• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Articles
  • PACTraD: Multi-Task Benchmark and Domain-Specific Attention Mechanism for Wildlife Classification, Detection, and Segmentation in Protected Area Camera Trap Data
  • 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
November 17, 2026
Physicists Show How a Solvent Shapes the Response of Drug Molecules
Many drug molecules can switch between different three-dimensional shapes. Using a mathematical model of ibuprofen dissolved in supercritical CO₂, researchers from HSE University and the Institute of Solution Chemistry of the Russian Academy of Sciences have shown that the solvent can make these molecules appear to respond unusually slowly. The molecules themselves continue to change shape rapidly, but their surroundings rearrange much more slowly, and this lag shows up in the measurements. The study has been published in The Journal of Chemical Physics. 
November 10, 2026
Physicists Train AI to Optimise Particle Beams in Accelerators
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science and the Budker Institute of Nuclear Physics at the Siberian Branch of the Russian Academy of Sciences have developed RLABC (Reinforcement Learning for Accelerator Beamline Control), a framework that uses reinforcement learning to identify optimal settings for a particle accelerator. In a computer simulation, RLABC optimised the accelerator's parameters to achieve a particle transmission rate of 70%. The study has been published in Computer Physics Communications.
November 9, 2026
'Organ-on-a-Chip Technology Could Eliminate the Need for Animal Testing'
The Laboratory of Molecular Physiology at the HSE Faculty of Biology and Biotechnology investigates how molecular regulators known as microRNAs control gene expression and contribute to the development of diseases, including cancer, viral and inflammatory conditions, and pregnancy complications. At HSE University, researchers develop organ-on-a-chip models: miniature devices containing living cells that mimic the functions of human organs, such as the placenta and intestines. These models help researchers understand how diseases develop and how drugs affect them. HSE News Service spoke with Evgeny Knyazev, Head of the Laboratory.

 

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

?

PACTraD: Multi-Task Benchmark and Domain-Specific Attention Mechanism for Wildlife Classification, Detection, and Segmentation in Protected Area Camera Trap Data

Big Data and Cognitive Computing. 2026. Vol. 10. No. 11. P. 1–52.
Aleksei Samarin, Nazarenko A., Nazarenko D., Afonina J., Kotenko E., Dozortseva A., Mamaeva A., Alexander Savelev, Narova G., Elena Mikhailova, Motyko A., Babina S., Valentin Malykh

Camera traps are a key tool for non-invasive wildlife monitoring, yet models trained on existing benchmarks often generalize poorly to new regions due to domain shift, class imbalance, and natural variability in illumination, season, and background. We introduce PACTraD, a benchmark of 116,973 annotated camera trap images collected in a protected area of the Baikal region across eight classes (deer, no_animals, bear, boar, hare, badger, lynx, wolf), with a pronounced long-tailed distribution (deer: 73.1%; lynx and wolf: 0.3% and 0.2%) and substantial seasonal and lighting variability, including infrared night imagery. The benchmark supports three tasks under a unified, reproducible protocol: classification, object detection, and semantic segmentation. We further propose a domain-specific attention mechanism augmenting self-attention with eleven learnable priors capturing contour, foreground/background separation, bilateral symmetry, discriminative part regions, texture frequency, confidence weighting, motion consistency, gradient enhancement, scale, color invariance, and shape compactness. Evaluated on six backbones for classification and detection and five for segmentation, against no-attention baselines and three generic attention modules (SE, SA, CBAM), it consistently performs best, raising weighted F1 for classification from 0.943 to 0.964 (DINOv3), AP50 for detection from 0.876 to 0.903 (InternImage-H), and mIoU for segmentation from 0.805 to 0.834 (SegMAN), with component-level ablations revealing task-specific contributions of each prior. However, performance on rare species remains limited (macro F1: 0.829 for classification), indicating that further research is needed to address long-tail recognition in camera trap data.

Research target: Mathematics Computer Science
Language: English
DOI
Text on another site
Keywords: computer visionimage segmentationobject detectionmulti-task learningWildlife monitoringcamera trapswildlife classificationdomain-specific attention
Similar publications
The medial septum model as a pacemaker of theta rhythm: the key role of short-term synaptic plasticity
Mysin I. E., Dubrovin S. V., Cognitive Neurodynamics 2026 Vol. 20 No. 191 P. 1–30
The hippocampal theta rhythm is crucial for memory and navigation. It is paced by parvalbumin-expressing GABAergic neurons in the medial septum. These neurons segregate into two subpopulations—Teevra and Komal cells—which fire in anti-phase bursts at theta frequency, with a stable phase shift of approximately 150 degrees, and exhibit mutual inhibition. While essential, the network mechanism ...
Added: November 14, 2026
Траектории ставок как сигнал сговора: LSTM-классификация аукционов государственных закупок
Ефимов К. Д., Журнал Новой экономической ассоциации 2026 № 72 С. 105–114
This study proposes a method for automatic detection of collusive behavior in electronic public procurement auctions based on analysis of the full bid trajectory. The empirical dataset comprises 508 auction histories from 2016–2020 collected from the RTS tender e-procurement platform; the positive class is labeled using case materials of the Federal Antimonopoly Service (FAS Russia), ...
Added: November 13, 2026
Model-Dependent Prompt-Component Ablation for Medical LLM Decision Support: Application to ENT Biologics Screening
Sergey N. Koltcov, Budkovaia M., Surkov A. et al., IEEE Journal of Biomedical and Health Informatics 2026 P. 1–10
Large language models (LLMs) show promise for clinical decision support, but privacy constraints and unreliable free-text decisions limit deployment. We present Medotor, a locally deployed system for screening patients with chronic rhinosinusitis with nasal polyps (CRSwNP) for biologic therapy, and evaluate prompt design on 163 retrospective cases (132 eligible and 31 ineligible). Five models were ...
Added: November 13, 2026
Upper Bound for Permanent Saturation of Metric Graphs using Interval Exchange Transformations
Ермолаев Е. С., Chernyshev V. L., Skripchenko A., Journal of Nonlinear Science 2026 Vol. 36 No. 122 (2026) P. 1–37
We study upper bounds for the moment of permanent -saturation in finite metric graphs. The dynamics is generated by moving points travelling with unit speed along edges and branching into all outgoing directions whenever they reach a vertex. We first reformulate this branched dynamics in terms of birth times at vertices and prove a sufficient ...
Added: November 12, 2026
Impact of 5G NR-V2X Message Losses on Connected Vehicle Warning Functions
Физулин А. В., Stepanyants V., Amerikanov A. et al., FUTURE TRANSPORTATION 2026 Vol. 6 No. 6 Article 264
Cooperative warning functions depend on whether V2X information becomes available in time to influence vehicle control. This article presents an event-based co-simulation framework coupling SUMO, ns-3 (ms-van3t), 5G-LENA NR sidelink and application records, with Sionna RT enabled for the intersection scenario. In 140 emergency-vehicle-warning runs, reducing mean packet reception ratio (PRR) from 0.9412 to 0.0675 ...
Added: November 12, 2026
On β-function of 𝒩 = 2 supersymmetric integrable sigma models. Part II
Alfimov Mikhail, Kurakin Andrey, Journal of High Energy Physics 2026 Vol. 2026 Article 99
We continue studying regularization scheme dependence of the 𝒩 = 2 supersymmetric sigma models. In the present work the previous result for the four loop β-function is extended to the five loop order. Namely, we find the renormalization scheme, in which the fifth loop contribution is completely eliminated, while the fourth loop contribution is represented ...
Added: November 12, 2026
Kripke Completeness For Predicate Modal Logics Of Bounded Alternativity: First Steps
Shehtman V. B., Shkatov D., Review of Symbolic Logic 2026 Vol. 19 No. 4 P. 859–882
We study Kripke completeness for predicate modal logics with propositional axioms of bounded alternativity corresponding to the condition on Kripke frames that every world sees at most n worlds. We prove that minimal predicate modal logics with axioms of bounded alternativity, as well as their extensions with the axiom of reflexivity, are strongly Kripke complete, whereas the ...
Added: November 12, 2026
On flexibility of trinomial varieties
Ignatev M., Vilkin T., Mediterranean Journal of Mathematics 2026 Vol. 23 No. 2 Article 70
Trinomial varieties are affine varieties given by a system of equations consisting of polynomials with three terms. Such varieties are total coordinate spaces of normal varieties with torus action of complexity one. For an affine variety X, we consider the subgroup SAut(X) of the automorphism group generated by all algebraic subgroups isomorphic to the additive ...
Added: November 12, 2026
Линейные отображения, сохраняющие матрицы с n или n − 1 различными собственными значениями
Maksaev A., Promyslov V., Тишутин П. С., Записки научных семинаров ПОМИ РАН 2026 Т. 554 С. 218–235
Let K be an algebraically closed field and let ℰₖ be the set of n × n matrices over K with exactly k distinct eigenvalues. Previously, the classification of linear maps T: Mₙ(K) → Mₙ(K) satisfying T(ℰₙ) ⊆ ℰₙ was obtained for invertible maps over fields of characteristic 0. In this paper, the classification is ...
Added: November 11, 2026
Nonexistence of Energy Function for Surface Diffeomorphisms with Nontrivial Basic Sets of Serpentine Geometric Type
Barinova M., Tirskaya Karina, Владикавказский математический журнал 2026 Vol. 28 No. 3 P. 25–43
In this paper, the problem of the existence of an energy function for discrete dynamical systems defined by structurally stable diffeomorphisms is studied. For the considered class of dynamical systems, such a function is defined as a continuous function that decreases along the orbits of the system outside the non-wandering set and remains constant on ...
Added: November 11, 2026
О статистических свойствах наилучших диофантовых приближений
Illarionov A., Математический сборник 2026 Т. 217 № 11 С. 56–87
Let $b(\alpha;T)$ be the number of best simultaneous Diophantine approximations with common denominator $\le T$ to the point $\alpha \in {\Bbb R}^n$. We derive asymptotic formulas for the mean value of this quantity (averaging is performed over all rational points of the form $\alpha = (k_1/N,\ldots, k_n/N)$, $N\le R$), as well as for its mathematical ...
Added: November 10, 2026
Structural model of decision support system for sustainable development of oil and gas companies
Stoianova A. D., Trofimets V. Y., Matrokhina K. V., International Journal of Engineering, Transactions A: Basics 2025 Vol. 38 No. 4 P. 701–709
The article considers the issue of managerial decision-making in an oil and gas company, which is related to the class of multi-criteria choice problems. To improve the validity of decisions in the context of companies’ sustainable development it is proposed to implement a Decision Support System (DSS). A brief review of the existing methods of ...
Added: November 10, 2026
К теореме Гудмана-Штрауса
Vereshchagin N., Математический сборник 2026 Т. 217 № 10 С. 3–46
Теорема Гудмана-Штрауса утверждает, что для “почти всякой” подстановки семейство подстановочных замощений софично, т.е. может быть задано локальными правилами для некоторой раскраски плиток. Условия на подстановку, гарантирующие софичность, довольно сложные. В настоящей работе мы предлагаем версию теоремы Гудмана-Штрауса с более простыми условиями на подстановку. Хотя эти условия достаточно ограничительны, мы показываем, что в сочетании с двумя простыми приемами (взятием достаточно ...
Added: November 10, 2026
EdFitter: a hybrid course recommendation system using large language models
Sergei Koltcov, Ryumin D., Alexandr Axyonov et al., PeerJ Computer Science 2026 Article 12:e4141
Educational institutions face increasing pressure to adapt their curricula to the rapidly evolving demands of the job market, and recommender systems can be important tools to guide students in selecting courses that align with their career goals. We present EdFitter, a hybrid course recommendation system that combines pretrained text embeddings for retrieval with large language ...
Added: November 10, 2026
Assessing density equilibration in confined Liquid–Liquid interfaces
Guskov T., Gerke K., Kondratyuk N. et al., Molecular Simulation 2026 Vol. 52 No. 7 P. 546 – 555
Equilibration is often assumed rather than tested in molecular dynamics studies of confined liquid–liquid interfaces, even though different physical properties may relax on different time scales. In this work, equilibration is examined using an automated truncation method based on the marginal standard error rule. Interfacial geometry, wetting behaviour, and density-related properties are analysed for liquid–liquid ...
Added: November 10, 2026
Influence of nuclear quantum effects on metastable states of warm dense hydrogen
Lukyanchuk V., Norman G., Kondratyuk N. et al., Scientific Reports 2026 Vol. 16 No. 1 Article 16435
Previously, it has been effectively shown that nuclear quantum effects (NQE) considerably influence the prediction of the warm dense hydrogen phase diagram. Here, we study the influence of NQE on the parameters of the conducting state formation in warm dense hydrogen using path integral molecular dynamics (PIMD) within the framework of the finite temperature density ...
Added: November 10, 2026
Machine Learning and Knowledge Discovery in Databases. Research Track and Applied Data Science Track. European Conference, ECML PKDD 2026, Naples, Italy, September 7–11, 2026, Proceedings
Cham: Springer, 2027.
This volume is Part VIII of the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2026, held in Naples, Italy, September 7–11, 2026. It contains 40 papers from the Research Track and the Applied Data Science Track and is published as volume 16948 of Lecture Notes in ...
Added: November 9, 2026
Artificial Intelligence for Software Engineering (AI4SE): A Review of Capabilities, Evaluation, and Verification Challenges
Avdoshin S.M., Pesotskaya E.Y., Proceedings of the Institute for System Programming of the RAS 2026 Vol. 38 No. 6, part 2 P. 133–146
Artificial intelligence has significantly reshaped contemporary software engineering practice, changing how software systems are designed, implemented, tested, and maintained. Recent advances in large language models and AI-assisted development tools have expanded the role of AI from supporting isolated tasks to participating in multiple stages of the software lifecycle. In many development settings, software is now created from high-level specifications ...
Added: November 8, 2026
MFL-ScrollNet: Recurrent Sliding-Window Detection for Panoramic Pipeline Magnetic Flux Leakage Images
Aleksei Samarin, Belous F., Торопов А. Г. et al., Technologies 2026 Vol. 14 No. 11 P. 1–21
Abstract Automated interpretation of magnetic flux leakage (MFL) data is central to condition assessment of long-distance oil and gas pipelines. Yet, full-resolution panoramas are difficult to process without either suppressing small anomalies through resizing or fragmenting elongated objects at sliding-window boundaries. We propose MFL-ScrollNet, a recurrent sliding-window detector that formulates panoramic analysis as an ordered sequence ...
Added: November 8, 2026
PULSE: Psychological Characteristics Unified Learning via Speech-based Estimation
Abdulkhadirov T., Ryumina E., Ryumin D. et al., Expert Systems with Applications 2026 Vol. 334 P. 1–29
Assessing human psychological characteristics from speech requires models that can jointly capture affective states, expressive behavior, and relatively stable personality traits. However, most existing speech-based frameworks address isolated tasks and use separate task-specific models. This leads to model proliferation and complicates inference in real-world intelligent systems. Unified models are also difficult to develop because few ...
Added: November 3, 2026
A Multi-Feature Fusion Deep Neural Network with Attention for Multi-Task Crop Monitoring
Obsie E. Y., Zhan Y., Liu Y., Engineering Research Express 2026 Article 7
Maintaining plant health is crucial for crop quality, food security, and agricultural productivity. Although deep learning methods have shown strong potential for species, disease, and severity classification, most existing approaches tackle these tasks separately, failing to exploit shared representations and interdependencies among them. Furthermore, the variability of disease symptoms, such as subtle differences in size, ...
Added: October 22, 2026
A Reproducible Microscopy Acquisition Pipeline and Microscopy-Aware Attention for Classification, Detection, and Segmentation of Microorganisms
Aleksei Samarin, Nazarenko A., Nazarenko D. et al., Machine Learning and Knowledge Extraction 2026 Vol. 8 No. 10 Article 330
Automated microscopic image analysis is essential for quantitative microbiology, yet manual acquisition and generic recognition models struggle with morphological variability and scene artifacts. We address both ends of this pipeline. First, we present a low-cost, open-source acquisition system, based on an Arduino UNO R3 microcontroller and NEMA 17 stepper motors, that automates focusing, magnification, and ...
Added: October 14, 2026
РАСПОЗНАВАНИЕ РУКОПИСНЫХ ГРАФИЧЕСКИХ ЭЛЕМЕНТОВ И МУЛЬТИЯЗЫЧНОГО ТЕКСТА: ОБЗОР СОВРЕМЕННЫХ ПОДХОДОВ, БАЗОВЫЙ МЕТОД И ПЕРСПЕКТИВЫ РАЗВИТИЯ
Piskunova A., Korolev D., Скопин Н. Ю. et al., В кн.: ГрафиКон 2025 : материалы 35-й Международной конференции по компьютерной графике и машинному зрению (Россия, Йошкар-Ола, 30 сентября – 2 октября 2025 г.).: Йошкар-Ола: Поволжский государственный технологический университет, 2025. С. 659–669.
This article presents an overview of modern methods for solving the problem of recognizing handwritten content, including multilingual text (Russian and English) and graphical elements such as block diagrams consisting of rectangles and arrows, with a focus on the recognition of whiteboard images. For multilingual handwritten text, architectures capable of processing multiple languages are considered, ...
Added: October 9, 2026
Automated Ranking of Soybean Plots from Close-Range RGB Video via Depth Filtering and Point-Based Counting
Teterin N., Slastnikov S., Rybakov Petr et al., Sensors 2026 Vol. 26 No. 19 Article 6171
Manual assessment of soybean yield components, such as pod number, is laborious, time-consuming, and subjective. Existing computer-vision approaches based on object detection or instance segmentation perform poorly on close-range RGB imagery of soybean canopies due to severe occlusions, ambiguous plant boundaries, and the high cost of bounding-box annotation. To address these challenges, we propose a ...
Added: October 7, 2026
  • 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