Search

In Few-Shot Learning (FSL), traditional metric-based approaches often rely on global metrics to compute similarity. However, in natural scenes, the spatial arrangement of key instances is often inconsistent across images. This spatial misalignment can result in mismatched semantic pixels, leading to inaccurate similarity measurements. To address this issue, we propose a novel method called the Layer-Wise Features Metric of Semantic-Pixel Matching (LWFM-SPM) to make finer comparisons. Our method enhances model performance through two key modules: (1) the Layer-Wise Embedding (LWE) Module, which refines the cross-correlation of image pairs to generate well-focused feature maps for each layer; (2)the Semantic-Pixel Matching (SPM) Module, which aligns critical pixels based on semantic embeddings using an assignment algorithm. We conducted extensive experiments to evaluate our method on four widely used few-shot classification benchmarks: miniImageNet, tieredImageNet, CUB-200-2011, and CIFAR-FS. The results indicate that LWFM-SPM achieves competitive performance across these benchmarks. Our code will be publicly available on https://github.com/Halo2Tang/Code-for-LWFM-SPM.

Wash trading among crypto assets induces short-term price jumps, which manifest as liquidity fluctuation. We develop a model to decompose asset liquidity into two components: liquidity jump and liquidity diffusion, which quantify the size and probability of wash trading. Using the trading data from US stock markets as a benchmark, we establish that the combination of high liquidity diffusion and high liquidity jump indicates wash trading. On the other hand, the majority of large-volume trades with high liquidity jump but low liquidity diffusion (<1) are actually legitimate ones. Our model provides advice to investors in making informed decisions in crypto investments, and to regulators in taking targeted actions to combat wash trading. While we use crypto assets to exemplify the utilities of our model, the model should remain effective for other asset classes with extreme liquidity.

Accurate prediction of mortality in nasopharyngeal carcinoma (NPC), a complex malignancy particularly challenging in advanced stages, is crucial for optimizing treatment strategies and improving patient outcomes. However, this predictive process is often compromised by the high-dimensional and heterogeneous nature of NPC-related data, coupled with the pervasive issue of incomplete multi-modal data, manifesting as missing radiological images or incomplete diagnostic reports. Traditional machine learning approaches suffer significant performance degradation when faced with such incomplete data, as they fail to effectively handle the high-dimensionality and intricate correlations across modalities. Even advanced multi-modal learning techniques like Transformers struggle to maintain robust performance in the presence of missing modalities, as they lack specialized mechanisms to adaptively integrate and align the diverse data types, while also capturing nuanced patterns and contextual relationships within the complex NPC data. To address these problem, we introduce IMAN: an adaptive network for robust NPC mortality prediction with missing modalities., Comment: The paper has been accepted by BIBM 2024

Generative Adversarial Networks (GANs) have emerged as a prominent research focus for image editing tasks, leveraging the powerful image generation capabilities of the GAN framework to produce remarkable results.However, prevailing approaches are contingent upon extensive training datasets and explicit supervision, presenting a significant challenge in manipulating the diverse attributes of new image classes with limited sample availability. To surmount this hurdle, we introduce TAGE, an innovative image generation network comprising three integral modules: the Codebook Learning Module (CLM), the Code Prediction Module (CPM) and the Prompt-driven Semantic Module (PSM). The CPM module delves into the semantic dimensions of category-agnostic attributes, encapsulating them within a discrete codebook. This module is predicated on the concept that images are assemblages of attributes, and thus, by editing these category-independent attributes, it is theoretically possible to generate images from unseen categories. Subsequently, the CPM module facilitates naturalistic image editing by predicting indices of category-independent attribute vectors within the codebook. Additionally, the PSM module generates semantic cues that are seamlessly integrated into the Transformer architecture of the CPM, enhancing the model's comprehension of the targeted attributes for editing. With these semantic cues, the model can generate images that accentuate desired attributes more prominently while maintaining the integrity of the original category, even with a limited number of samples. We have conducted extensive experiments utilizing the Animal Faces, Flowers, and VGGFaces datasets. The results of these experiments demonstrate that our proposed method not only achieves superior performance but also exhibits a high degree of stability when compared to other few-shot image generation techniques., Comment: Accepted by International Conference on Signal Processing Systems Conference

Accurate segmentation of lesion regions is crucial for clinical diagnosis and treatment across various diseases. While deep convolutional networks have achieved satisfactory results in medical image segmentation, they face challenges such as loss of lesion shape information due to continuous convolution and downsampling, as well as the high cost of manually labeling lesions with varying shapes and sizes. To address these issues, we propose a novel medical visual prompting (MVP) framework that leverages pre-training and prompting concepts from natural language processing (NLP). The framework utilizes three key components: Super-Pixel Guided Prompting (SPGP) for superpixelating the input image, Image Embedding Guided Prompting (IEGP) for freezing patch embedding and merging with superpixels to provide visual prompts, and Adaptive Attention Mechanism Guided Prompting (AAGP) for pinpointing prompt content and efficiently adapting all layers. By integrating SPGP, IEGP, and AAGP, the MVP enables the segmentation network to better learn shape prompting information and facilitates mutual learning across different tasks. Extensive experiments conducted on five datasets demonstrate superior performance of this method in various challenging medical image tasks, while simplifying single-task medical segmentation models. This novel framework offers improved performance with fewer parameters and holds significant potential for accurate segmentation of lesion regions in various medical tasks, making it clinically valuable.

Medical landmark detection is crucial in various medical imaging modalities and procedures. Although deep learning-based methods have achieve promising performance, they are mostly designed for specific anatomical regions or tasks. In this work, we propose a universal model for multi-domain landmark detection by leveraging transformer architecture and developing a prompting component, named as Adaptive Query Prompting (AQP). Instead of embedding additional modules in the backbone network, we design a separate module to generate prompts that can be effectively extended to any other transformer network. In our proposed AQP, prompts are learnable parameters maintained in a memory space called prompt pool. The central idea is to keep the backbone frozen and then optimize prompts to instruct the model inference process. Furthermore, we employ a lightweight decoder to decode landmarks from the extracted features, namely Light-MLD. Thanks to the lightweight nature of the decoder and AQP, we can handle multiple datasets by sharing the backbone encoder and then only perform partial parameter tuning without incurring much additional cost. It has the potential to be extended to more landmark detection tasks. We conduct experiments on three widely used X-ray datasets for different medical landmark detection tasks. Our proposed Light-MLD coupled with AQP achieves SOTA performance on many metrics even without the use of elaborate structural designs or complex frameworks.

We model a portfolio of crypto assets that does not respond well to multivariate autoregressive models because of discontinuity in conditional covariance matrix and posterior covariance matrix caused by extreme liquidity. We adjust asset-level return and volatility with liquidity to reduce such discontinuity, and restore the effectiveness of a set of liquidity-adjusted VECM-DCC/ADCC-BL models at extreme liquidity. We establish two distinctive yet complementary portfolio liquidity measures: portfolio liquidity jump that quantifies the effect of liquidity adjustment in forecasting the conditional covariance matrix, and portfolio liquidity diffusion that quantifies the effect of liquidity adjustment in estimating the posterior covariance matrix., Comment: 50 pages, 7 figures

We propose that the liquidity of an asset includes two components: liquidity jump and liquidity diffusion. We show that liquidity diffusion has a higher correlation with crypto wash trading than liquidity jump and demonstrate that treatment on wash trading significantly reduces the level of liquidity diffusion, but only marginally reduces that of liquidity jump. We confirm that the autoregressive models are highly effective in modeling the liquidity-adjusted return with and without the treatment on wash trading. We argue that treatment on wash trading is unnecessary in modeling established crypto assets that trade in unregulated but mainstream exchanges., Comment: 37 pages all inclusive

Emotion recognition in conversation (ERC) has received increasing attention from researchers due to its wide range of applications.As conversation has a natural graph structure,numerous approaches used to model ERC based on graph convolutional networks (GCNs) have yielded significant results.However,the aggregation approach of traditional GCNs suffers from the node information redundancy problem,leading to node discriminant information loss.Additionally,single-layer GCNs lack the capacity to capture long-range contextual information from the graph. Furthermore,the majority of approaches are based on textual modality or stitching together different modalities, resulting in a weak ability to capture interactions between modalities. To address these problems, we present the relational bilevel aggregation graph convolutional network (RBA-GCN), which consists of three modules: the graph generation module (GGM), similarity-based cluster building module (SCBM) and bilevel aggregation module (BiAM). First, GGM constructs a novel graph to reduce the redundancy of target node information.Then,SCBM calculates the node similarity in the target node and its structural neighborhood, where noisy information with low similarity is filtered out to preserve the discriminant information of the node. Meanwhile, BiAM is a novel aggregation method that can preserve the information of nodes during the aggregation process. This module can construct the interaction between different modalities and capture long-range contextual information based on similarity clusters. On both the IEMOCAP and MELD datasets, the weighted average F1 score of RBA-GCN has a 2.17$\sim$5.21\% improvement over that of the most advanced method.Our code is available at https://github.com/luftmenscher/RBA-GCN and our article with the same name has been published in IEEE/ACM Transactions on Audio,Speech,and Language Processing,vol.31,2023

We study the impacts of regime changes and related rule implementations on IPOs initial return for China entrepreneurial boards (ChiNext and STAR). We propose that an initial return contains the issuer fair value and an investors overreaction and examine their magnitudes and determinants. Our findings reveal an evolution of IPO pricing in response to the progression of regulation changes along four dimensions: 1) governing regulation regime, 2) listing day trading restrictions, 3) listing rules for issuers, and 4) participation requirements for investors. We find that the most efficient regulation regime in Chinese IPO pricing has four characteristics: 1) registration system, 2) no hard return caps nor trading curbs that restrict the initial return; 3) more specific listing rules for issuers, and 4) more stringent participation requirements for investors. In all contexts, we show that the registration regime governing the STAR IPOs offers the most efficient pricing., Comment: 41 pages, 4 figures

We establish innovative liquidity premium measures, and construct liquidity-adjusted return and volatility to model assets with extreme liquidity, represented by a portfolio of selected crypto assets, and upon which we develop a set of liquidity-adjusted ARMA-GARCH/EGARCH models. We demonstrate that these models produce superior predictability at extreme liquidity to their traditional counterparts. We provide empirical support by comparing the performances of a series of Mean Variance portfolios., Comment: 48 page, 7 figures

Meteorological radar reflectivity data (i.e. radar echo) significantly influences precipitation prediction. It can facilitate accurate and expeditious forecasting of short-term heavy rainfall bypassing the need for complex Numerical Weather Prediction (NWP) models. In comparison to conventional models, Deep Learning (DL)-based radar echo extrapolation algorithms exhibit higher effectiveness and efficiency. Nevertheless, the development of reliable and generalized echo extrapolation algorithm is impeded by three primary challenges: cumulative error spreading, imprecise representation of sparsely distributed echoes, and inaccurate description of non-stationary motion processes. To tackle these challenges, this paper proposes a novel radar echo extrapolation algorithm called Temporal-Spatial Parallel Transformer, referred to as TempEE. TempEE avoids using auto-regression and instead employs a one-step forward strategy to prevent cumulative error spreading during the extrapolation process. Additionally, we propose the incorporation of a Multi-level Temporal-Spatial Attention mechanism to improve the algorithm's capability of capturing both global and local information while emphasizing task-related regions, including sparse echo representations, in an efficient manner. Furthermore, the algorithm extracts spatio-temporal representations from continuous echo images using a parallel encoder to model the non-stationary motion process for echo extrapolation. The superiority of our TempEE has been demonstrated in the context of the classic radar echo extrapolation task, utilizing a real-world dataset. Extensive experiments have further validated the efficacy and indispensability of various components within TempEE., Comment: Have been accepted by IEEE Transactions on Geoscience and Remote Sensing, see https://ieeexplore.ieee.org/document/10238744

Hashing is very popular for remote sensing image search. This article proposes a multiview hashing with learnable parameters to retrieve the queried images for a large-scale remote sensing dataset. Existing methods always neglect that real-world remote sensing data lies on a low-dimensional manifold embedded in high-dimensional ambient space. Unlike previous methods, this article proposes to learn the consensus compact codes in a view-specific low-dimensional subspace. Furthermore, we have added a hyperparameter learnable module to avoid complex parameter tuning. In order to prove the effectiveness of our method, we carried out experiments on three widely used remote sensing data sets and compared them with seven state-of-the-art methods. Extensive experiments show that the proposed method can achieve competitive results compared to the other method., Comment: 5 pages,icassp accepted

Since its inauguration, ChiNext has gone through three time periods with two different regulation regimes and three different sets of listing day trading restrictions. This paper studies the impact of regulation regimes and listing day trading restrictions on the initial return of ChiNext IPOs. We hypothesize that the initial return of a ChiNext IPO contains the issuers intrinsic value and the investors overreaction. The intrinsic value is represented by the IPOs 21st day return (monthly return), and the difference between the monthly and initial returns (intramonth return) is a proxy of the overreaction. We find that all significant variables for all three returns in all three time periods fall into four categories: pre-listing demand, post-listing demand, market condition and pre-listing issuer value. We observe stark contrasts among variable categories for each of the returns in the three time periods, which reveals an evolution of the investors behavior with regard to the progression of regulation regimes. Based on our findings, we argue that the differences among the levels and determinants of initial return, monthly return (intrinsic value) and intramonth return (overreaction) in different time periods can be largely explained by regulation regime changes along two dimensions: 1) approval vs. registration and 2) listing day trading curbs and return limits. We find that IPO pricing is demand-driven under the approval regime, but value-driven under the registration regime. We further compare the impact of regulation regime changes on ChiNext IPO pricing practice, and propose a future research plan on ChiNext IPO pricing efficiency with policy implication.

Clathrate hydride \emph{Fm}\={3}\emph{m}-LaH$_{10}$ has been proven as the most extraordinary superconductor with the critical temperature $T_c$ above 250 K upon compression of hundreds of GPa in recent years. A general hope is to reduce the stabilization pressure and maintain the high $T_c$ value of the specific phase in LaH$_{10}$. However, strong structural instability distorts \emph{Fm}\={3}\emph{m} structure and leads to a rapid decrease of $T_c$ at low pressures. Here, we investigate the phase stability and superconducting behaviors of \emph{Fm}\={3}\emph{m}-LaH$_{10}$ with enhanced chemical pre-compression through partly replacing La by Ce atoms from both experiments and calculations. For explicitly characterizing the synthesized hydride, we choose lanthanum-cerium alloy with stoichiometry composition of 1:1. X-ray diffraction and Raman scattering measurements reveal the stabilization of \emph{Fm}\={3}\emph{m}-La$_{0.5}$Ce$_{0.5}$H$_{10}$ in the pressure range of 140-160 GPa. Superconductivity with $T_c$ of 175$\pm$2 K at 155 GPa is confirmed with the observation of the zero-resistivity state and supported by the theoretical calculations. These findings provide applicability in the future explorations for a large variety of hydrogen-rich hydrides., Comment: 6 pages, 5 figures

Inspired by the high critical temperature in yttrium superhydride and the low stabilized pressure in superconducting cerium superhydride, we carry out four independent runs to synthesize yttrium-cerium alloy hydrides. The phases examined by the Raman scattering and x-ray diffraction measurements. The superconductivity is detected with the zero-resistance state at the critical temperature in the range of 97-140 K at pressures ranging from 114 GPa to 120$\pm$4 GPa. The maximum critical temperature of the synthesized hydrides is larger than those reported for cerium hydrides, while the corresponding stabilized pressure is much lower than those for superconducting yttrium hydrides. The structural analysis and theoretical calculations suggest that the phase of Y$_{0.5}$Ce$_{0.5}$H$_9$ has the space group $P6_3/mmc$ with the calculated critical temperature of 119 K, in fair agreement with the experiments. These results indicate that alloying superhydrides indeed can maintain relatively high critical temperature at modest pressures accessible by many laboratories., Comment: 6 pages, 6 figures