing the main performance indicators, i.e. embedding imperceptibility and capacity. Metaheuristic optimization can be used to flexibly customize embedding options, including parameters and locations ...
Added: January 28, 2026
Rendering ‘The Story of God and People’ into Minimal Russian: A Translator’s Commentary
Gladkova A., , in: Explorations in Applied Ethnolinguistics: Words, Cultures, and Global Perspectives.: Palgrave Macmillan, 2025. Ch. 8 P. 149–162.
This chapter is a reflective analysis of the author’s experience of translating The Story of God and People (henceforth: The Story) from Anna Wierzbicka’s book What Christians Believe: The Story of God and People in Minimal English from English into Russian (Wierzbicka, 2019; Vežbickaja, 2021). ...
Added: January 28, 2026
Attribution of de re Propositional Attitudes as a Means of Persuasion
D.B. Tiskin, Frolov K., Herald of the Russian Academy of Sciences 2025 Vol. 95 No. 1 P. 26–33
By de re propositional attitude ascription for rhetorical purposes we will understand uttering a modal statement wherein the speaker deliberately uses a description of the object of an attitude that is knowingly unavailable for the attitude holder. As the existence of the de re rhetorical statement class is revealed, it gives rise to two questions, which will be the primary concern ...
Added: January 26, 2026
Iterative Ricci-Foster Curvature Flow with GMM-Based Edge Pruning: A Novel Approach to Community Detection
Sorokin K., Beketov M., Онучин А. et al., / arxiv.org. Серия cs.SI "Social and Information Networks ". 2025.
Community detection in complex networks is a fundamental problem, open to new approaches in various scientific settings. We introduce a novel community detection method, based on Ricci flow on graphs. Our technique iteratively updates edge weights (their metric lengths) according to their (combinatorial) Foster version of Ricci curvature computed from effective resistance distance between the ...
Added: January 15, 2026
Implementing Transport Coding in OMNeT++ for Message Delay Reduction
Petrovanov I., Sergeev A., / Series Computer Science "arxiv.org". 2025. No. 2512.18332.
Transport coding reduces message delay in packet-switched networks by introducing controlled redundancy at the transport layer:  original packets are encoded into  coded packets, and the message is reconstructed after the first  successful deliveries, effectively shifting latency from the maximum packet delay to the -th order statistic. We present a concise, reproducible discrete-event implementation of transport coding in OMNeT++, including ...
Added: December 24, 2025
РАЗРАБОТКА МОДЕЛИ ЦИФРОВОЙ ЗРЕЛОСТИ ГОСУДАРСТВЕННОГО УПРАВЛЕНИЯ В РЕГИОНАХ РОССИЙСКОЙ ФЕДЕРАЦИИ
Styrin E. M., Вопросы государственного и муниципального управления 2025 № 4 С. 35–60
This article addresses the problem of insuffi cient diagnostic depth in the current approaches to assessing the digital maturity of public administration in the regions of the Russian Federation. The federal methodology proposed by the Ministry of Digital Development focuses on external performance indicators of digital transformation but does not fully reveal the internal organizational capabilities of government agencies. ...
Added: December 23, 2025
Метаэтические основания выравнивания искусственного интеллекта: методологические подходы и их ограничения
Snetkov I., Философия. Журнал Высшей школы экономики 2025 Т. 9 № 3 С. 277–302
The article investigates the alignment problem, which concerns the integration of moral values into the architecture of artificial intelligence (AI) systems to mitigate existential risks. It examines conceptual approaches to addressing the alignment problem, including the utilitarian principles proposed by S. Russell and E. Yudkowsky’s concept of “coherent extrap- olated volition”. The study introduces the ...
Added: December 21, 2025
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit