Search Results

In real urban driving scenes, human actions are very complex and have the characteristic of multiple concurrent actions. It has a great significance to detect human actions in urban traffic scenes for auxiliary or autonomous driving systems. In ...

• The TITAN-Human Action dataset is built for action detection in urban driving scenes.
• We propose a novel semantics-guided network for spatial-temporal action detection.
• The experimental results show that the proposed SGDNet ...

Image captioning is a typical task in multimodal learning. Many existing image captioning models rely on autoregressive paradigms, causing notable delays in inference and impacting practical applications. While non-autoregressive methods ...$\mathrm{}$

Replaying episodic memory hippocampus-based is a promising class incremental learning (CIL) method, and it must address the problem of catastrophic forgetting. However, most current studies have ignored background information provided by the ...

Fast and accurate object detection in foggy weather is crucial for visual tasks such as autonomous driving and video surveillance. Existing methods typically preprocess images with enhancement techniques before the object detector, so that the ...

• We design a Restoration Subnetwork Module (RSM) based on the atmospheric scattering model and three Adaptive Feature Fusion Modules (AFFM) for encouraging the network to learn more discriminative features from foggy images.
• We ...

Manual scribbles have been introduced to RGB-D Salient Object Detection (SOD) as a credible indicator for salient regions and backgrounds, helping to strike a balance between detection accuracy and labeling efficiency. Previous works address this task by ...

• Semantic segmentation of strawberries using the modified Segment Anything Model.
• Class weight resolves severe sample category imbalance.
• CLAHE algorithm reduces the natural light impact in agricultural image processing.
• ...

Strawberry holds significant economic value, but the laborious and time-consuming process of evaluating phenotypic traits in numerous germplasm resources during breeding poses a challenge. Prior studies relied on manual image collection within a ...

Virtual sample generation (VSG) is an important technology for dealing with small sample learning in some industries. Using evolutionary computation algorithms to solve VSG is a promising way. However, two issues remain unaddressed in the existing VSG ...

Temporal language grounding in videos aims to ground one video segment in an untrimmed video based on a given sentence query. The main challenge in this task lies in how to align the video and textual modalities effectively. Most existing methods ...

Existing two-stage methods for 3D Human Pose Estimation often use 2D poses as input, which are then lifted to obtain 3D representations. This typically involves frame-by-frame estimation, whether in 2D or 3D, resulting in high computational ...

• TDFR recovers dense temporal frames from sparsely ones provided by a 2D pose estimator.
• TDFR facilitates 10x increase in estimation speed while maintaining accuracy.
• STAF module adaptively fuses through both spatial and temporal ...

The purpose of this study is to explore the application of generative artificial intelligence (AI) in Chinese literacy teaching in the first grade of primary school and its influence on teachers' practical knowledge construction and teaching innovation. ...

In this paper, a high dimensional double rotor model is proposed. We establish its dynamic equations, and simply it into a four-dimensional mapping form. The bifurcations of the double rotor mapping under different control parameters are ...

Visible-infrared person re-identification (VI-ReID) has raised more attention in night-time surveillance applications due to the struggle to capture valid appearance information under poor illumination conditions via visible cameras. Existing works ...

Recent research about lung cancer risk prediction model require the data for predicting as same as the data for training whether based on single-source data or multi-source data. Both of them either cannot fully use collected multi-source data to ...

In recent years, although research on person re-identification (ReID) has made significant progress, occluded person ReID remains a major challenge. In real-world scenes, persons are often occluded by various obstacles such as vehicles, umbrellas,...

• Designed Mask-guided Discriminative Feature Enhancement and Fusion (MDFEF) module to balance global and local information, suppressing occlusion noise.
• Proposed end-to-end Mask-guided Discriminative Feature Network (MDFNet) for ...

Knowledge graph embedding (KGE) is essential for various applications, particularly in link prediction and other downstream tasks. While existing convolutional neural network (CNN)-based methods have been effective, they face challenges in ...

• We construct a new dynamic adaptive atrous convolutional neural network.
• Convolutional kernel can dynamically learn multidimensional attentions to inputs.
• Model can expand receptive field and avoid losses from pooling and ...

Multivariate time series forecasting is a significant research problem in many fields such as economics, finance and transportation, where simultaneous long- and short-term forecasting is required. However, current techniques are typically ...

• It is for long- and short-term forecasting on multivariate time series data.
• It is a multi-granular hierarchy network using idea of granularity division.
• The external relationships and internal correlation are introduced and mined.

Advances in large language models (LLMs) have empowered a variety of applications. However, there is still a significant gap in research when it comes to understanding and enhancing the capabilities of LLMs in the field of mental health. In this work, we ...

Depression detection is a challenging and crucial task in psychological illness diagnosis. Utilizing online user posts to predict whether a user suffers from depression seems an effective and promising direction. However, existing methods suffer from ...