Search

Generative models of expressive piano performance are usually assessed by comparing their predictions to a reference human performance. A generative algorithm is taken to be better than competing ones if it produces performances that are closer to a human reference performance. However, expert human performers can (and do) interpret music in different ways, making for different possible references, and quantitative closeness is not necessarily aligned with perceptual similarity, raising concerns about the validity of this evaluation approach. In this work, we present a number of experiments that shed light on this problem. Using precisely measured high-quality performances of classical piano music, we carry out a listening test indicating that listeners can sometimes perceive subtle performance difference that go unnoticed under quantitative evaluation. We further present tests that indicate that such evaluation frameworks show a lot of variability in reliability and validity across different reference performances and pieces. We discuss these results and their implications for quantitative evaluation, and hope to foster a critical appreciation of the uncertainties involved in quantitative assessments of such performances within the wider music information retrieval (MIR) community.

Symbolic Music Alignment is the process of matching performed MIDI notes to corresponding score notes. In this paper, we introduce a reinforcement learning (RL)-based online symbolic music alignment technique. The RL agent - an attention-based neural network - iteratively estimates the current score position from local score and performance contexts. For this symbolic alignment task, environment states can be sampled exhaustively and the reward is dense, rendering a formulation as a simplified offline RL problem straightforward. We evaluate the trained agent in three ways. First, in its capacity to identify correct score positions for sampled test contexts; second, as the core technique of a complete algorithm for symbolic online note-wise alignment; and finally, as a real-time symbolic score follower. We further investigate the pitch-based score and performance representations used as the agent's inputs. To this end, we develop a second model, a two-step Dynamic Time Warping (DTW)-based offline alignment algorithm leveraging the same input representation. The proposed model outperforms a state-of-the-art reference model of offline symbolic music alignment.

Compressed sensing is an image reconstruction technique to achieve high-quality results from limited amount of data. In order to achieve this, it utilizes prior knowledge about the samples that shall be reconstructed. Focusing on image reconstruction in nanotomography, this work proposes enhancements by including additional problem-specific knowledge. In more detail, we propose further classes of algebraic inequalities that are added to the compressed sensing model. The first consists in a valid upper bound on the pixel brightness. It only exploits general information about the projections and is thus applicable to a broad range of reconstruction problems. The second class is applicable whenever the sample material is of roughly homogeneous composition. The model favors a constant density and penalizes deviations from it. The resulting mathematical optimization models are algorithmically tractable and can be solved to global optimality by state-of-the-art available implementations of interior point methods. In order to evaluate the novel models, obtained results are compared to existing image reconstruction methods, tested on simulated and experimental data sets. The experimental data comprise one 360{\deg} electron tomography tilt series of a macroporous zeolite particle and one absorption contrast nano X-ray computed tomography (nano-CT) data set of a copper microlattice structure. The enriched models are optimized quickly and show improved reconstruction quality, outperforming the existing models. Promisingly, our approach yields superior reconstruction results, particularly when information about the samples is available for a small number of tilt angles only, Comment: 13 pages, 10 figures

We propose an online 3D semantic segmentation method that incrementally reconstructs a 3D semantic map from a stream of RGB-D frames. Unlike offline methods, ours is directly applicable to scenarios with real-time constraints, such as robotics or mixed reality. To overcome the inherent challenges of online methods, we make two main contributions. First, to effectively extract information from the input RGB-D video stream, we jointly estimate geometry and semantic labels per frame in 3D. A key focus of our approach is to reason about semantic entities both in the 2D input and the local 3D domain to leverage differences in spatial context and network architectures. Our method predicts 2D features using an off-the-shelf segmentation network. The extracted 2D features are refined by a lightweight 3D network to enable reasoning about the local 3D structure. Second, to efficiently deal with an infinite stream of input RGB-D frames, a subsequent network serves as a temporal expert predicting the incremental scene updates by leveraging 2D, 3D, and past information in a learned manner. These updates are then integrated into a global scene representation. Using these main contributions, our method can enable scenarios with real-time constraints and can scale to arbitrary scene sizes by processing and updating the scene only in a local region defined by the new measurement. Our experiments demonstrate improved results compared to existing online methods that purely operate in local regions and show that complementary sources of information can boost the performance. We provide a thorough ablation study on the benefits of different architectural as well as algorithmic design decisions. Our method yields competitive results on the popular ScanNet benchmark and SceneNN dataset.

Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D labeling framework that, without any human intervention, can generate labels for RGB-D scans at equal (or better) level of accuracy than comparable manually annotated datasets such as ScanNet. Our approach is based on an ensemble of state-of-the-art segmentation models and 3D lifting through neural rendering. We demonstrate the effectiveness of our LabelMaker pipeline by generating significantly better labels for the ScanNet datasets and automatically labelling the previously unlabeled ARKitScenes dataset. Code and models are available at https://labelmaker.org

We compare conversion rates of association football (soccer) penalties during regulation or extra time with those during shootouts. Our data consists of roughly 50,000 penalties from the eleven~most recent seasons in European men's football competitions. About one third of the penalties are from more than 1,500 penalty shootouts. We find that shootout conversion rates are significantly lower, and attribute this to worse performance of shooters rather than better performance of goalkeepers. We also find that, statistically, there is no advantage for either team in the usual alternating shooting order. These main findings are complemented by a number of more detailed analyses., Comment: Working paper

This work systematically investigates the oxidation of extra virgin olive oil (EVOO) under accelerated storage conditions with UV absorption and total fluorescence spectroscopy. With the large amount of data collected, it proposes a method to monitor the oil's quality based on machine learning applied to highly-aggregated data. EVOO is a high-quality vegetable oil that has earned worldwide reputation for its numerous health benefits and excellent taste. Despite its outstanding quality, EVOO degrades over time owing to oxidation, which can affect both its health qualities and flavour. Therefore, it is highly relevant to quantify the effects of oxidation on EVOO and develop methods to assess it that can be easily implemented under field conditions, rather than in specialized laboratories. The following study demonstrates that fluorescence spectroscopy has the capability to monitor the effect of oxidation and assess the quality of EVOO, even when the data are highly aggregated. It shows that complex laboratory equipment is not necessary to exploit fluorescence spectroscopy using the proposed method and that cost-effective solutions, which can be used in-field by non-scientists, could provide an easily-accessible assessment of the quality of EVOO.

Nanomechanical sensors based on detecting and tracking resonance frequency shifts are to be used in many applications. Various open- and closed-loop tracking schemes, all offering a trade-off between speed and precision, have been studied both theoretically and experimentally. In this work, we advocate the use of a frequency counter as a frequency shift monitor in conjunction with a self-sustaining oscillator (SSO) nanoelectromechanical system (NEMS) configuration. We derive a theoretical model for characterizing the speed and precision of frequency measurements with state-of-the-art frequency counters. Based on the understanding provided by this model, we introduce novel enhancements to frequency counters that result in a trade-off characteristics which is on a par with the other tracking schemes. We describe a low-cost field-programmable-gate array (FPGA) based implementation for the proposed frequency counter and use it with the SSO-NEMS device in order to study its frequency tracking performance. We compare the proposed approach with the phase-locked-loop based scheme both in theory and experimentally. Our results show that similar or better performance can be achieved at a substantially lower cost and improved ease-of-use. We obtain almost perfect correspondence between the theoretical model predictions and the experimental measurements.

We discuss the synergies between heliospheric and dust science, the open science questions, the technological endeavors and programmatic aspects that are important to maintain or develop in the decade to come. In particular, we illustrate how we can use interstellar dust in the solar system as a tracer for the (dynamic) heliosphere properties, and emphasize the fairly unexplored, but potentially important science question of the role of cosmic dust in heliospheric and astrospheric physics. We show that an Interstellar Probe mission with a dedicated dust suite would bring unprecedented advances to interstellar dust research, and can also contribute-through measuring dust - to heliospheric science. This can, in particular, be done well if we work in synergy with other missions inside the solar system, thereby using multiple vantage points in space to measure the dust as it `rolls' into the heliosphere. Such synergies between missions inside the solar system and far out are crucial for disentangling the spatially and temporally varying dust flow. Finally, we highlight the relevant instrumentation and its suitability for contributing to finding answers to the research questions., Comment: 18 pages, 7 Figures, 5 Tables. Originally submitted as white paper for the National Academies Decadal Survey for Solar and Space Physics 2024-2033

Optimal packing of objects in containers is a critical problem in various real-life and industrial applications. This paper investigates the two-dimensional packing of convex polygons without rotations, where only translations are allowed. We study different settings depending on the type of containers used, including minimizing the number of containers or the size of the container based on an objective function. Building on prior research in the field, we develop polynomial-time algorithms with improved approximation guarantees upon the best-known results by Alt, de Berg and Knauer, as well as Aamand, Abrahamsen, Beretta and Kleist, for problems such as Polygon Area Minimization, Polygon Perimeter Minimization, Polygon Strip Packing, and Polygon Bin Packing. Our approach utilizes a sequence of object transformations that allows sorting by height and orientation, thus enhancing the effectiveness of shelf packing algorithms for polygon packing problems. In addition, we present efficient approximation algorithms for special cases of the Polygon Bin Packing problem, progressing toward solving an open question concerning an O(1)-approximation algorithm for arbitrary polygons., Comment: This is the full version of the same-named paper which will be presented at ESA 2023 conference

Topologically Interlocked Structures (TIS) are structural assemblies that achieve stability and carrying capacity through the geometric arrangement of interlocking blocks, relying solely on normal and friction forces for load transfer. Unlike beam-like TIS, whose deflection never exceeds the height of the blocks, the deflection of slab-like TIS often does. Yet, the upper limit of deflection of slab-like TIS, a key parameter defining their loading energy capacity, remains unexplored. Here, we establish a theoretical upper bound for the deflection capacity of slab-like TIS and outline a systematic design strategy to approach this upper bound. This strategy is based on engineering the contact interfaces such that the non-central blocks are more engaged in the structural response, leading to a more global and holistic deformation mode with higher deflections. We demonstrate the application of this strategy in a numerical case study on a typical slab-like TIS. We show that it leads to a 350$\%$ increase in deflection, yielding a value closer to the upper bound than previously reported in the literature. We also show that the resulting deflection mode engages all the blocks equally, avoids localized sliding modes, and resembles that of monolithic equivalents. Lastly, we show that the strategy not only maximizes the assembly's deflection capacity but also its loading energy capacity.

In nanomechanical photothermal absorption spectroscopy and microscopy, the measured substance becomes a part of the detection system itself, inducing a nanomechanical resonance frequency shift upon thermal relaxation. Suspended, nanometer-thin ceramic or 2D material resonators are innately highly-sensitive thermal detectors of localized heat exchanges from substances on their surface or integrated into the resonator itself. Consequently, the combined nanoresonator-analyte system is a self-measuring spectrometer and microscope: responding to a substances transfer of heat over the entire spectrum for which it absorbs, according to the intensity it experiences. Limited by their own thermostatistical fluctuation phenomena, nanoresonators have demonstrated sufficient sensitivity for measuring trace analyte as well as single particles and molecules with incoherent light or focused and unfocused coherent light. They are versatile in their design, support various sampling methods and hyphenation with other spectroscopic methods, and are capable in a wide range of applications including fingerprinting, separation science, and surface sciences., Comment: perspective article, 23 pages with references, 7 figures

Challenges drive the state-of-the-art of automated medical image analysis. The quantity of public training data that they provide can limit the performance of their solutions. Public access to the training methodology for these solutions remains absent. This study implements the Type Three (T3) challenge format, which allows for training solutions on private data and guarantees reusable training methodologies. With T3, challenge organizers train a codebase provided by the participants on sequestered training data. T3 was implemented in the STOIC2021 challenge, with the goal of predicting from a computed tomography (CT) scan whether subjects had a severe COVID-19 infection, defined as intubation or death within one month. STOIC2021 consisted of a Qualification phase, where participants developed challenge solutions using 2000 publicly available CT scans, and a Final phase, where participants submitted their training methodologies with which solutions were trained on CT scans of 9724 subjects. The organizers successfully trained six of the eight Final phase submissions. The submitted codebases for training and running inference were released publicly. The winning solution obtained an area under the receiver operating characteristic curve for discerning between severe and non-severe COVID-19 of 0.815. The Final phase solutions of all finalists improved upon their Qualification phase solutions.HSUXJM-TNZF9CHSUXJM-TNZF9C

In the evolving landscape of artificial intelligence, multimodal and Neuro-Symbolic paradigms stand at the forefront, with a particular emphasis on the identification and interaction with entities and their relations across diverse modalities. Addressing the need for complex querying and interaction in this context, we introduce SNeL (Structured Neuro-symbolic Language), a versatile query language designed to facilitate nuanced interactions with neural networks processing multimodal data. SNeL's expressive interface enables the construction of intricate queries, supporting logical and arithmetic operators, comparators, nesting, and more. This allows users to target specific entities, specify their properties, and limit results, thereby efficiently extracting information from a scene. By aligning high-level symbolic reasoning with low-level neural processing, SNeL effectively bridges the Neuro-Symbolic divide. The language's versatility extends to a variety of data types, including images, audio, and text, making it a powerful tool for multimodal scene understanding. Our evaluations demonstrate SNeL's potential to reshape the way we interact with complex neural networks, underscoring its efficacy in driving targeted information extraction and facilitating a deeper understanding of the rich semantics encapsulated in multimodal AI models.

Denoising Diffusion Probabilistic Models (DDPMs) have made great strides in generating high-quality samples in both discrete and continuous domains. However, Discrete DDPMs (D3PMs) have yet to be applied to the domain of Symbolic Music. This work presents the direct generation of Polyphonic Symbolic Music using D3PMs. Our model exhibits state-of-the-art sample quality, according to current quantitative evaluation metrics, and allows for flexible infilling at the note level. We further show, that our models are accessible to post-hoc classifier guidance, widening the scope of possible applications. However, we also cast a critical view on quantitative evaluation of music sample quality via statistical metrics, and present a simple algorithm that can confound our metrics with completely spurious, non-musical samples., Comment: In Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI-23), Macau, China

COVID-19 presence classification and severity prediction via (3D) thorax computed tomography scans have become important tasks in recent times. Especially for capacity planning of intensive care units, predicting the future severity of a COVID-19 patient is crucial. The presented approach follows state-of-theart techniques to aid medical professionals in these situations. It comprises an ensemble learning strategy via 5-fold cross-validation that includes transfer learning and combines pre-trained 3D-versions of ResNet34 and DenseNet121 for COVID19 classification and severity prediction respectively. Further, domain-specific preprocessing was applied to optimize model performance. In addition, medical information like the infection-lung-ratio, patient age, and sex were included. The presented model achieves an AUC of 79.0% to predict COVID-19 severity, and 83.7% AUC to classify the presence of an infection, which is comparable with other currently popular methods. This approach is implemented using the AUCMEDI framework and relies on well-known network architectures to ensure robustness and reproducibility.

Understanding light-matter interaction at the nanoscale requires probing the optical properties of matter at the individual nano-absorber level. To this end, we have developed a nanomechanical photothermal sensing platform that can be used as a full spectromicroscopy tool for single molecule and single particle analysis. As a demonstration, the absorption cross-section of individual gold nanorods is resolved from the spectroscopic and polarization standpoint. By exploiting the capabilities of nanomechanical photothermal spectromicroscopy, the longitudinal localized surface plasmon resonance (LSPR) in the NIR range is unravelled and quantitatively characterized. The polarization features of the transversal surface plasmon resonance (TSPR) in the VIS range are also analyzed. The measurements are compared with the finite element method (FEM), elucidating the role played by electron-surface and bulk scattering in these plasmonic nanostructures, as well as the interaction between the nano-absorber and the nanoresonator, ultimately resulting in absorption strength modulation. Finally, a comprehensive comparison is conducted, evaluating the signal-to-noise ratio of nanomechanical photothermal spectromicroscopy against other cutting-edge single molecule and particle spectroscopy techniques. This analysis highlights the remarkable potential of nanomechanical photothermal spectromicroscopy due to its exceptional sensitivity.

In recent years, the increasing availability of personal data has raised concerns regarding privacy and security. One of the critical processes to address these concerns is data anonymization, which aims to protect individual privacy and prevent the release of sensitive information. This research focuses on the importance of face anonymization. Therefore, we introduce GANonymization, a novel face anonymization framework with facial expression-preserving abilities. Our approach is based on a high-level representation of a face, which is synthesized into an anonymized version based on a generative adversarial network (GAN). The effectiveness of the approach was assessed by evaluating its performance in removing identifiable facial attributes to increase the anonymity of the given individual face. Additionally, the performance of preserving facial expressions was evaluated on several affect recognition datasets and outperformed the state-of-the-art methods in most categories. Finally, our approach was analyzed for its ability to remove various facial traits, such as jewelry, hair color, and multiple others. Here, it demonstrated reliable performance in removing these attributes. Our results suggest that GANonymization is a promising approach for anonymizing faces while preserving facial expressions., Comment: 26 pages, 11 figures, 6 tables, ACM Transactions on Multimedia Computing, Communications, and Applications

Full dimensional potential energy surfaces (PESs) based on machine learning (ML) techniques provide means for accurate and efficient molecular simulations in the gas- and condensed-phase for various experimental observables ranging from spectroscopy to reaction dynamics. Here, the MLpot extension with PhysNet as the ML-based model for a PES is introduced into the newly developed pyCHARMM API. To illustrate conceiving, validating, refining and using a typical workflow, para-chloro-phenol is considered as an example. The main focus is on how to approach a concrete problem from a practical perspective and applications to spectroscopic observables and the free energy for the -OH torsion in solution are discussed in detail. For the computed IR spectra in the fingerprint region the computations for para-chloro-phenol in water are in good qualitative agreement with experiment carried out in CCl$_4$. Also, relative intensities are largely consistent with experimental findings. The barrier for rotation of the -OH group increases from $\sim 3.5$ kcal/mol in the gas phase to $\sim 4.1$ kcal/mol from simulations in water due to favourable H-bonding interactions of the -OH group with surrounding water molecules., Comment: 38 pages, 11 figures

Nanomechanical resonators can serve as high performance detectors and have potential to be widely used in the industry for a variety of applications. Most nanomechanical sensing applications rely on detecting changes of resonance frequency. In commonly used frequency tracking schemes, the resonator is driven at or close to its resonance frequency. Closed-loop systems can continually check whether the resonator is at resonance and accordingly adjust the frequency of the driving signal. In this work, we study three resonance frequency tracking schemes, a feedback-free (FF), a self-sustaining oscillator (SSO), and a phase-locked loop oscillator (PLLO) scheme. We improve and extend the theoretical models for the FF and the SSO tracking schemes, and test the models experimentally with a nanoelectromechanical system (NEMS) resonator. We employ a SSO architecture with a pulsed positive feedback topology and compare it to the commonly used PLLO and FF schemes. We show that all tracking schemes are theoretically equivalent and that they all are subject to the same speed versus accuracy trade-off characteristics. In order to verify the theoretical models, we present experimental steady-state measurements for all tracking schemes. Frequency stability is characterized by computing the Allan deviation. We obtain almost perfect correspondence between the theoretical models and the experimental measurements. These results show that the choice of the tracking scheme is dictated by cost, robustness and usability in practice as opposed to fundamental theoretical differences in performance.

This paper introduces the ACCompanion, an expressive accompaniment system. Similarly to a musician who accompanies a soloist playing a given musical piece, our system can produce a human-like rendition of the accompaniment part that follows the soloist's choices in terms of tempo, dynamics, and articulation. The ACCompanion works in the symbolic domain, i.e., it needs a musical instrument capable of producing and playing MIDI data, with explicitly encoded onset, offset, and pitch for each played note. We describe the components that go into such a system, from real-time score following and prediction to expressive performance generation and online adaptation to the expressive choices of the human player. Based on our experience with repeated live demonstrations in front of various audiences, we offer an analysis of the challenges of combining these components into a system that is highly reactive and precise, while still a reliable musical partner, robust to possible performance errors and responsive to expressive variations., Comment: In Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI-23), Macao, China. The differences/extensions with the previous version include a technical appendix, added missing links, and minor text updates. 10 pages, 4 figures

The paper explores the optical properties of an exfoliated MoSe$_2$ monolayer implanted with Cr$^+$ ions, accelerated to 25 eV. Photoluminescence of the implanted MoSe$_2$ reveals an emission line from Cr-related defects that is present only under weak electron doping. Unlike band-to-band transition, the Cr-introduced emission is characterised by non-zero activation energy, long lifetimes, and weak response to the magnetic field. To rationalise the experimental results and get insights into the atomic structure of the defects, we modelled the Cr-ion irradiation process using ab-initio molecular dynamics simulations followed by the electronic structure calculations of the system with defects. The experimental and theoretical results suggest that the recombination of electrons on the acceptors, which could be introduced by the Cr implantation-induced defects, with the valence band holes is the most likely origin of the low energy emission. Our results demonstrate the potential of low-energy ion implantation as a tool to tailor the properties of 2D materials by doping.

Bifurcations in kinetic pathways decide the evolution of a system. An example is crystallization, in which the thermodynamically stable polymorph may not form due to kinetic hindrance. Here, we use confined self-assembly to investigate the interplay of thermodynamics and kinetics in the crystallization pathways of finite clusters. We report the observation of decahedral clusters from colloidal particles in emulsion droplets and show that these decahedral clusters can be thermodynamically stable just like icosahedral clusters. Our hard sphere simulations reveal how the development of the early nucleus shape passes through a bifurcation that decides the cluster symmetry. A geometric argument explains why decahedral clusters are kinetically hindered and why icosahedral clusters can be dominant even if they are not the thermodynamic ground state., Comment: Article + supplementary information. 41 pages, 22 figures

Recent advances in experimental methodology enabled studies of the quantum-state and conformational dependence of chemical reactions under precisely controlled conditions in the gas phase. Here, we generated samples of selected gauche and s-trans 2,3-dibromobutadiene (DBB) by electrostatic deflection in a molecular beam and studied their reaction with Coulomb crystals of laser-cooled $\mathrm{Ca^{+}}$ ions in an ion trap. The rate coefficients for the total reaction were found to strongly depend on both the conformation of DBB and the electronic state of $\mathrm{Ca^{+}}$. In the $\mathrm{(4p)~^{2}P_{1/2}}$ and $\mathrm{(3d)~^{2}D_{3/2}}$ excited states of $\mathrm{Ca^{+}}$, the reaction is capture-limited and faster for the gauche conformer due to long-range ion-dipole interactions. In the $\mathrm{(4s)~^{2}S_{1/2}}$ ground state of $\mathrm{Ca^{+}}$, the reaction rate for s-trans DBB still conforms with the capture limit, while that for gauche DBB is strongly suppressed. The experimental observations were analysed with the help of adiabatic capture theory, ab-initio calculations and reactive molecular dynamics simulations on a machine-learned full-dimensional potential energy surface of the system. The theory yields near-quantitative agreement for s-trans-DBB, but overestimates the reactivity of the gauche-conformer compared to the experiment. The present study points to the important role of molecular geometry even in strongly reactive exothermic systems and illustrates striking differences in the reactivity of individual conformers in gas-phase ion-molecule reactions.

The rise of machine learning has greatly influenced the field of computational chemistry, and that of atomistic molecular dynamics simulations in particular. One of its most exciting prospects is the development of accurate, full-dimensional potential energy surfaces (PESs) for molecules and clusters, which, however, often require thousands to tens of thousands of ab initio data points restricting the community to medium sized molecules and/or lower levels of theory (e.g. DFT). Transfer learning, which improves a global PES from a lower to a higher level of theory, offers a data efficient alternative requiring only a fraction of the high level data (on the order of 100 are found to be sufficient for malonaldehyde). The present work demonstrates that even with Hartree-Fock theory and a double-zeta basis set as the lower level model, transfer learning yields CCSD(T)-level quality for H-transfer barrier energies, harmonic frequencies and H-transfer tunneling splittings. Most importantly, finite-temperature molecular dynamics simulations on the sub-microsecond time scale in the gas phase are possible and the infrared spectra determined from the transfer learned PESs are in good agreement with experiment. It is concluded that routine, long-time atomistic simulations on PESs fulfilling CCSD(T)-standards become possible.

We present a multi-modal stress dataset that uses digital job interviews to induce stress. The dataset provides multi-modal data of 40 participants including audio, video (motion capturing, facial recognition, eye tracking) as well as physiological information (photoplethysmography, electrodermal activity). In addition to that, the dataset contains time-continuous annotations for stress and occurred emotions (e.g. shame, anger, anxiety, surprise). In order to establish a baseline, five different machine learning classifiers (Support Vector Machine, K-Nearest Neighbors, Random Forest, Long-Short-Term Memory Network) have been trained and evaluated on the proposed dataset for a binary stress classification task. The best-performing classifier achieved an accuracy of 88.3% and an F1-score of 87.5%.

Nanoelectromechanical systems (NEMS) have proven outstanding performance in the detection of small masses down to single proton sensitivity. To obtain a high enough throughput for the application in practical mass spectrometry, NEMS resonators have to be arranged in two-dimensional (2D) arrays. However, all state-of-the-art electromechanical transduction methods rely on electrical lines placed close to the mechanical resonators, which drastically restricts the density of 2D resonator arrays. An exception is the transduction by surface acoustic waves (SAWs), which has so far only been shown for the transduction of single nanomechanical pillar resonators. Here, we demonstrate the transduction of pillar pairs by surface acoustic waves. The pillars have a diameter of 700 nm and show a mass responsivity of -588$\pm$98 ng$^{-1}$. The distances between the pillar pairs are 70 nm and 14.3 $\mu$m. SAW transduction enabled us to measure both pillars of each pair with electrical lines no closer than 300 $\mu$m, illustrating the potential of SAWs to transduce dense arrays of pillar resonators, a crucial step towards practical mass spectrometry with NEMS., Comment: 6 pages, 4 figures

Counterfactual explanations are a common tool to explain artificial intelligence models. For Reinforcement Learning (RL) agents, they answer "Why not?" or "What if?" questions by illustrating what minimal change to a state is needed such that an agent chooses a different action. Generating counterfactual explanations for RL agents with visual input is especially challenging because of their large state spaces and because their decisions are part of an overarching policy, which includes long-term decision-making. However, research focusing on counterfactual explanations, specifically for RL agents with visual input, is scarce and does not go beyond identifying defective agents. It is unclear whether counterfactual explanations are still helpful for more complex tasks like analyzing the learned strategies of different agents or choosing a fitting agent for a specific task. We propose a novel but simple method to generate counterfactual explanations for RL agents by formulating the problem as a domain transfer problem which allows the use of adversarial learning techniques like StarGAN. Our method is fully model-agnostic and we demonstrate that it outperforms the only previous method in several computational metrics. Furthermore, we show in a user study that our method performs best when analyzing which strategies different agents pursue.

Traditional semantic image search methods aim to retrieve images that match the meaning of the text query. However, these methods typically search for objects on the whole image, without considering the localization of objects within the image. This paper presents an extension of existing object detection models for semantic image search that considers the semantic alignment between object proposals and text queries, with a focus on searching for objects within images. The proposed model uses a single feature extractor, a pre-trained Convolutional Neural Network, and a transformer encoder to encode the text query. Proposal-text alignment is performed using contrastive learning, producing a score for each proposal that reflects its semantic alignment with the text query. The Region Proposal Network (RPN) is used to generate object proposals, and the end-to-end training process allows for an efficient and effective solution for semantic image search. The proposed model was trained end-to-end, providing a promising solution for semantic image search that retrieves images that match the meaning of the text query and generates semantically relevant object proposals.