Search Results

The bidirectional long short-term memory (BiLSTM) network involves significant amount of parameter computations. This paper proposes the memristor-based bidirectional long short-term memory (MBiLSTM) network, with its capability of in-memory ...

Open repository projects serve as valuable resources for scholarly communication and knowledge dissemination. However, interacting with these repositories can be challenging due to the vast amount of data, the restriction of browsing features, and ...

In many real-world applications, 16-beam LiDAR-based 3D object detection (3DOD) is indispensable in scene understanding. However, the absence of well-labeled large-scale 16-beam LiDAR datasets impedes the development of these 3DOD methods. To avoid ...

• Integrated Solution Innovation: Combining explicit point cloud tech with implicit 3D Gaussian rendering to enhance leaf structure fidelity and address background blur.
• UV Texture Optimization: Specialized refinement for thin structures,...

In modern agricultural science research, high-fidelity three-dimensional (3D) leaf models are crucial for crop growth analysis. However, reconstructing the complex morphology and texture of leaves from a single viewpoint under varying natural ...

Unsupervised Domain Adaptation (UDA) is a promising strategy for representing unlabeled data through domain alignment. Nonetheless, a considerable number of whole-domain alignment techniques often neglect the essential interconnections between ...

• Using the discrepancy between images and labels can enhance the performance of variational auto-encoder for segmentation tasks.
• Variational inference enables the adaptive tuning of representational capabilities, which is guided by the ...

Generic event boundary detection (GEBD), inspired by human visual cognitive behaviors of segmenting videos into meaningful temporal chunks, finds utility in various applications. This paper demonstrates that SOTA GEBD models often prioritize final ...

Large language models (LLMs) adeptly navigate the intricate dependencies between sentences and texts, accurately predicting subsequent words or phrases. Such capabilities underscore LLMs’ supre-macy in sequential information processing and their ...

In recent years, considerable work has been done on the application of artificial intelligence (AI) and machine learning (ML) in the realm of cultural heritage. The purpose of this panel is to address the following questions: What is the current ...

The goal of objective point cloud quality assessment (PCQA) research is to develop quantitative metrics that measure point cloud quality in a perceptually consistent manner. Merging the research of cognitive science and intuition of the human visual ...

Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, typographic attacks, which disrupt ...

Recent proposed neural network-based Temporal Action Detection (TAD) models are inherently limited to extracting the discriminative representations and modeling action instances with various lengths from complex scenes by shared-weights detection ...

Generic event boundary detection (GEBD) aims at pinpointing event boundaries naturally perceived by humans, playing a crucial role in understanding long-form videos. Given the diverse nature of generic boundaries, spanning different video ...

Institutions have focused on the digitization process, metadata workflow, and digital infrastructure development for digital librarianship in recent decades. The undergoing digital shift that is accelerated by the pandemic crisis has signified the ...

This article concentrates on the fixed-time synchronization (FXTS) of fractional-order complex-valued delayed neural networks with discontinuous activation functions. On the basis of the nonsmooth analysis, differential inclusion theory, Lyapunov ...

The temporal action localization research aims to discover action instances from untrimmed videos, representing a fundamental step in the field of intelligent video understanding. With the advent of deep learning, backbone networks have been instrumental ...

Human activity recognition (HAR) based on multimodal wearable motion sensors is a valuable technology, and gymnastics action recognition is one of its important application scenarios. However, this field faces challenges such as excessive sensor ...

Display Omitted

Recent years have witnessed a growing interest in compressed video action recognition due to the rapid growth of online videos. It remarkably reduces the storage by replacing raw videos with sparsely sampled RGB frames and other compressed motion cues (...

Healthy dietary intake has a broad influence on the quality of life, and nutrition prediction plays a great role in the auxiliary decision-making of diet. Given a food image, existing nutrition prediction methods directly regress the nutrition content. ...

To address the calibration challenge in 3D printing technology, an improved calibration system has been developed, which facilitates the widespread use of bionic stents. Crucially, this system only requires a reference object with known dimensions ...

The knowledge gradient (KG) algorithm is a popular policy for the best arm identification (BAI) problem. It is built on the simple idea of always choosing the measurement that yields the greatest expected one-step improvement in the estimate of the best ...