Search

Electroencephalography (EEG) is a non-invasive technique to measure and record brain electrical activity, widely used in various BCI and healthcare applications. Early EEG decoding methods rely on supervised learning, limited by specific tasks and datasets, hindering model performance and generalizability. With the success of large language models, there is a growing body of studies focusing on EEG foundation models. However, these studies still leave challenges: Firstly, most of existing EEG foundation models employ full EEG modeling strategy. It models the spatial and temporal dependencies between all EEG patches together, but ignores that the spatial and temporal dependencies are heterogeneous due to the unique structural characteristics of EEG signals. Secondly, existing EEG foundation models have limited generalizability on a wide range of downstream BCI tasks due to varying formats of EEG data, making it challenging to adapt to. To address these challenges, we propose a novel foundation model called CBraMod. Specifically, we devise a criss-cross transformer as the backbone to thoroughly leverage the structural characteristics of EEG signals, which can model spatial and temporal dependencies separately through two parallel attention mechanisms. And we utilize an asymmetric conditional positional encoding scheme which can encode positional information of EEG patches and be easily adapted to the EEG with diverse formats. CBraMod is pre-trained on a very large corpus of EEG through patch-based masked EEG reconstruction. We evaluate CBraMod on up to 10 downstream BCI tasks (12 public datasets). CBraMod achieves the state-of-the-art performance across the wide range of tasks, proving its strong capability and generalizability. The source code is publicly available at \url{https://github.com/wjq-learning/CBraMod}.

Recently, the Diffusion Probabilistic Model (DPM)-based methods have achieved substantial success in the field of medical image segmentation. However, most of these methods fail to enable the diffusion model to learn edge features and non-edge features effectively and to inject them efficiently into the diffusion backbone. Additionally, the domain gap between the images features and the diffusion model features poses a great challenge to prostate segmentation. In this paper, we proposed CriDiff, a two-stage feature injecting framework with a Crisscross Injection Strategy (CIS) and a Generative Pre-train (GP) approach for prostate segmentation. The CIS maximizes the use of multi-level features by efficiently harnessing the complementarity of high and low-level features. To effectively learn multi-level of edge features and non-edge features, we proposed two parallel conditioners in the CIS: the Boundary Enhance Conditioner (BEC) and the Core Enhance Conditioner (CEC), which discriminatively model the image edge regions and non-edge regions, respectively. Moreover, the GP approach eases the inconsistency between the images features and the diffusion model without adding additional parameters. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the proposed method and achieve state-of-the-art performance on four evaluation metrics., Comment: Accepted in MICCAI 2024

Accurate, and effective traffic forecasting is vital for smart traffic systems, crucial in urban traffic planning and management. Current Spatio-Temporal Transformer models, despite their prediction capabilities, struggle with balancing computational efficiency and accuracy, favoring global over local information, and handling spatial and temporal data separately, limiting insight into complex interactions. We introduce the Criss-Crossed Dual-Stream Enhanced Rectified Transformer model (CCDSReFormer), which includes three innovative modules: Enhanced Rectified Spatial Self-attention (ReSSA), Enhanced Rectified Delay Aware Self-attention (ReDASA), and Enhanced Rectified Temporal Self-attention (ReTSA). These modules aim to lower computational needs via sparse attention, focus on local information for better traffic dynamics understanding, and merge spatial and temporal insights through a unique learning method. Extensive tests on six real-world datasets highlight CCDSReFormer's superior performance. An ablation study also confirms the significant impact of each component on the model's predictive accuracy, showcasing our model's ability to forecast traffic flow effectively., Comment: 18 pages

In [6], it was shown that the linear Lagrange element space on criss-cross meshes and its divergence exhibit spurious eigenvalues when applied in the mixed formulation of the Laplace eigenvalue problem, despite satisfying both the inf-sup condition and ellipticity on the discrete kernel. The lack of a Fortin interpolation is responsible for the spurious eigenvalues produced by the linear Lagrange space. In contrast, results in [8] confirm that quartic and higher-order Lagrange elements do not yield spurious eigenvalues on general meshes without nearly singular vertices, including criss-cross meshes as a special case. In this paper, we investigate quadratic and cubic Lagrange elements on criss-cross meshes. We prove the convergence of discrete eigenvalues by fitting the Lagrange elements on criss-cross meshes into a complex and constructing a Fortin interpolation. As a by-product, we construct bounded commuting projections for the finite element Stokes complex, which induces isomorphisms between cohomologies of the continuous and discrete complexes. We provide numerical examples to validate the theoretical results., Comment: 19 pages, 8 figures

Using integral field spectroscopy from MaNGA, we study the resolved microstructures in a shocked region in Criss Cross Nebula (CCN), with an unprecedentedly high resolution of $\lesssim$1000 AU. We measure surface brightness maps for 34 emission lines, which can be broadly divided into three categories: (1) the [OIII] $\lambda$5007-like group including seven high-ionization lines and two [OII] auroral lines which uniformly present a remarkable lane structure, (2) the H$\alpha$ $\lambda$6563-like group including 23 low-ionization or recombination lines which present a clump-like structure, and (3) [OII] $\lambda$3726 and [OII] $\lambda$3729 showing high densities at both the [OIII] $\lambda$5007 lane and the H$\alpha$ clump. We use these measurements to constrain resolved shock models implemented in MAPPINGS V. We find our data can be reasonably well-fitted by a model which includes a plane-parallel shock with a velocity of $133\pm5$ km/s, plus an isotropic two-dimensional Gaussian component which is likely another clump of gas ionized by photons from the shocked region, and a constant background. We compare the electron density and temperature profiles as predicted by our model with those calculated using observed emission line ratios. We find different line ratios to provide inconsistent temperature maps, and the discrepancies can be attributed to observational effects caused by limited spatial resolution and projection of the shock geometry, as well as contamination of the additional Gaussian component. Implications on shock properties and perspectives on future IFS-based studies of CCN are discussed., Comment: Accepted for publication in ApJ, 21 pages, 15 figures

Text image super-resolution is a unique and important task to enhance readability of text images to humans. It is widely used as pre-processing in scene text recognition. However, due to the complex degradation in natural scenes, recovering high-resolution texts from the low-resolution inputs is ambiguous and challenging. Existing methods mainly leverage deep neural networks trained with pixel-wise losses designed for natural image reconstruction, which ignore the unique character characteristics of texts. A few works proposed content-based losses. However, they only focus on text recognizers' accuracy, while the reconstructed images may still be ambiguous to humans. Further, they often have weak generalizability to handle cross languages. To this end, we present TATSR, a Text-Aware Text Super-Resolution framework, which effectively learns the unique text characteristics using Criss-Cross Transformer Blocks (CCTBs) and a novel Content Perceptual (CP) Loss. The CCTB extracts vertical and horizontal content information from text images by two orthogonal transformers, respectively. The CP Loss supervises the text reconstruction with content semantics by multi-scale text recognition features, which effectively incorporates content awareness into the framework. Extensive experiments on various language datasets demonstrate that TATSR outperforms state-of-the-art methods in terms of both recognition accuracy and human perception.

Document-level relation extraction (RE) aims to identify relations between two entities in a given document. Compared with its sentence-level counterpart, document-level RE requires complex reasoning. Previous research normally completed reasoning through information propagation on the mention-level or entity-level document-graph, but rarely considered reasoning at the entity-pair-level.In this paper, we propose a novel model, called Densely Connected Criss-Cross Attention Network (Dense-CCNet), for document-level RE, which can complete logical reasoning at the entity-pair-level. Specifically, the Dense-CCNet performs entity-pair-level logical reasoning through the Criss-Cross Attention (CCA), which can collect contextual information in horizontal and vertical directions on the entity-pair matrix to enhance the corresponding entity-pair representation. In addition, we densely connect multiple layers of the CCA to simultaneously capture the features of single-hop and multi-hop logical reasoning.We evaluate our Dense-CCNet model on three public document-level RE datasets, DocRED, CDR, and GDA. Experimental results demonstrate that our model achieves state-of-the-art performance on these three datasets.

This paper investigates the problem of correcting multiple criss-cross insertions and deletions in arrays. More precisely, we study the unique recovery of $n \times n$ arrays affected by $t$-criss-cross deletions defined as any combination of $t_r$ row and $t_c$ column deletions such that $t_r + t_c = t$ for a given $t$. We show an equivalence between correcting $t$-criss-cross deletions and $t$-criss-cross insertions and show that a code correcting $t$-criss-cross insertions/deletions has redundancy at least $tn + t \log n - \log(t!)$. Then, we present an existential construction of $t$-criss-cross insertion/deletion correcting code with redundancy bounded from above by $tn + \mathcal{O}(t^2 \log^2 n)$. The main ingredients of the presented code construction are systematic binary $t$-deletion correcting codes and Gabidulin codes. The first ingredient helps locating the indices of the inserted/deleted rows and columns, thus transforming the insertion/deletion-correction problem into a row/column erasure-correction problem which is then solved using the second ingredient.

This paper studies the problem of constructing codes correcting deletions in arrays. Under this model, it is assumed that an $n\times n$ array can experience deletions of rows and columns. These deletion errors are referred to as $(t_r,t_c)$-criss-cross deletions if $t_r$ rows and $t_c$ columns are deleted, while a code correcting these deletion patterns is called a $(t_r,t_c)$-criss-cross deletion correction code. The definitions for criss-cross insertions are similar. It is first shown that when $t_r=t_c$ the problems of correcting criss-cross deletions and criss-cross insertions are equivalent. The focus of this paper lies on the case of $(1,1)$-criss-cross deletions. A non-asymptotic upper bound on the cardinality of $(1,1)$-criss-cross deletion correction codes is shown which assures that the redundancy is at least $2n-3+2\log n$ bits. A code construction with an existential encoding and an explicit decoding algorithm is presented. The redundancy of the construction is at most $2n+4 \log n + 7 +2 \log e$. A construction with explicit encoder and decoder is presented. The explicit encoder adds an extra $5\log n + 5$ bits of redundancy to the construction., Comment: Submitted to IEEE Transactions on Information Theory for possible publication. Several examples are added to help understand the concepts explained in the paper

We investigate a mechanism to manipulate wall-bounded flows whereby wave-like undulations of the wall topography drives the creation of bespoke longitudinal vortices. A resonant interaction between the ambient vorticity of the undisturbed shear flow and the undulation of streamlines enforced by the wall topography serves to slightly rotate the spanwise vorticity of the mean flow into the streamwise direction, creating a swirling motion, in the form of regular streamwise rolls. The process is kinematic and essentially identical to the `direct drive' CL1 mechanism for Langmuir circulation (LC) proposed by Craik (1970). Boundary layers are modelled by selecting suitable primary flow profiles. A simple, easily integrable expression for the cross-plane stream function is found in two asymptotic regimes: the resonant onset of the essentially inviscid instability at early times, and the fully developed steady state viscous flow. Linear-order solutions for flow over undulating boundaries are obtained, fully analytical in the special case of a power-law profile. These solutions allow us to quickly map out the circulation response to boundary design parameters. The study is supplemented with direct numerical simulations which verify the manifestation of boundary induced Langmuir vortices in laminar flows with no-slip boundaries. Simulations show good qualitative agreement with theory. Quantitatively, the comparisons rest on a displacement length closure parameter adopted in the perturbation theory. While wall-driven LC appear to become unstable in turbulent flows, we propose that the mechanism can promote swirling motion in boundary layers, a flow feature which has been reported to reduce drag in some situations., Comment: 31 pages, 22 figures

This paper proposes a novel framework for lung segmentation in chest X-rays. It consists of two key contributions, a criss-cross attention based segmentation network and radiorealistic chest X-ray image synthesis (i.e. a synthesized radiograph that appears anatomically realistic) for data augmentation. The criss-cross attention modules capture rich global contextual information in both horizontal and vertical directions for all the pixels thus facilitating accurate lung segmentation. To reduce the manual annotation burden and to train a robust lung segmentor that can be adapted to pathological lungs with hazy lung boundaries, an image-to-image translation module is employed to synthesize radiorealistic abnormal CXRs from the source of normal ones for data augmentation. The lung masks of synthetic abnormal CXRs are propagated from the segmentation results of their normal counterparts, and then serve as pseudo masks for robust segmentor training. In addition, we annotate 100 CXRs with lung masks on a more challenging NIH Chest X-ray dataset containing both posterioranterior and anteroposterior views for evaluation. Extensive experiments validate the robustness and effectiveness of the proposed framework. The code and data can be found from https://github.com/rsummers11/CADLab/tree/master/Lung_Segmentation_XLSor ., Comment: Accepted by MIDL 2019

We show that properly detuning the carrier frequency of each of the criss-cross bichromatic waves from the transition frequency of the atom, it is possible to form a two-dimensional trap for atoms if the intensity of the waves is sufficiently large. For zero and near zero initial phases of waves, and also for $\pi$ and near $\pi$ phase shift between criss-cross waves a dynamic spatial structure of square cells with the side $\lambda /\sqrt{2}$ is formed. Numerical simulations are carried out for sodium atoms., Comment: 16 pages, 6 figures

Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85% of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9%, 45.76% and 55.47% on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at \url{https://github.com/speedinghzl/CCNet}., Comment: IEEE TPAMI 2020 & ICCV 2019

In this paper, we extend the original criss-cross algorithms for computing the $\varepsilon$-pseudospectral abscissa and radius to general spectral value sets. By proposing new root-finding-based strategies for the horizontal/radial search subphases, we significantly reduce the number of expensive Hamiltonian eigenvalue decompositions incurred, which typically translates to meaningful speedups in overall computation times. Furthermore, and partly necessitated by our root-finding approach, we develop a new way of handling the singular pencils or problematic interior searches that can arise when computing the $\varepsilon$-spectral value set radius. Compared to would-be direct extensions of the original algorithms, that is, without our additional modifications, our improved criss-cross algorithms are not only noticeably faster but also more robust and numerically accurate, for both spectral value set and pseudospectral problems., Comment: Final version

Students entering high school face many new academic challenges. One of the most important is their ability to read and understand more complex text in literature, mathematics, science, and social studies courses as they navigate through a rigorous high school curriculum. The Regional Educational Laboratory (REL) Northwest conducted a study to examine the effectiveness of a teacher professional development program called Project CRISS, which stands for Creating Independence through Student-owned Strategies. Through Project CRISS, high school teachers learn how to apply research-based learning principles and reading/writing strategies in all major subject or content areas using materials, training, and follow-up support provided by the developer. The pretest and posttest were administered in the fall and spring, respectively, of the second implementation year of the treatment. It was hypothesized that by year 2 of the treatment, teachers would have had familiarity with how to use the Project CRISS instructional methods, given the training and guided coaching they received during the first year of implementation. During the second year, when student impact was assessed, the model specified that teachers would continue to receive some training from the national trainer and technical assistance from the district-certified, in-school local facilitator. There was no statistically significant difference between the treatment group and control group on the mean reading comprehension scores. Because random selection was conducted within a blocking design defined by cohorts, poverty status, and state, a sensitivity analysis was performed to determine whether explicit modeling of the effect size variability across blocks would alter the substantive result. The substantive result remained the same: there was no statistically significant treatment effect. In addition to the main impact analysis, one exploratory research question was addressed: does the impact of Project CRISS on student reading comprehension differ for boys and girls? Concerning the moderating effect of gender, no statistically significant impact difference was found between boys and girls. Appendices include: (1) Statistical power analysis; (2) Teacher questionnaire for treatment schools; (3) Missing data imputation procedures; (4) Project CRISS full implementation model description; and (5) Complete multilevel model results for impact analysis. (Contains 3 figures, 18 tables and 4 endnotes.)

Project CRISS[R] (CReating Independence through Student-owned Strategies) is a professional development program for teachers that aims to improve reading, writing, and learning for 3rd- through 12th-grade students. The implementation of Project CRISS[R] does not require a change in the curriculum or materials being used in the classroom, but instead calls for a change in teaching style to focus on three primary concepts derived from cognitive psychology and brain research. These three concepts include students (1) monitoring their learning to assess when they have understood content, (2) integrating new information with prior knowledge, and (3) being actively involved in the learning process through discussing, writing, organizing information, and analyzing the structure of text to help improve comprehension. In Project CRISS[R], teachers incorporate these concepts into their regular classroom instruction through the use of comprehension strategies (such as using background knowledge, questioning, organizing graphically, and summarizing). Project CRISS[R] calls for students to apply these comprehension strategies to content they encounter, to gain an understanding of when and how it is most appropriate to use these strategies, and to learn to use the strategies that work best for them. Two studies of Project CRISS[R] that fall within the scope of the Adolescent Literacy review protocol meet What Works Clearinghouse (WWC) evidence standards. The two studies included 2,569 students, ranging from grade 4 through grade 6, who attended public schools in Arizona, California, Florida, Georgia, Louisiana, Montana, Oregon, Texas, Virginia, and Wisconsin. Based on these two studies, the WWC considers the extent of evidence for Project CRISS[R] on adolescent learners to be medium to large for the comprehension domain. No studies that meet WWC evidence standards examined the effectiveness of Project CRISS[R] on adolescent learners in the alphabetics, reading fluency, or general literacy achievement domains. Project CRISS[R] was found to have potentially positive effects on comprehension for adolescent learners. Appended are: (1) Study characteristics: Horsfall & Santa, 1994 (random assignment study); (2) Study characteristics: James-Burdumy et al., 2009 (randomized controlled trial); (3) Outcome measures for the comprehension domain; (4) Summary of study findings included in the rating for the comprehension domain; (5) Project CRISS[R] rating for the comprehension domain; and (6) Extent of evidence by domain. (Contains 20 footnotes.) [The following two studies are reviewed in this intervention report: Horsfall, S., & Santa, C. (1994). "Project CRISS: Validation report for the Program Effectiveness Panel." Unpublished manuscript; and James-Burdumy, S., Mansfield, W., Deke, J., Carey, N., Lugo-Gil, J., Hershey, A., et al. (2009). "Effectiveness of selected supplemental reading comprehension interventions: Impacts on a first cohort of fifth-grade students" (NCEE 2009-4032). Washington, DC: National Center for Education Evaluation and Regional Assistance, Institute of Education Sciences, U.S. Department of Education.]