Causally Probing the Role of the Hippocampus in Fear Discrimination: A Precision Functional Mapping-Guided, Transcranial Magnetic Stimulation Study in Participants With Posttraumatic Stress Symptoms.

Background: Fear overgeneralization is a promising pathogenic mechanism of clinical anxiety. A dominant model posits that hippocampal pattern separation failures drive overgeneralization. Hippocampal network-targeted transcranial magnetic stimulation (HNT-TMS) has been shown to strengthen hippocampal-dependent learning/memory processes. However, no study has examined whether HNT-TMS can alter fear learning/memory. Methods: Continuous theta burst stimulation was delivered to individualized left posterior parietal stimulation sites derived via seed-based connectivity, precision functional mapping, and electric field modeling methods. A vertex control site was also stimulated in a within-participant, randomized controlled design. Continuous theta burst stimulation was delivered prior to 2 visual discrimination tasks (1 fear based, 1 neutral). Multilevel models were used to model and test data. Participants were undergraduates with posttraumatic stress symptoms (final n = 25). Results: Main analyses did not indicate that HNT-TMS strengthened discrimination. However, multilevel interaction analyses revealed that HNT-TMS strengthened fear discrimination in participants with lower fear sensitization (indexed by responses to a control stimulus with no similarity to the conditioned fear cue) across multiple indices (anxiety ratings: ß = 0.10, 95% CI, 0.04 to 0.17, p = .001; risk ratings: ß = 0.07, 95% CI, 0.00 to 0.13, p = .037). Conclusions: Overgeneralization is an associative process that reflects deficient discrimination of the fear cue from similar cues. In contrast, sensitization reflects nonassociative responding unrelated to fear cue similarity. Our results suggest that HNT-TMS may selectively sharpen fear discrimination when associative response patterns, which putatively implicate the hippocampus, are more strongly engaged.

Fear overgeneralization is a promising pathogenic mechanism of clinical anxiety that is thought to be driven by deficient hippocampal discrimination. Using hippocampal network­targeted transcranial magnetic stimulation (HNT-TMS) in healthy participants with symptoms of posttraumatic stress, Webler et al. report that HNT-TMS did not strengthen discrimination overall, but it did strengthen fear discrimination in participants with lower fear sensitization. Sensitization reflects nonassociative fear responding unrelated to fear cue similarity and therefore is not expected to engage the hippocampal discrimination function. These results suggest that HNT-TMS may selectively sharpen fear discrimination when the hippocampal discrimination function is more strongly engaged.

Robust Ensemble of Two Different Multimodal Approaches to Segment 3D Ischemic Stroke Segmentation Using Brain Tumor Representation Among Multiple Center Datasets.

Ischemic stroke segmentation at an acute stage is vital in assessing the severity of patients' impairment and guiding therapeutic decision-making for reperfusion. Although many deep learning studies have shown attractive performance in medical segmentation, it is difficult to use these models trained on public data with private hospitals' datasets. Here, we demonstrate an ensemble model that employs two different multimodal approaches for generalization, a more effective way to perform on external datasets. First, after we jointly train a segmentation model on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) MR modalities, the model is inferred on the DWI images. Second, a channel-wise segmentation model is trained by concatenating the DWI and ADC images as input, and then is inferred using both MR modalities. Before training with ischemic stroke data, we utilized BraTS 2021, a public brain tumor dataset, for transfer learning. An extensive ablation study evaluates which strategy learns better representations for ischemic stroke segmentation. In our study, nnU-Net well-known for robustness is selected as our baseline model. Our proposed method is evaluated on three different datasets: the Asan Medical Center (AMC) I and II, and the 2022 Ischemic Stroke Lesion Segmentation (ISLES). Our experiments are widely validated over a large, multi-center, and multi-scanner dataset with a huge amount of 846 scans. Not only stroke lesion models can benefit from transfer learning using brain tumor data, but combining the MR modalities using different training schemes also highly improves segmentation performance. The method achieved a top-1 ranking in the ongoing ISLES'22 challenge and performed particularly well on lesion-wise metrics of interest to neuroradiologists, achieving a Dice coefficient of 78.69% and a lesion-wise F1 score of 82.46%. Also, the method was relatively robust on the AMC I (Dice, 60.35%; lesion-wise F1, 68.30%) and II (Dice; 74.12%; lesion-wise F1, 67.53%) datasets in different settings. The high segmentation accuracy of our proposed method could improve radiologists' ability to detect ischemic stroke lesions in MRI images. Our model weights and inference code are available on https://github.com/MDOpx/ISLES22-model-inference .

Exaggerated sensitivity to threat and reduced medial prefrontal engagement during threat generalization in reactive aggressive adolescents.

Aggressive adolescents tend to exhibit abnormal fear acquisition and extinction, and reactive aggressive adolescents are often more anxious. However, the relationship between fear generalization and reactive aggression (RA) remains unknown. According to Reactive-Proactive Aggression Questionnaire (RPQ) scores, 61 adolescents were divided into two groups, namely, a high RA group (N=30) and a low aggression (LA) group (N=31). All participants underwent three consecutive phases of the Pavlovian conditioning paradigm (i.e., habituation, acquisition, and generalization), and neural activation of the medial prefrontal cortex (mPFC) was assessed by functional near-infrared spectroscopy (fNIRS). The stimuli were ten circles with varying sizes, including two conditioned stimuli (CSs) and generalization stimuli (GSs). A scream at 85 decibels served as the auditory unconditioned stimulus (US). The US expectancy ratings of both CSs and GSs were higher in the RA group than in the LA group. The fNIRS results showed that GSs evoked lower mPFC activation in the RA group compared to the LA group during fear generalization. These findings suggest that abnormalities in fear acquisition and generalization are prototypical dysregulations in adolescents with RA. They provide neurocognitive evidence for dysregulated fear learning in the mechanisms underlying adolescents with RA, highlighting the need to develop emotional regulation interventions for these individuals.

Exploring the 'black box' of anxiety: An ERP study of non-consciously triggered fear generalization.

Individuals with anxiety disorders frequently display heightened fear responses, even in situations where there is no imminent danger. We hypothesize that these irrational fear responses are related to automatic processing of fear generalization. The initial automatic detection of stimuli often operates at a non-conscious level. However, whether fear generalization can occur when the cues are not perceived consciously remains unclear. The current study investigated the neurocognitive mechanisms underlying fear conditioning and its non-conscious and conscious generalization using a backward masking paradigm, combined with analysis of event-related potentials from electroencephalographic recordings. Behaviorally, participants showed heightened shock expectancy in response to non-conscious perceived generalization stimuli compared to those perceived consciously. Nonetheless, participants could not consciously distinguish between danger and safe cues in non-conscious trials. Physiologically, danger cues evoked larger frontal N1 amplitudes than safety cues in non-conscious trials, suggesting enhanced attention vigilance towards danger cues in the early sensory processing stage. Meanwhile, when fear generalization was conscious, it was accompanied by a larger P2 amplitude, indicating attention orientation or stimulus evaluation. In addition, fear conditioning was associated with sustained discrimination on P2, P3, and LPP. These findings collectively suggest that non-conscious fear generalization occurs at the neural level, yet additional control conditions are required to confirm this phenomenon on the US expectancy. Thus, non-consciously fear generalization may represent a mechanism that could trigger automatic irrational fear, highlighting the need for further research to explore therapeutic targets in anxiety disorders.

Imagery rescripting and extinction: Effects on US expectancy, US revaluation, and the generalization of fear reduction.

Exposure therapy consists of exposing patients to their fears and thereby diminishing their harm expectancies (i.e., extinction or expectancy learning). Although effective for many anxiety patients, its long-term success depends on the generalization of these harm expectancies to other stimuli. However, research shows that this generalization of extinction is limited. Besides decreasing harm expectancies, fear reduction may also be achieved by changing the meaning of an aversive memory representation (US revaluation). Imagery rescripting (ImRs) may be more successful in generalizing fear reduction because it allegedly works through US revaluation. The current experiment aimed to test working mechanisms for ImRs and extinction (revaluation and expectancy learning, respectively), and to examine generalization of fear reduction. In a fear conditioning paradigm, 113 healthy participants watched an aversive film clip that was used as the US. The manipulation consisted of imagining a script with a positive ending to the film clip (ImRs-only), extinction (extinction-only), or both (ImRs + extinction). Results showed enhanced US revaluation in ImRs + extinction. US expectancy decreased more strongly in the extinction conditions. Generalization of fear reduction was found in all conditions. Our results suggest different working mechanisms for ImRs and exposure. Future research should replicate this in (sub)clinical samples.

GABAergic interneurons in the hippocampal CA1 mediate contextual fear generalization in PTSD rats.

Fear overgeneralization is widely accepted as a pathogenic marker of post-traumatic stress disorder (PTSD). Recently, GABAergic interneurons have been regarded as key players in the regulation of fear memory. The role of hippocampal GABAergic interneurons in contextual fear generalization of PTSD remains incompletely understood. In the present study, we established a rat model of PTSD with inescapable foot shocks (IFS) and observed the loss of GABAergic interneuron phenotype in the hippocampal cornu ammonis-1 (CA1) subfield. To determine whether the loss of GABAergic interneuron phenotype was associated with fear generalization in PTSD rats, we used adeno-associated virus (AAV) to reduce the expression of GAD67 in CA1 and observed its effect on fear generalization. The results showed that the reduction of GAD67 in CA1 enhanced contextual fear generalization in rats. We investigated whether the PERK pathway was involved in the GABAergic interneuron injury. Increased expression of p-PERK, CHOP, and Caspase12 in GABAergic interneurons of PTSD rats was observed. Then, we used salubrinal, an endoplasmic reticulum stress inhibitor, to modulate the PERK pathway. The salubrinal treatment significantly protected the GABAergic interneurons and relieved fear generalization in PTSD rats. In addition, the results showed that salubrinal down-regulated the expression of CHOP and Caspase12 in GABAergic interneurons of PTSD rats. In conclusion, this study provided evidence that the loss of GABAergic interneuron phenotype in CA1 may contribute to contextual fear generalization in PTSD. The PERK pathway is involved in the GABAergic interneuron injury of PTSD rats and modulating it can protect GABAergic interneurons and constrain contextual fear generalization.

CauDR: A causality-inspired domain generalization framework for fundus-based diabetic retinopathy grading.

Diabetic retinopathy (DR) is the most common diabetic complication, which usually leads to retinal damage, vision loss, and even blindness. A computer-aided DR grading system has a significant impact on helping ophthalmologists with rapid screening and diagnosis. Recent advances in fundus photography have precipitated the development of novel retinal imaging cameras and their subsequent implementation in clinical practice. However, most deep learning-based algorithms for DR grading demonstrate limited generalization across domains. This inferior performance stems from variance in imaging protocols and devices inducing domain shifts. We posit that declining model performance between domains arises from learning spurious correlations in the data. Incorporating do-operations from causality analysis into model architectures may mitigate this issue and improve generalizability. Specifically, a novel universal structural causal model (SCM) was proposed to analyze spurious correlations in fundus imaging. Building on this, a causality-inspired diabetic retinopathy grading framework named CauDR was developed to eliminate spurious correlations and achieve more generalizable DR diagnostics. Furthermore, existing datasets were reorganized into 4DR benchmark for DG scenario. Results demonstrate the effectiveness and the state-of-the-art (SOTA) performance of CauDR. Diabetic retinopathy (DR) is the most common diabetic complication, which usually leads to retinal damage, vision loss, and even blindness. A computer-aided DR grading system has a significant impact on helping ophthalmologists with rapid screening and diagnosis. Recent advances in fundus photography have precipitated the development of novel retinal imaging cameras and their subsequent implementation in clinical practice. However, most deep learning-based algorithms for DR grading demonstrate limited generalization across domains. This inferior performance stems from variance in imaging protocols and devices inducing domain shifts. We posit that declining model performance between domains arises from learning spurious correlations in the data. Incorporating do-operations from causality analysis into model architectures may mitigate this issue and improve generalizability. Specifically, a novel universal structural causal model (SCM) was proposed to analyze spurious correlations in fundus imaging. Building on this, a causality-inspired diabetic retinopathy grading framework named CauDR was developed to eliminate spurious correlations and achieve more generalizable DR diagnostics. Furthermore, existing datasets were reorganized into 4DR benchmark for DG scenario. Results demonstrate the effectiveness and the state-of-the-art (SOTA) performance of CauDR.

Disruption of positive- and negative-feature morphine interoceptive occasion setters by dopamine receptor agonism and antagonism in male and female rats.

RATIONALE: Internally perceived stimuli evoked by morphine administration can form Pavlovian associations such that they can function as occasion setters (OSs) for externally perceived reward cues in rats, coming to modulate reward-seeking behaviour. Though much research has investigated mechanisms underlying opioid-related reinforcement and analgesia, neurotransmitter systems involved in the functioning of opioids as Pavlovian interoceptive discriminative stimuli remain to be disentangled despite documented differences in the development of tolerance to analgesic versus discriminative stimulus effects. OBJECTIVES: Dopamine has been implicated in many opioid-related behaviours, so we aimed to investigate the role of this neurotransmitter in expression of morphine occasion setting. METHODS: Male and female rats were assigned to positive- (FP) or negative-feature (FN) groups and received an injection of morphine or saline before each training session. A 15-s white noise conditioned stimulus (CS) was presented 8 times during every training session; offset of this stimulus was followed by 4-s access to liquid sucrose on morphine, but not saline, sessions for FP rats. FN rats learned the reverse contingency. Following stable discrimination, rats began generalization testing for expression of morphine-guided sucrose seeking after systemic pretreatment with different doses of the non-selective dopamine receptor antagonist, flupenthixol, and the non-selective dopamine receptor agonist, apomorphine, combined with training doses of morphine or saline in a Latin-square design. RESULTS: The morphine discrimination was acquired under both FP and FN contingencies by males and females. Neither flupenthixol nor apomorphine at any dose substituted for morphine, but both apomorphine and flupenthixol disrupted expression of the morphine OS. This inhibition was specific to sucrose seeking during CS presentations rather than during the period before CS onset and, in the case of apomorphine more so than flupenthixol, to trials on which access to sucrose was anticipated. CONCLUSIONS: Our findings lend support to a mechanism of occasion setting involving gating of CS-induced dopamine release rather than by direct dopaminergic modulation by the morphine stimulus.

Confronting heterogeneity in cryogenic electron microscopy data: Innovative strategies and future perspectives with data-driven methods.

The surge in the influx of data from cryogenic electron microscopy (cryo-EM) experiments has intensified the demand for robust algorithms capable of autonomously managing structurally heterogeneous datasets. This presents a wealth of exciting opportunities from a data science viewpoint, inspiring the development of numerous innovative, application-specific methods, many of which leverage contemporary data-driven techniques. However, addressing the challenges posed by heterogeneous datasets remains a paramount yet unresolved issue in the field. Here, we explore the subtleties of this challenge and the array of strategies devised to confront it. We pinpoint the shortcomings of existing methodologies and deliberate on prospective avenues for improvement. Specifically, our discussion focuses on strategies to mitigate model overfitting and manage data noise, as well as the effects of constraints, priors, and invariances on the optimization process.

A reliability generalization meta-analysis of the family resilience assessment scale (FRAS).

PROBLEM: Practitioners and researchers frequently rely on the Family Resilience Assessment Scale (FRAS) to assess family resilience, and previous research reported varying reliability statistics for the measurements with the scale. The present study aims to generalize the reliability of the FRAS based on Cronbach's alpha coefficients reported in the selected studies. ELIGIBILITY CRITERIA: We selected relevant research on various databases, including Web of Science, PubMed, ProQuest, Scopus, YÖK Thesis Center, DergiPark, and TR Index. SAMPLE: Satisfying our inclusion criteria, fifty-five studies were included in the present study. RESULTS: We calculated the reliability generalization coefficients for the FRAS total score to be 0.951 (95% CI [0.942, 0.958]) and 0.949 for Family Communication and Problem Solving, 0.792 for Utilizing Social and Economic Resources, 0.861 for Maintaining a Positive Outlook, 0.635 for Family Connectedness, 0.873 for Family Spirituality, and 0.702 for Ability to Make Meaning of Adversity. CONCLUSIONS: In a nutshell, our findings secure substantial insights into the reliability of the FRAS and its subscales for prospective researchers and practitioners. In this study, generalized Cronbach's alpha values imply average, good, and acceptable reliability for the FRAS subscales and total score, except for Family Connectedness. IMPLICATIONS: The distinct contribution of our research may be to reemphasize the significance of avoiding reliability induction and to raise awareness among prospective researchers of evaluating the reliability of any measurement they would obtain.

Valence-Dependent Implicit Action Generalization Among Group Members.

People implicitly generalize the actions of known individuals in a social group to unknown members. However, actions have social goals and evaluative valences, and the extent to which actions with different valences (helpful and harmful) are implicitly generalized among group members remains unclear. We used computer animations to simulate social group actions, where helping and hindering actions were represented by aiding and obstructing another's climb up a hill. Study 1 found that helpful actions are implicitly expected to be shared among members of the same group but not among members of different groups, but no such effect was found for harmful actions. This suggests that helpful actions are more likely than harmful actions to be implicitly generalized to group members. This finding was replicated in Study 2 by increasing the group size from three to five. Study 3 found that the null effect for generalizing harmful actions among group members is not due to the difficulty of detecting action generalization, as both helpful and harmful actions are similarly generalized within particular individuals. Moreover, Study 4 demonstrated that weakening social group information resulted in the absence of implicit generalization for helpful actions, suggesting the specificity of group membership. Study 5 revealed that the generalization of helping actions occurred when actions were performed by multiple group members rather than being repeated by one group member, showing group-based inductive generalization. Overall, these findings support valence-dependent implicit action generalization among group members. This implies that people may possess different knowledge regarding valenced actions on category-based generalization.

Intolerance of uncertainty affects the behavioral and neural mechanisms of higher generalization.

Intolerance of uncertainty (IU) is associated with several anxiety disorders. In this study, we employed rewards and losses as unconditioned positive and negative stimuli, respectively, to explore the effects of an individual's IU level on positive and negative generalizations using magnetic resonance imaging technology. Following instrumental learning, 48 participants (24 high IU; 24 low IU) were invited to complete positive and negative generalization tasks; their behavioral responses and neural activities were recorded by functional magnetic resonance imaging. The behavior results demonstrated that participants with high IUs exhibited higher generalizations to both positive and negative cues as compared with participants having low IUs. Neuroimaging results demonstrated that they exhibited higher activation levels in the right anterior insula and the default mode network (i.e. precuneus and posterior cingulate gyrus), as well as related reward circuits (i.e. caudate and right putamen). Therefore, higher generalization scores and the related abnormal brain activation may be key markers of IU as a vulnerability factor for anxiety disorders.

Domain generalization for retinal vessel segmentation via Hessian-based vector field.

Blessed by vast amounts of data, learning-based methods have achieved remarkable performance in countless tasks in computer vision and medical image analysis. Although these deep models can simulate highly nonlinear mapping functions, they are not robust with regard to the domain shift of input data. This is a significant concern that impedes the large-scale deployment of deep models in medical images since they have inherent variation in data distribution due to the lack of imaging standardization. Therefore, researchers have explored many domain generalization (DG) methods to alleviate this problem. In this work, we introduce a Hessian-based vector field that can effectively model the tubular shape of vessels, which is an invariant feature for data across various distributions. The vector field serves as a good embedding feature to take advantage of the self-attention mechanism in a vision transformer. We design paralleled transformer blocks that stress the local features with different scales. Furthermore, we present a novel data augmentation method that introduces perturbations in image style while the vessel structure remains unchanged. In experiments conducted on public datasets of different modalities, we show that our model achieves superior generalizability compared with the existing algorithms. Our code and trained model are publicly available at https://github.com/MedICL-VU/Vector-Field-Transformer.

Sugar detection in adulterated honey using hyper-spectral imaging with stacking generalization method.

This paper develops a new hybrid, automated, and non-invasive approach by combining hyper-spectral imaging, Savitzky-Golay (SG) Filter, Principal Components Analysis (PCA), Machine Learning (ML) classifiers/regressors, and stacking generalization methods to detect sugar in honey. First, the 32 different sugar concentration levels in honey were predicted using various ML regressors. Second, the six ranges of sugar were classified using various classifiers. Third, the 11 types of honey and 100% sugar were classified using classifiers. The stacking model (STM) obtained R2: 0.999, RMSE: 0.493 ml (v/v), RPD: 40.2, a 10-fold average R2: 0.996 and RMSE: 1.27 ml (v/v) for predicting 32 sugar concentrations. The STM achieved a Matthews Correlation Coefficient (MCC) of 99.7% and a Kappa score of 99.7%, a 10-fold average MCC of 98.9% and a Kappa score of 98.9% for classifying the six sugar ranges and 12 categories of honey types and a sugar.

Generalization of a positive-feature interoceptive morphine occasion setter across the rat estrous cycle.

INTRODUCTION: Interoceptive stimuli elicited by drug administration acquire conditioned modulatory properties of the induction of conditioned appetitive behaviours by exteroceptive cues. This effect may be modeled using a drug discrimination task in which the drug stimulus is trained as a positive-feature (FP) occasion setter (OS) that disambiguates the relation between an exteroceptive light conditioned stimulus (CS) and a sucrose unconditioned stimulus (US). We previously reported that females are less sensitive to generalization of a FP morphine OS than males, so we investigated the role of endogenous ovarian hormones in this difference. METHODS: Male and female rats received intermixed injections of 3.2 mg/kg morphine or saline before each daily training session. Training consisted of 8 presentations of the CS, each followed by access to sucrose on morphine, but not saline sessions. Following acquisiton, rats were tested for generalization of the morphine stimulus to 0, 1.0, 3.2, and 5.4 mg/kg morphine. Female rats were monitored for estrous cyclicity using vaginal cytology throughout the study. RESULTS: Both sexes acquired stable drug discrimination. A gradient of generalization was measured across morphine doses and this behaviour did not differ by sex, nor did it differ across the estrous cycle in females. CONCLUSIONS: Morphine generalization is independent of fluctuations in levels of sex and endogenous gonadal hormones in females under these experimental conditions.

Multilevel factors predict treatment response following semantic feature-based intervention in bilingual aphasia.

Semantic feature-based treatments (SFTs) are effective rehabilitation strategies for word retrieval deficits in bilinguals with aphasia (BWA). However, few studies have prospectively evaluated the effects of key parameters of these interventions on treatment outcomes. This study examined the influence of intervention-level (i.e., treatment language and treatment sessions), individual-level (baseline naming severity and age), and stimulus-level (i.e., lexical frequency, phonological length, and phonological neighborhood density) factors on naming improvement in a treated and untreated language for 34 Spanish-English BWA who completed 40 hours of SFT. Results revealed significant improvement over time in both languages. In the treated language, individuals who received therapy in their L1 improved more. Additionally, higher pre-treatment naming scores predicted greater response to treatment. Finally, a frequency effect on baseline naming accuracy and phonological effects on accuracy over time were associated with differential treatment gains. These findings indicate that multilevel factors are influential predictors of bilingual treatment outcomes.

TO-UGDA: target-oriented unsupervised graph domain adaptation.

Graph domain adaptation (GDA) aims to address the challenge of limited label data in the target graph domain. Existing methods such as UDAGCN, GRADE, DEAL, and COCO for different-level (node-level, graph-level) adaptation tasks exhibit variations in domain feature extraction, and most of them solely rely on representation alignment to transfer label information from a labeled source domain to an unlabeled target domain. However, this approach can be influenced by irrelevant information and usually ignores the conditional shift of the downstream predictor. To effectively address this issue, we introduce a target-oriented unsupervised graph domain adaptive framework for graph adaptation called TO-UGDA. Particularly, domain-invariant feature representations are extracted using graph information bottleneck. The discrepancy between two domains is minimized using an adversarial alignment strategy to obtain a unified feature distribution. Additionally, the meta pseudo-label is introduced to enhance downstream adaptation and improve the model's generalizability. Through extensive experimentation on real-world graph datasets, it is proved that the proposed framework achieves excellent performance across various node-level and graph-level adaptation tasks.

Decentralized stochastic sharpness-aware minimization algorithm.

In recent years, distributed stochastic algorithms have become increasingly useful in the field of machine learning. However, similar to traditional stochastic algorithms, they face a challenge where achieving high fitness on the training set does not necessarily result in good performance on the test set. To address this issue, we propose to use of a distributed network topology to improve the generalization ability of the algorithms. We specifically focus on the Sharpness-Aware Minimization (SAM) algorithm, which relies on perturbation weights to find the maximum point with better generalization ability. In this paper, we present the decentralized stochastic sharpness-aware minimization (D-SSAM) algorithm, which incorporates the distributed network topology. We also provide sublinear convergence results for non-convex targets, which is comparable to consequence of Decentralized Stochastic Gradient Descent (DSGD). Finally, we empirically demonstrate the effectiveness of these results in deep networks and discuss their relationship to the generalization behavior of SAM.

A Multi-Modal Egocentric Activity Recognition Approach towards Video Domain Generalization.

Egocentric activity recognition is a prominent computer vision task that is based on the use of wearable cameras. Since egocentric videos are captured through the perspective of the person wearing the camera, her/his body motions severely complicate the video content, imposing several challenges. In this work we propose a novel approach for domain-generalized egocentric human activity recognition. Typical approaches use a large amount of training data, aiming to cover all possible variants of each action. Moreover, several recent approaches have attempted to handle discrepancies between domains with a variety of costly and mostly unsupervised domain adaptation methods. In our approach we show that through simple manipulation of available source domain data and with minor involvement from the target domain, we are able to produce robust models, able to adequately predict human activity in egocentric video sequences. To this end, we introduce a novel three-stream deep neural network architecture combining elements of vision transformers and residual neural networks which are trained using multi-modal data. We evaluate the proposed approach using a challenging, egocentric video dataset and demonstrate its superiority over recent, state-of-the-art research works.

Dynamic graph transformer network via dual-view connectivity for autism spectrum disorder identification.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that requires objective and accurate identification methods for effective early intervention. Previous population-based methods via functional connectivity (FC) analysis ignore the differences between positive and negative FCs, which provide the potential information complementarity. And they also require additional information to construct a pre-defined graph. Meanwhile, two challenging demand attentions are the imbalance of performance caused by the class distribution and the inherent heterogeneity of multi-site data. In this paper, we propose a novel dynamic graph Transformer network based on dual-view connectivity for ASD Identification. It is based on the Autoencoders, which regard the input feature as individual feature and without any inductive bias. First, a dual-view feature extractor is designed to extract individual and complementary information from positive and negative connectivity. Then Graph Transformer network is innovated with a hot plugging K-Nearest Neighbor (KNN) algorithm module which constructs a dynamic population graph without any additional information. Additionally, we introduce the PolyLoss function and the Vrex method to address the class imbalance and improve the model's generalizability. The evaluation experiment on 1102 subjects from the ABIDE I dataset demonstrates our method can achieve superior performance over several state-of-the-art methods and satisfying generalizability for ASD identification.