Search

Event cameras excel in capturing high-contrast scenes and dynamic objects, offering a significant advantage over traditional frame-based cameras. Despite active research into leveraging event cameras for semantic segmentation, generating pixel-wise dense semantic maps for such challenging scenarios remains labor-intensive. As a remedy, we present EV-WSSS: a novel weakly supervised approach for event-based semantic segmentation that utilizes sparse point annotations. To fully leverage the temporal characteristics of event data, the proposed framework performs asymmetric dual-student learning between 1) the original forward event data and 2) the longer reversed event data, which contain complementary information from the past and the future, respectively. Besides, to mitigate the challenges posed by sparse supervision, we propose feature-level contrastive learning based on class-wise prototypes, carefully aggregated at both spatial region and sample levels. Additionally, we further excavate the potential of our dual-student learning model by exchanging prototypes between the two learning paths, thereby harnessing their complementary strengths. With extensive experiments on various datasets, including DSEC Night-Point with sparse point annotations newly provided by this paper, the proposed method achieves substantial segmentation results even without relying on pixel-level dense ground truths. The code and dataset are available at https://github.com/Chohoonhee/EV-WSSS., Comment: Accepted by ECCV2024

The large abundance of perspective camera datasets facilitated the emergence of novel learning-based strategies for various tasks, such as camera localization, single image depth estimation, or view synthesis. However, panoramic or omnidirectional image datasets, including essential information, such as pose and depth, are mostly made with synthetic scenes. In this work, we introduce a large scale 360$^{\circ}$ videos dataset in the wild. This dataset has been carefully scraped from the Internet and has been captured from various locations worldwide. Hence, this dataset exhibits very diversified environments (e.g., indoor and outdoor) and contexts (e.g., with and without moving objects). Each of the 25K images constituting our dataset is provided with its respective camera's pose and depth map. We illustrate the relevance of our dataset for two main tasks, namely, single image depth estimation and view synthesis.

Vision and language models (VLMs) such as CLIP have showcased remarkable zero-shot recognition abilities yet face challenges in visio-linguistic compositionality, particularly in linguistic comprehension and fine-grained image-text alignment. This paper explores the intricate relationship between compositionality and recognition -- two pivotal aspects of VLM capability. We conduct a comprehensive evaluation of existing VLMs, covering both pre-training approaches aimed at recognition and the fine-tuning methods designed to improve compositionality. Our evaluation employs 12 benchmarks for compositionality, along with 21 zero-shot classification and two retrieval benchmarks for recognition. In our analysis from 274 CLIP model checkpoints, we reveal patterns and trade-offs that emerge between compositional understanding and recognition accuracy. Ultimately, this necessitates strategic efforts towards developing models that improve both capabilities, as well as the meticulous formulation of benchmarks for compositionality. We open our evaluation framework at https://github.com/ytaek-oh/vl_compo., Comment: Accepted to CVPRW 2024 on 'What is Next in Multimodal Foundation Models?'. Code: https://github.com/ytaek-oh/vl_compo

High-momentum two-particle correlations are a useful tool for studying jet-quenching effects in the quark-gluon plasma. Angular correlations between neutral-pion triggers and charged hadrons with transverse momenta in the range 4--12~GeV/$c$ and 0.5--7~GeV/$c$, respectively, have been measured by the PHENIX experiment in 2014 for Au$+$Au collisions at $\sqrt{s_{_{NN}}}=200$~GeV. Suppression is observed in the yield of high-momentum jet fragments opposite the trigger particle, which indicates jet suppression stemming from in-medium partonic energy loss, while enhancement is observed for low-momentum particles. The ratio and differences between the yield in Au$+$Au collisions and $p$$+$$p$ collisions, $I_{AA}$ and $\Delta_{AA}$, as a function of the trigger-hadron azimuthal separation, $\Delta\phi$, are measured for the first time at the Relativistic Heavy Ion Collider. These results better quantify how the yield of low-$p_T$ associated hadrons is enhanced at wide angle, which is crucial for studying energy loss as well as medium-response effects., Comment: 534 authors from 83 institutions, 12 pages, 7 figures. v1 is version submitted to Physical Review C. HEPdata tables for the points plotted in figures for this and previous PHENIX publications are (or will be) publicly available at http://www.phenix.bnl.gov/papers.html

Fuzzing is an effective technique for discovering software vulnerabilities by generating random test inputs and executing them against the target program. However, fuzzing large and complex programs remains challenging due to difficulties in uncovering deeply hidden vulnerabilities. This paper addresses the limitations of existing coverage-guided fuzzers, focusing on the scheduler and mutator components. Existing schedulers suffer from information sparsity and the inability to handle fine-grained feedback metrics. The mutators are agnostic of target program branches, leading to wasted computation and slower coverage exploration. To overcome these issues, we propose an end-to-end online stochastic control formulation for coverage-guided fuzzing. Our approach incorporates a novel scheduler and custom mutator that can adapt to branch logic, maximizing aggregate edge coverage achieved over multiple stages. The scheduler utilizes fine-grained branch distance measures to identify frontier branches, where new coverage is likely to be achieved. The mutator leverages branch distance information to perform efficient and targeted seed mutations, leading to robust progress with minimal overhead. We present FOX, a proof-of-concept implementation of our control-theoretic approach, and compare it to industry-standard coverage-guided fuzzers. 6 CPU-years of extensive evaluations on the FuzzBench dataset and complex real-world programs (a total of 38 test programs) demonstrate that FOX outperforms existing state-of-the-art fuzzers, achieving average coverage improvements up to 26.45% in real-world standalone programs and 6.59% in FuzzBench programs over the state-of-the-art AFL++. In addition, it uncovers 20 unique bugs in popular real-world applications including eight that are previously unknown, showcasing real-world security impact., Comment: To Appear in Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS '24)

Recent advancements in zero-shot video diffusion models have shown promise for text-driven video editing, but challenges remain in achieving high temporal consistency. To address this, we introduce Video-3DGS, a 3D Gaussian Splatting (3DGS)-based video refiner designed to enhance temporal consistency in zero-shot video editors. Our approach utilizes a two-stage 3D Gaussian optimizing process tailored for editing dynamic monocular videos. In the first stage, Video-3DGS employs an improved version of COLMAP, referred to as MC-COLMAP, which processes original videos using a Masked and Clipped approach. For each video clip, MC-COLMAP generates the point clouds for dynamic foreground objects and complex backgrounds. These point clouds are utilized to initialize two sets of 3D Gaussians (Frg-3DGS and Bkg-3DGS) aiming to represent foreground and background views. Both foreground and background views are then merged with a 2D learnable parameter map to reconstruct full views. In the second stage, we leverage the reconstruction ability developed in the first stage to impose the temporal constraints on the video diffusion model. To demonstrate the efficacy of Video-3DGS on both stages, we conduct extensive experiments across two related tasks: Video Reconstruction and Video Editing. Video-3DGS trained with 3k iterations significantly improves video reconstruction quality (+3 PSNR, +7 PSNR increase) and training efficiency (x1.9, x4.5 times faster) over NeRF-based and 3DGS-based state-of-art methods on DAVIS dataset, respectively. Moreover, it enhances video editing by ensuring temporal consistency across 58 dynamic monocular videos., Comment: Project page at https://video-3dgs-project.github.io/

Knowledge distillation (KD) has emerged as a promising technique for addressing the computational challenges associated with deploying large-scale recommender systems. KD transfers the knowledge of a massive teacher system to a compact student model, to reduce the huge computational burdens for inference while retaining high accuracy. The existing KD studies primarily focus on one-time distillation in static environments, leaving a substantial gap in their applicability to real-world scenarios dealing with continuously incoming users, items, and their interactions. In this work, we delve into a systematic approach to operating the teacher-student KD in a non-stationary data stream. Our goal is to enable efficient deployment through a compact student, which preserves the high performance of the massive teacher, while effectively adapting to continuously incoming data. We propose Continual Collaborative Distillation (CCD) framework, where both the teacher and the student continually and collaboratively evolve along the data stream. CCD facilitates the student in effectively adapting to new data, while also enabling the teacher to fully leverage accumulated knowledge. We validate the effectiveness of CCD through extensive quantitative, ablative, and exploratory experiments on two real-world datasets. We expect this research direction to contribute to narrowing the gap between existing KD studies and practical applications, thereby enhancing the applicability of KD in real-world systems., Comment: Accepted by KDD 2024 research track. 9 main pages + 1 appendix page, 5 figures

The primary purpose of studying quarkonium production in relativistic heavy-ion collisions is to understand the properties of the quark-gluon plasma. At various collision systems, measurements of quarkonium states of different binding energies, such as $\Upsilon(nS)$, can provide comprehensive information. A model study has been performed to investigate the modification of $\Upsilon(nS)$ production in Pb-Pb collisions at $\sqrt{s_{\mathrm{NN}}}=$ 5.02 TeV and Au-Au collisions at $\sqrt{s_{\mathrm{NN}}}=$ 200 GeV. The Monte-Carlo simulation study is performed with a publicly available hydrodynamic simulation package for the quark-gluon plasma medium and a theoretical calculation of temperature-dependent thermal width of $\Upsilon(nS)$ considering the gluo-dissociation and inelastic parton scattering for dissociation inside the medium. In addition, we perform a systematic study with different descriptions of initial collision geometry and formation time of $\Upsilon(nS)$ to investigate their impacts on yield modification. The model calculation with a varied parameter set can describe the experimental data of $\Upsilon(nS)$ in Pb-Pb collisions at 5.02 TeV and $\Upsilon(2S)$ in Au-Au collisions at 200 GeV but underestimates the modification of $\Upsilon(1S)$ at the lower collision energy. The nuclear absorption mechanism is explored to understand the discrepancy between the data and simulation., Comment: 9 pages, 11 figures

Electronic Health Records (EHRs) are relational databases that store the entire medical histories of patients within hospitals. They record numerous aspects of patients' medical care, from hospital admission and diagnosis to treatment and discharge. While EHRs are vital sources of clinical data, exploring them beyond a predefined set of queries requires skills in query languages like SQL. To make information retrieval more accessible, one strategy is to build a question-answering system, possibly leveraging text-to-SQL models that can automatically translate natural language questions into corresponding SQL queries and use these queries to retrieve the answers. The EHRSQL 2024 shared task aims to advance and promote research in developing a question-answering system for EHRs using text-to-SQL modeling, capable of reliably providing requested answers to various healthcare professionals to improve their clinical work processes and satisfy their needs. Among more than 100 participants who applied to the shared task, eight teams were formed and completed the entire shared task requirement and demonstrated a wide range of methods to effectively solve this task. In this paper, we describe the task of reliable text-to-SQL modeling, the dataset, and the methods and results of the participants. We hope this shared task will spur further research and insights into developing reliable question-answering systems for EHRs., Comment: The 6th Clinical Natural Language Processing Workshop at NAACL 2024; Minor Change from Camera-Ready

In recent years, radicalization is being increasingly attempted on video-sharing platforms. Previous studies have been proposed to identify online radicalization using generic social context analysis, without taking into account comprehensive viewer traits and how those can affect viewers' perception of radicalizing content. To address the challenge, we examine QAnon, a conspiracy-based radicalizing group, and have designed a comprehensive questionnaire aiming to understand viewers' perceptions of QAnon videos. We outline the traits of viewers that QAnon videos are the most appealing to, and identify influential factors that impact viewers' perception of the videos.

Multi-target multi-camera tracking is a crucial task that involves identifying and tracking individuals over time using video streams from multiple cameras. This task has practical applications in various fields, such as visual surveillance, crowd behavior analysis, and anomaly detection. However, due to the difficulty and cost of collecting and labeling data, existing datasets for this task are either synthetically generated or artificially constructed within a controlled camera network setting, which limits their ability to model real-world dynamics and generalize to diverse camera configurations. To address this issue, we present MTMMC, a real-world, large-scale dataset that includes long video sequences captured by 16 multi-modal cameras in two different environments - campus and factory - across various time, weather, and season conditions. This dataset provides a challenging test-bed for studying multi-camera tracking under diverse real-world complexities and includes an additional input modality of spatially aligned and temporally synchronized RGB and thermal cameras, which enhances the accuracy of multi-camera tracking. MTMMC is a super-set of existing datasets, benefiting independent fields such as person detection, re-identification, and multiple object tracking. We provide baselines and new learning setups on this dataset and set the reference scores for future studies. The datasets, models, and test server will be made publicly available., Comment: Accepted on CVPR 2024

This paper proposes an algorithm for synthesizing novel views under few-shot setup. The main concept is to develop a stable surface regularization technique called Annealing Signed Distance Function (ASDF), which anneals the surface in a coarse-to-fine manner to accelerate convergence speed. We observe that the Eikonal loss - which is a widely known geometric regularization - requires dense training signal to shape different level-sets of SDF, leading to low-fidelity results under few-shot training. In contrast, the proposed surface regularization successfully reconstructs scenes and produce high-fidelity geometry with stable training. Our method is further accelerated by utilizing grid representation and monocular geometric priors. Finally, the proposed approach is up to 45 times faster than existing few-shot novel view synthesis methods, and it produces comparable results in the ScanNet dataset and NeRF-Real dataset., Comment: 3DV 2024

There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples (termed Hybrid-AT). With the assumption that adversarial and clean samples are from two different domains, a common practice in prior works is to adopt Dual BN, where BN and BN are used for adversarial and clean branches, respectively. A popular belief for motivating Dual BN is that estimating normalization statistics of this mixture distribution is challenging and thus disentangling it for normalization achieves stronger robustness. In contrast to this belief, we reveal that disentangling statistics plays a less role than disentangling affine parameters in model training. This finding aligns with prior work (Rebuffi et al., 2023), and we build upon their research for further investigations. We demonstrate that the domain gap between adversarial and clean samples is not very large, which is counter-intuitive considering the significant influence of adversarial perturbation on the model accuracy. We further propose a two-task hypothesis which serves as the empirical foundation and a unified framework for Hybrid-AT improvement. We also investigate Dual BN in test-time and reveal that affine parameters characterize the robustness during inference. Overall, our work sheds new light on understanding the mechanism of Dual BN in Hybrid-AT and its underlying justification., Comment: Accepted at TMLR

We establish rigorous benchmarks for visual perception robustness. Synthetic images such as ImageNet-C, ImageNet-9, and Stylized ImageNet provide specific type of evaluation over synthetic corruptions, backgrounds, and textures, yet those robustness benchmarks are restricted in specified variations and have low synthetic quality. In this work, we introduce generative model as a data source for synthesizing hard images that benchmark deep models' robustness. Leveraging diffusion models, we are able to generate images with more diversified backgrounds, textures, and materials than any prior work, where we term this benchmark as ImageNet-D. Experimental results show that ImageNet-D results in a significant accuracy drop to a range of vision models, from the standard ResNet visual classifier to the latest foundation models like CLIP and MiniGPT-4, significantly reducing their accuracy by up to 60\%. Our work suggests that diffusion models can be an effective source to test vision models. The code and dataset are available at https://github.com/chenshuang-zhang/imagenet_d., Comment: Accepted at CVPR 2024

Large language models (LLMs) are able to solve various tasks with only a few demonstrations utilizing their in-context learning (ICL) abilities. However, LLMs often rely on their pre-trained semantic priors of demonstrations rather than on the input-label relationships to proceed with ICL prediction. In this work, we term this phenomenon as the 'Demonstration Shortcut'. While previous works have primarily focused on improving ICL prediction results for predefined tasks, we aim to rectify the Demonstration Shortcut, thereby enabling the LLM to effectively learn new input-label relationships from demonstrations. To achieve this, we introduce In-Context Calibration, a demonstration-aware calibration method. We evaluate the effectiveness of the proposed method in two settings: (1) the Original ICL Task using the standard label space and (2) the Task Learning setting, where the label space is replaced with semantically unrelated tokens. In both settings, In-Context Calibration demonstrates substantial improvements, with results generalized across three LLM families (OPT, GPT, and Llama2) under various configurations., Comment: NAACL 2024

We introduce KorMedMCQA, the first Korean multiple-choice question answering (MCQA) benchmark derived from Korean healthcare professional licensing examinations, covering from the year 2012 to year 2023. This dataset consists of a selection of questions from the license examinations for doctors, nurses, and pharmacists, featuring a diverse array of subjects. We conduct baseline experiments on various large language models, including proprietary/open-source, multilingual/Korean-additional pretrained, and clinical context pretrained models, highlighting the potential for further enhancements. We make our data publicly available on HuggingFace (https://huggingface.co/datasets/sean0042/KorMedMCQA) and provide a evaluation script via LM-Harness, inviting further exploration and advancement in Korean healthcare environments.

Recommender systems often suffer from selection bias as users tend to rate their preferred items. The datasets collected under such conditions exhibit entries missing not at random and thus are not randomized-controlled trials representing the target population. To address this challenge, a doubly robust estimator and its enhanced variants have been proposed as they ensure unbiasedness when accurate imputed errors or predicted propensities are provided. However, we argue that existing estimators rely on miscalibrated imputed errors and propensity scores as they depend on rudimentary models for estimation. We provide theoretical insights into how miscalibrated imputation and propensity models may limit the effectiveness of doubly robust estimators and validate our theorems using real-world datasets. On this basis, we propose a Doubly Calibrated Estimator that involves the calibration of both the imputation and propensity models. To achieve this, we introduce calibration experts that consider different logit distributions across users. Moreover, we devise a tri-level joint learning framework, allowing the simultaneous optimization of calibration experts alongside prediction and imputation models. Through extensive experiments on real-world datasets, we demonstrate the superiority of the Doubly Calibrated Estimator in the context of debiased recommendation tasks., Comment: WWW 2024

Recent recommender systems started to use rating elicitation, which asks new users to rate a small seed itemset for inferring their preferences, to improve the quality of initial recommendations. The key challenge of the rating elicitation is to choose the seed items which can best infer the new users' preference. This paper proposes a novel end-to-end Deep learning framework for Rating Elicitation (DRE), that chooses all the seed items at a time with consideration of the non-linear interactions. To this end, it first defines categorical distributions to sample seed items from the entire itemset, then it trains both the categorical distributions and a neural reconstruction network to infer users' preferences on the remaining items from CF information of the sampled seed items. Through the end-to-end training, the categorical distributions are learned to select the most representative seed items while reflecting the complex non-linear interactions. Experimental results show that DRE outperforms the state-of-the-art approaches in the recommendation quality by accurately inferring the new users' preferences and its seed itemset better represents the latent space than the seed itemset obtained by the other methods., Comment: WWW 2020

Despite the importance of having a measure of confidence in recommendation results, it has been surprisingly overlooked in the literature compared to the accuracy of the recommendation. In this dissertation, I propose a model calibration framework for recommender systems for estimating accurate confidence in recommendation results based on the learned ranking scores. Moreover, I subsequently introduce two real-world applications of confidence on recommendations: (1) Training a small student model by treating the confidence of a big teacher model as additional learning guidance, (2) Adjusting the number of presented items based on the expected user utility estimated with calibrated probability., Comment: Doctoral Dissertation

The conventional top-K recommendation, which presents the top-K items with the highest ranking scores, is a common practice for generating personalized ranking lists. However, is this fixed-size top-K recommendation the optimal approach for every user's satisfaction? Not necessarily. We point out that providing fixed-size recommendations without taking into account user utility can be suboptimal, as it may unavoidably include irrelevant items or limit the exposure to relevant ones. To address this issue, we introduce Top-Personalized-K Recommendation, a new recommendation task aimed at generating a personalized-sized ranking list to maximize individual user satisfaction. As a solution to the proposed task, we develop a model-agnostic framework named PerK. PerK estimates the expected user utility by leveraging calibrated interaction probabilities, subsequently selecting the recommendation size that maximizes this expected utility. Through extensive experiments on real-world datasets, we demonstrate the superiority of PerK in Top-Personalized-K recommendation task. We expect that Top-Personalized-K recommendation has the potential to offer enhanced solutions for various real-world recommendation scenarios, based on its great compatibility with existing models., Comment: WWW 2024

Discharge summaries in Electronic Health Records (EHRs) are crucial for clinical decision-making, but their length and complexity make information extraction challenging, especially when dealing with accumulated summaries across multiple patient admissions. Large Language Models (LLMs) show promise in addressing this challenge by efficiently analyzing vast and complex data. Existing benchmarks, however, fall short in properly evaluating LLMs' capabilities in this context, as they typically focus on single-note information or limited topics, failing to reflect the real-world inquiries required by clinicians. To bridge this gap, we introduce EHRNoteQA, a novel benchmark built on the MIMIC-IV EHR, comprising 962 different QA pairs each linked to distinct patients' discharge summaries. Every QA pair is initially generated using GPT-4 and then manually reviewed and refined by three clinicians to ensure clinical relevance. EHRNoteQA includes questions that require information across multiple discharge summaries and covers eight diverse topics, mirroring the complexity and diversity of real clinical inquiries. We offer EHRNoteQA in two formats: open-ended and multi-choice question answering, and propose a reliable evaluation method for each. We evaluate 27 LLMs using EHRNoteQA and examine various factors affecting the model performance (e.g., the length and number of discharge summaries). Furthermore, to validate EHRNoteQA as a reliable proxy for expert evaluations in clinical practice, we measure the correlation between the LLM performance on EHRNoteQA, and the LLM performance manually evaluated by clinicians. Results show that LLM performance on EHRNoteQA have higher correlation with clinician-evaluated performance (Spearman: 0.78, Kendall: 0.62) compared to other benchmarks, demonstrating its practical relevance in evaluating LLMs in clinical settings., Comment: Under Review

The emission of the pre-equilibrium particles during nuclear collisions at moderate beam energies is still an open question. This influences the properties of the compound nucleus but also changes the interpretation of the quasi-fission process. A systematic analysis of the data obtained by the FAZIA collaboration during a recent experiment with a neutron rich projectile is presented. The full range of charged particles detected in the experiment is within the limit of isotopic resolution of the FAZIA detector. Quasi-projectile (QP) fragments were detected in majority thanks to the forward angular acceptance of the experimental setup which was confirmed by introducing cuts based on the HIPSE event generator calculations. The main goal was to compare the experimental results with the HIPSE simulations after introducing these cuts to investigate the influence of the n-rich entrance channel on the QP fragment properties. More specifically, the lowering of N/Z of QP fragments with beam energy was found to be present since the initial phase of the reaction. Thus, pre-equilibrium emissions might be a possible candidate to explain such an effect., Comment: 10 pages, 10 figures

Brain modulation is a modification process of brain activity through external stimulations. However, which condition can induce the activation is still unclear. Therefore, we aimed to identify brain activation conditions using 40 Hz monaural beat (MB). Under this stimulation, auditory sense status which is determined by frequency and power range is the condition to consider. Hence, we designed five sessions to compare; no stimulation, audible (AB), inaudible in frequency, inaudible in power, and inaudible in frequency and power. Ten healthy participants underwent each stimulation session for ten minutes with electroencephalogram (EEG) recording. For analysis, we calculated the power spectral density (PSD) of EEG for each session and compared them in frequency, time, and five brain regions. As a result, we observed the prominent power peak at 40 Hz in only AB. The induced EEG amplitude increase started at one minute and increased until the end of the session. These results of AB had significant differences in frontal, central, temporal, parietal, and occipital regions compared to other stimulations. From the statistical analysis, the PSD of the right temporal region was significantly higher than the left. We figure out the role that the auditory sense is important to lead brain activation. These findings help to understand the neurophysiological principle and effects of auditory stimulation., Comment: Accepted to EMBC 2023

Electroencephalography (EEG) has been widely used to study the relationship between naps and working memory, yet the effects of naps on distinct working memory tasks remain unclear. Here, participants performed word-pair and visuospatial working memory tasks pre- and post-nap sessions. We found marked differences in accuracy and reaction time between tasks performed pre- and post-nap. In order to identify the impact of naps on performance in each working memory task, we employed clustering to classify participants as high- or low-performers. Analysis of sleep architecture revealed significant variations in sleep onset latency and rapid eye movement (REM) proportion. In addition, the two groups exhibited prominent differences, especially in the delta power of the Non-REM 3 stage linked to memory. Our results emphasize the interplay between nap-related neural activity and working memory, underlining specific EEG markers associated with cognitive performance., Comment: Submitted to 2024 12th IEEE International Winter Conference on Brain-Computer Interface

The monaural beat is known that it can modulate brain and personal states. However, which changes in brain waves are related to changes in state is still unclear. Therefore, we aimed to investigate the effects of monaural beats and find the relationship between them. Ten participants took part in five separate random sessions, which included a baseline session and four sessions with monaural beats stimulation: one audible session and three inaudible sessions. Electroencephalogram (EEG) were recorded and participants completed pre- and post-stimulation questionnaires assessing mood and sleepiness. As a result, audible session led to increased arousal and positive mood compared to other conditions. From the neurophysiological analysis, statistical differences in frontal-central, central-central, and central-parietal connectivity were observed only in the audible session. Furthermore, a significant correlation was identified between sleepiness and EEG power in the temporal and occipital regions. These results suggested a more detailed correlation for stimulation to change its personal state. These findings have implications for applications in areas such as cognitive enhancement, mood regulation, and sleep management.

Polysomnography (PSG) is an indispensable diagnostic tool in sleep medicine, essential for identifying various sleep disorders. By capturing physiological signals, including EEG, EOG, EMG, and cardiorespiratory metrics, PSG presents a patient's sleep architecture. However, its dependency on complex equipment and expertise confines its use to specialized clinical settings. Addressing these limitations, our study aims to perform PSG by developing a system that requires only a single EEG measurement. We propose a novel system capable of reconstructing multi-signal PSG from a single-channel EEG based on a masked autoencoder. The masked autoencoder was trained and evaluated using the Sleep-EDF-20 dataset, with mean squared error as the metric for assessing the similarity between original and reconstructed signals. The model demonstrated proficiency in reconstructing multi-signal data. Our results present promise for the development of more accessible and long-term sleep monitoring systems. This suggests the expansion of PSG's applicability, enabling its use beyond the confines of clinics., Comment: Proc. 12th IEEE International Winter Conference on Brain-Computer Interface

Existing video compression (VC) methods primarily aim to reduce the spatial and temporal redundancies between consecutive frames in a video while preserving its quality. In this regard, previous works have achieved remarkable results on videos acquired under specific settings such as instant (known) exposure time and shutter speed which often result in sharp videos. However, when these methods are evaluated on videos captured under different temporal priors, which lead to degradations like motion blur and low frame rate, they fail to maintain the quality of the contents. In this work, we tackle the VC problem in a general scenario where a given video can be blurry due to predefined camera settings or dynamics in the scene. By exploiting the natural trade-off between visual enhancement and data compression, we formulate VC as a min-max optimization problem and propose an effective framework and training strategy to tackle the problem. Extensive experimental results on several benchmark datasets confirm the effectiveness of our method compared to several state-of-the-art VC approaches., Comment: Accepted to WACV 2024

Despite the breakthroughs in biomarker discovery facilitated by differential gene analysis, challenges remain, particularly at the single-cell level. Traditional methodologies heavily rely on user-supplied cell annotations, focusing on individually expressed data, often neglecting the critical interactions between biological conditions, such as healthy versus diseased states. In response, here we introduce scBeacon, an innovative framework built upon a deep contrastive siamese network. scBeacon pioneers an unsupervised approach, adeptly identifying matched cell populations across varied conditions, enabling a refined differential gene analysis. By utilizing a VQ-VAE framework, a contrastive siamese network, and a greedy iterative strategy, scBeacon effectively pinpoints differential genes that hold potential as key biomarkers. Comprehensive evaluations on a diverse array of datasets validate scBeacon's superiority over existing single-cell differential gene analysis tools. Its precision and adaptability underscore its significant role in enhancing diagnostic accuracy in biomarker discovery. With the emphasis on the importance of biomarkers in diagnosis, scBeacon is positioned to be a pivotal asset in the evolution of personalized medicine and targeted treatments.

Electronic Health Records (EHRs), which contain patients' medical histories in various multi-modal formats, often overlook the potential for joint reasoning across imaging and table modalities underexplored in current EHR Question Answering (QA) systems. In this paper, we introduce EHRXQA, a novel multi-modal question answering dataset combining structured EHRs and chest X-ray images. To develop our dataset, we first construct two uni-modal resources: 1) The MIMIC-CXR-VQA dataset, our newly created medical visual question answering (VQA) benchmark, specifically designed to augment the imaging modality in EHR QA, and 2) EHRSQL (MIMIC-IV), a refashioned version of a previously established table-based EHR QA dataset. By integrating these two uni-modal resources, we successfully construct a multi-modal EHR QA dataset that necessitates both uni-modal and cross-modal reasoning. To address the unique challenges of multi-modal questions within EHRs, we propose a NeuralSQL-based strategy equipped with an external VQA API. This pioneering endeavor enhances engagement with multi-modal EHR sources and we believe that our dataset can catalyze advances in real-world medical scenarios such as clinical decision-making and research. EHRXQA is available at https://github.com/baeseongsu/ehrxqa., Comment: Accepted at NeurIPS 2023 Datasets and Benchmarks Track (10 pages for main text, 4 pages for references, 39 pages for supplementary materials)

Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain contains unlabeled video frames. Drawing upon recent advancements of self-supervised learning of the object motion from unlabeled videos with geometric constraint, we design a \textbf{Mo}tion-guided \textbf{D}omain \textbf{A}daptive semantic segmentation framework (MoDA). MoDA harnesses the self-supervised object motion cues to facilitate cross-domain alignment for segmentation task. First, we present an object discovery module to localize and segment target moving objects using object motion information. Then, we propose a semantic mining module that takes the object masks to refine the pseudo labels in the target domain. Subsequently, these high-quality pseudo labels are used in the self-training loop to bridge the cross-domain gap. On domain adaptive video and image segmentation experiments, MoDA shows the effectiveness utilizing object motion as guidance for domain alignment compared with optical flow information. Moreover, MoDA exhibits versatility as it can complement existing state-of-the-art UDA approaches. Code at https://github.com/feipanir/MoDA., Comment: CVPR 2024 Workshop on Learning with Limited Labelled Data for Image and Video Understanding. Best Paper Award

In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge. This project is designed to challenge the computer vision community to develop robust image captioning models that advance the state-of-the-art both in terms of accuracy and fairness. Through the challenge, the image captioning models were tested using a new evaluation dataset that includes a large variety of visual concepts from many domains. There was no specific training data provided for the challenge, and therefore the challenge entries were required to adapt to new types of image descriptions that had not been seen during training. This report includes information on the newly proposed NICE dataset, evaluation methods, challenge results, and technical details of top-ranking entries. We expect that the outcomes of the challenge will contribute to the improvement of AI models on various vision-language tasks., Comment: Tech report, project page https://nice.lgresearch.ai/

For a positive integer $m$, a (positive definite integral) quadratic form is called primitively $m$-universal if it primitively represents all quadratic forms of rank $m$. It was proved in arXiv:2202.13573 that there are exactly $107$ equivalence classes of primitively $1$-universal quaternary quadratic forms. In this article, we prove that the minimal rank of primitively $2$-universal quadratic forms is six, and there are exactly $201$ equivalence classes of primitively $2$-universal senary quadratic forms., Comment: 35 pages

The development of large language models tailored for handling patients' clinical notes is often hindered by the limited accessibility and usability of these notes due to strict privacy regulations. To address these challenges, we first create synthetic large-scale clinical notes using publicly available case reports extracted from biomedical literature. We then use these synthetic notes to train our specialized clinical large language model, Asclepius. While Asclepius is trained on synthetic data, we assess its potential performance in real-world applications by evaluating it using real clinical notes. We benchmark Asclepius against several other large language models, including GPT-3.5-turbo and other open-source alternatives. To further validate our approach using synthetic notes, we also compare Asclepius with its variants trained on real clinical notes. Our findings convincingly demonstrate that synthetic clinical notes can serve as viable substitutes for real ones when constructing high-performing clinical language models. This conclusion is supported by detailed evaluations conducted by both GPT-4 and medical professionals. All resources including weights, codes, and data used in the development of Asclepius are made publicly accessible for future research. (https://github.com/starmpcc/Asclepius), Comment: ACL 2024 (Findings)

An investigation of the quasiprojectile breakup channel in semiperipheral and peripheral collisions of $^{58,64}$Ni+$^{58,64}$Ni at 32 and 52 MeV/nucleon is presented. Data have been acquired in the first experimental campaign of the INDRA-FAZIA apparatus in GANIL. The effect of isospin diffusion between projectile and target in the two asymmetric reactions has been highlighted by means of the isospin transport ratio technique, exploiting the neutron-to-proton ratio of the quasiprojectile reconstructed from the two breakup fragments. We found evidence that, for the same reaction centrality, a higher degree of relaxation of the initial isospin imbalance is achieved in the breakup channel with respect to the more populated binary output, possibly indicating the indirect selection of specific dynamical features. We have proposed an interpretation based on different average projectile-target contact times related to the two exit channels under investigation, with a longer interaction for the breakup channel. The time information has been extracted from AMD simulations of the studied systems coupled to GEMINI++: the model calculations support the hypothesis hereby presented.

Learning computer vision models from (and for) movies has a long-standing history. While great progress has been attained, there is still a need for a pretrained multimodal model that can perform well in the ever-growing set of movie understanding tasks the community has been establishing. In this work, we introduce Long-range Multimodal Pretraining, a strategy, and a model that leverages movie data to train transferable multimodal and cross-modal encoders. Our key idea is to learn from all modalities in a movie by observing and extracting relationships over a long-range. After pretraining, we run ablation studies on the LVU benchmark and validate our modeling choices and the importance of learning from long-range time spans. Our model achieves state-of-the-art on several LVU tasks while being much more data efficient than previous works. Finally, we evaluate our model's transferability by setting a new state-of-the-art in five different benchmarks., Comment: Accepted to ICCV 2023