Multi-scale features are crucial in encoding objects with varying scales in vision tasks. The classic top-down and bottom-up feature pyramid networks are a common strategy for multi-scale feature extraction. However, these approaches suffer from the loss or degradation of feature information, which impairs the fusion effect of non-adjacent levels. In this paper, we propose an Asymptotic Feature Pyramid Network (AFPN) that supports direct interaction between non-adjacent levels. AFPN starts by fusing two adjacent low-level features and asymptotic incorporates higher-level features into the fusion process. This fusion way avoids the significant semantic gap between non-adjacent levels. Adaptive spatial fusion operation is further used to mitigate potential multi-object information conflicts during feature fusion at each spatial location. To reduce parameters, computational requirements, and inference speed, we propose a Lightweight Asymptotic Feature Pyramid Network (LightAFPN) that uses the concept of reparametrization. We evaluate the proposed method on the MS-COCO 2017, PASCAL VOC and Cityscapes datasets in both object detection and semantic segmentation frameworks. Experimental evaluation shows that our method achieves more competitive results than other state-of-the-art feature pyramid networks. The code is available at https://github.com/gyyang23/AFPN.

3-D imaging sonar is crucial in the exploration of marine resources, and the development of portable device with high-imaging quality and high-real-time performance is the general trend. However, traditional framework methods are limited by the huge amount of computation brought by high-quality imaging, making it difficult to implement in engineering. To address this issue, we develop 3-D real-time sonar system in an algorithm-hardware co-designed way. An ultrawideband distributed and parallel subarray beamforming algorithm (UWB-DPS) is proposed for 3-D acoustic imaging. This is a multistage array time-frequency beamforming method under a distributed parallel computing architecture. Based on this, we propose field-programmable gate array (FPGA)-based accelerator. It divides a large sonar receiving planar array into multiple parallel subarrays, and complete the beamforming in two stages, which can reduce the calculation load and speeds up 3-D imaging. For engineering implementation, we optimized the sparseness of the planar transducer array, with a sparse rate as high as 97.7%. The experimental results show that the calculation amount of the proposed UWB-DPS algorithm is reduced to 1/5.7 of the traditional framework algorithm, the imaging performance is effectively improved, and the FPGA-based accelerator outperforms the CPU software implementation by 935 $\times $ .

This paper presents an efficient visualization and exploration approach for modeling and characterizing the relationships and uncertainties in the context of a multidimensional ensemble dataset. Its core is a novel dissimilarity-preserving projection technique that characterizes not only the relationships among the mean values of the ensemble data objects but also the relationships among the distributions of ensemble members. This uncertainty-aware projection scheme leads to an improved understanding of the intrinsic structure in an ensemble dataset. The analysis of the ensemble dataset is further augmented by a suite of visual encoding and exploration tools. Experimental results on both artificial and real-world datasets demonstrate the effectiveness of our approach.

In current multimodal sentiment analysis, aligned and complete multimodal sequences are often crucial. Obtaining complete multimodal data in the real world presents various challenges, and aligning multimodal sequences often requires a significant amount of effort. Unfortunately, most multimodal sentiment analysis methods fail when dealing with missing modalities or unaligned multimodal sequences. To tackle these two challenges simultaneously in a simple and lightweight manner, we present the Unified Multimodal Framework (UniMF). The primary components of UniMF comprise two distinct modules. The first module, Translation Module, translates missing modalities using information from existing modalities. The second module, Prediction Module, uses the attention mechanism to fuse the multimodal information and generate predictions. To enhance the translation performance of the Translation Module, we introduce the Multimodal Generation Mask (MGM) and utilize it to construct the Multimodal Generation Transformer (MGT). The MGT can generate the missing modality while focusing on information from existing modalities. Furthermore, we introduce the Multimodal Understanding Transformer (MUT) in the Prediction Module, which includes the Multimodal Understanding Mask (MUM) and a unique sequence, MultiModalSequence ( MMSeq ), representing a unified multimodality. To assess the performance of UniMF, we perform experiments on four multimodal sentiment datasets, and UniMF attains competitive or state-of-the-art outcomes with fewer learnable parameters. Furthermore, the experimental outcomes signify that UniMF, supported by MGT and MUT - two transformers utilizing special attention mechanisms, can efficiently manage both generating task of missing modalities and understanding task of unaligned multimodal sequences. The implementation of this work is publicly accessible at https://github.com/gw-zhong/UniMF .

Optical coherence tomography (OCT), as a non-destructive and high-resolution fingerprint acquisition technology, is robust against poor skin conditions and resistant to spoof attacks. It measures fingertip information on and beneath skin as 3D volume data, containing the surface fingerprint, internal fingerprint and sweat glands. Various methods have been proposed to extract internal fingerprints, which ignore the inter-slice dependence and often require manually selected parameters. In this paper, a modified U-Net that combines residual learning, bidirectional convolutional long short-term memory and hybrid dilated convolution (denoted as BCL-U Net) for OCT volume data segmentation and two fingerprint reconstruction approaches are proposed. To the best of our knowledge, it is the first time that simultaneous and automatic extraction is performed for surface fingerprint, internal fingerprint and sweat glands. The proposed BCL-U Net utilizes the spatial dependence in OCT volume data and deals with segmentation of objects with diverse sizes to achieve accurate extraction. Comparisons have been performed to demonstrate the advantages of the proposed method. A thorough evaluation of the recognition abilities of internal and surface fingerprints is conducted using a dataset significantly larger than previous studies. Four databases containing internal and surface fingerprints are generated from 1572 OCT volume data by the proposed method. The internal fingerprint matching experiment has achieved a lowest equal error rate (EER) of 0.95%. Mixed internal and surface fingerprint matching experiment is also performed and achieves an EER of 3.67%, verifying the consistency of the internal and surface fingerprints. The matching experiments for fingers under poor skin conditions show that internal fingerprints achieve an EER of 2.47% that is much lower than that of surface fingerprints, which proves the advantage of internal fingerprints and indicates the potential of the internal fingerprints to supplement or replace the surface fingerprints for some specific applications.