Existing wavelet pooling methods discard the high-frequency sub-bands, which can improve the noise-robustness of convolutional neural networks (CNNs) but lose the essential detailed features. Besides, most of them depend on different wavelets, which is ...

Quantization replaces floating point arithmetic with integer arithmetic in deep neural networks, enabling more efficient on-device inference with less power and memory. However, it also brings in loss of generalization and even potential errors to ...

Keyphrase extraction aims to identify the purport-specific words or phrases from a free-format natural language document, which also requires the keyphrases to be concise and informative. Existing works mainly encode the document and phrases into ...

• Documents in real settings exhibit complex, diverse semantic richness.
• Keyphrases from a document often distribute across multiple topics.
• We propose a gated topic modeling schema for semantic-adaptive assignment.
• Scoring ...

Recent years have seen the wide application of natural language processing (NLP) models in crucial areas such as finance, medical treatment, and news media, raising concerns about the model robustness and vulnerabilities. We find that prompt ...

Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. Along this line, we propose a formal framework to evaluate ...

High-utility sequential pattern mining (HUSPM) has emerged as an important topic due to its wide application and considerable popularity. However, due to the combinatorial explosion of the search space when the HUSPM problem encounters a low-utility ...

Dialogue State Tracking (DST) module is an essential component of task-oriented dialog systems to understand users’ goals and needs. Collecting dialogue state labels including slots and values can be costly, requiring experts to annotate all (slot, ...

Global average pooling (GAP) plays an important role in traditional channel attention. However, there is the disadvantage of insufficient information to use the result of GAP as the channel scalar. At the same time, the existing spatial attention models ...

Nanorobotic manipulation inside Scanning Electron Microscope (SEM) is widely used in nanomaterial characterization and assembly tasks. However, tedious and time-consuming hardware regulations, like axis alignment, are still critical and mandatory to keep ...

Training a model from scratch in a data-deficient environment is a challenging task. In this challenge, multiple differentiated backbones are used to train, and a number of tricks are used to assist in model training, such as initializing weights, ...

Intelligent IoT is a prerequisite for societal priorities such as a smart power grid, smart urban infrastructures and smart highways. These applications bring requirements such as real-time guarantees, data and action consistency, fault-tolerance, high ...

Over the last decade, automatic differentiation (AD) has profoundly impacted graphics and vision applications --- both broadly via deep learning and specifically for inverse rendering. Traditional AD methods ignore gradients at discontinuities, instead ...

Deep neural networks have been widely adopted for many real-world applications and their reliability has been widely concerned. This paper introduces a notion of ε-weakened robustness (briefly as ε-robustness) for analyzing the reliability and some ...

Pneumonia mainly refers to lung infections caused by pathogens, such as bacteria and viruses. Currently, deep learning methods have been applied to identify pneumonia. However, the traditional deep learning methods for pneumonia identification take less ...

In an autonomous underwater vehicles– (AUVs–) based optical-acoustic hybrid network, it is critical to achieve ultra high-speed reliable communications, in order to reap the benefits of the complementary systems and perform high-bandwidth and low-latency ...

Utility mining has emerged as an important and interesting topic owing to its wide application and considerable popularity. However, conventional utility mining methods have a bias toward items that have longer on-shelf time as they have a greater chance ...

Dongba hieroglyphs is a text form that transitions from pictographs to pictographs and phonetic characters. In order to distinguish them from modern characters, many Dongba hieroglyphs use tables to distinguish between Dongba hieroglyphs and modern ...

The Vision Meets Drone (VisDrone2020) Single Object Tracking is the third annual UAV tracking evaluation activity organized by the VisDrone team, in conjunction with European Conference on Computer Vision (ECCV 2020). The VisDrone-SOT2020 ...

Among liver cancer patients, diabetes is one of the most common complications. This paper uses the Diabetes Dataset of the National Clinical Medical Science Data Center to explore the factors affecting liver cancer in patients with type 2 diabetes ...

Nearly every commodity imaging system we directly interact with, or indirectly rely on, leverages power efficient, application-adjustable black-box hardware image signal processing (ISPs) units, running either in dedicated hardware blocks, or as ...