Visual retrieval from brain signals is a key challenge in Brain-Computer Interfaces (BCIs). Existing methods directly map noisy neural signals into a unified feature space, ignoring the dual-stream mechanism of neural decoding: brain signals are generated through the interaction of bottom-up perception (processing visual saliency) and top-down cognition (interpreting semantic concepts based on prior knowledge). In Rapid Serial Visual Presentation paradigm, standard encoders prioritize high-level semantic abstractions over actual salient features encoded in human vision, lacking the semantic guidance needed to stabilize inherently noisy signals. This mismatch causes perceptual misalignment and semantic inconsistency. To resolve this, we propose NeuroAlign, a dynamic dual-stream framework that explicitly separates and coordinates these two processes. Specifically, we utilize Visual Saliency Extraction (VSE) to capture salient features and Semantic Guidance Alignment (SGA) to provide top-down semantic guidance. These processes are coordinated by the Dynamic Loss Adjustment (DLA) mechanism, which adaptively prioritizes structural alignment before shifting to semantic refinement. Extensive experiments on THINGS-EEG2 and THINGS-MEG datasets demonstrate that NeuroAlign achieves SOTA performance, reaching 48.1% (\(\uparrow 2.4\%\)) and 14.5% (\(\uparrow 2.6\%\)) Top-1 accuracy in intra- and inter-subject retrieval, respectively.

Computed tomography (CT) is a widely-used imaging technology that assists clinical decision-making with high-quality human body representations. To reduce the radiation dose posed by CT, sparse-view (SV) CT is developed with preserved image quality. However, these methods are still stuck with a fixed uniform SV (USV) sampling strategy, which inhibits the possibility of acquiring a better image with an even reduced dose. In this paper, we explore this possibility via learning an active SV (ASV) sampling policy that optimizes the sampling positions for regions of interest (RoI)-specific, high-quality reconstruction. To this end, we design an sampling agent for the recommendation of ASV sampling positions based on on-the-fly reconstruction with obtained sinograms in a progressive fashion. With such a design, we achieve better performances on the NIH-AAPM dataset over popular USV sampling, especially when the number of views is small. Finally, such a design enables the RoI-aware reconstruction with improved local quality within the RoI that are clinically important. Experiments on the VerSe dataset demonstrate the ability of the proposed sampling policy, which is difficult to achieve with USV sampling.

Object detection, as a fundamental problem in computer vision, has been widely used in many industrial applications, such as intelligent manufacturing and intelligent video surveillance. In this work, we find that classification and regression have different sensitivities to the object translation, from the investigation about the availability of highly overlapping proposals. More specifically, the regressor head has intrinsic characteristics of higher sensitivity to translation than the classifier. Based on it, we propose a decoupled sampling strategy for a deep detector, named Decoupled R-CNN, to decouple the proposals sampling for the two tasks, which induces two sensitivity-specific heads. Furthermore, we adopt the cascaded structure for the single regressor head of Decoupled R-CNN, which is an extremely simple but highly effective way of improving the performance of object detection. Extensive empirical analyses using real-world datasets demonstrate the value of the proposed method when compared with the state-of-the-art models. The reproducing code is available athttps://github.com/shouwangzhe134/Decoupled-R-CNN.

In this paper, a sparse representation-based intuitionistic fuzzy clustering (SRIFC) approach is presented for solving the large-scale decision making (LSDM) problem. It consists of two algorithms: the sparse representation-based intuitionistic fuzzy clustering-exactly precision algorithm (which is presented for an exactly precision requirement), and the sparse representation-based intuitionistic fuzzy clustering-soft precision and scalable algorithm (which is proposed for soft precision and scalable requirements). In the proposed SRIFC approach, decision makers are clustered into several interest groups according to their interest preferences and relation sparsity of their intuitionistic fuzzy assessment information. The purpose of the presented SRIFC approach is to investigate the group intra-relations among DMs and to detect the group leaders for each interest group during the clustering process. According to the illustrative experiment results, the presented SRIFC approach is an adaptive and the unsupervised clustering method and presents more robust and efficient for LSDM problems.

In this paper, a customized sparse representation model is proposed to take advantage of the variational information for undersampled face recognition. The proposed model with the mixed norm is a generalization of the extended sparse representation-based classification model. This model guarantees the sparsity of representation coefficient and the robustness for the variational information from generic data set. The mixed norm well fits the distribution of variational information (such as illumination, expression, poses, and occlusion) and the interference information (somewhat face-specific in generic data set) simultaneously. We compare the proposed method with the related methods on several popular face databases, including AR, CMU-PIE, Georgia, and LFW databases. The experimental results show that the proposed method outperforms several popular face recognition methods.