2,631 Result(s)
-
Article
Dual stage black-box adversarial attack against vision transformer
Relying on wide receptive fields, Vision Transformers (ViTs) are more robust than Convolutional Neural Networks (CNNs). Consequently, some transfer-based attack methods that perform well on CNNs perform poorly...
-
Article
Gait Characteristics and Adaptation Strategies of Ants with Missing Legs
This paper systematically studies the movement behavior changes of Camponotus japonicus under one or two leg injuries. Firstly, a linear motion channel matching the size of the ants’ legs was designed, and the...
-
Article
An extended power geometric technique for multiple-attribute decision-making under single-valued neutrosophic sets and applications to embedded computers’ performance evaluation
Embedded computer systems refer to specialized computer systems that integrate operating systems and functional software into computer hardware systems, are application centric, based on computer technology, a...
-
Article
A combined exponential TODIM-GRA framework for multiple-attribute group decision-making under 2-tuple linguistic Pythagorean fuzzy sets and applications to art teaching quality evaluation in higher education institutions
With the increasing number of students majoring in art in universities, the improvement of the quality of art teaching in universities is becoming increasingly important. However, due to the unique characteris...
-
Article
Dual-AutoEncoder & Bipartite Graph Embedding for article recommendation
Existing methods in article recommendation fail to fully use the article information, or pay less attention to the correlations among articles and "User-Article"s, resulting in inaccurate recommendation perfor...
-
Article
ClKI: closed-loop and knowledge iterative via self-distillation for image sentiment analysis
Image sentiment analysis has received a lot of attention due to the fact that users prefer to express their private emotions using images on social platforms. Researchers strive to obtain more discriminative f...
-
Article
Learning to detect extreme objects for remote sensing images
The scale and shape of objects in remote sensing images varies greatly, and thus the object detection of remote sensing image has always been a relatively challenging task. Focusing on the problem of multi-sca...
-
Article
A Novel Memristors Based Echo State Network Model Inspired by the Brain’s Uni-hemispheric Slow-Wave Sleep Characteristics
Memristors serve as electronic components with the ability to store charge and demonstrate resistive states, which are similar to the synaptic connections between biological neurons. For this reason, they have...
-
Article
PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition
In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mi...
-
Article
Machine learning-based spatial downscaling and bias-correction framework for high-resolution temperature forecasting
High-resolution temperature forecasting plays a crucial role in various applications such as climate impact assessment, hydrological modeling, and localized weather forecasting. The existing low-resolution for...
-
Article
Open AccessAnalysis of Emotional Tendency of Tourism Consumers Based on LSTM and Fuzzy Control Algorithm
Learning the emotional tendency of travelers improves their interests and provide optimal traveling recommendations. This, however, requires large volumes of data such as travel plans, visit sites, personal in...
-
Article
ROMOT: Referring-expression-comprehension open-set multi-object tracking
Traditional multi-object tracking is limited to tracking a predefined set of categories, whereas open-vocabulary tracking expands its capabilities to track novel categories. In this paper, we propose ROMOT (re...
-
Article
Contrastive visual feature filtering for generalized zero-shot learning
Generalized zero-shot learning aims to classify images from seen and unseen classes only by training with seen samples, which encounters the seen-unseen bias problem. Existing methods seek to solve the seen-un...
-
Article
Open AccessDynamic Color Regulation of the Lycaenid Butterfly Wing Scales
Butterfly coloration originates from the finely structured scales grown on the underlying wing cuticle. Most researchers who study butterfly scales are focused on the static optic properties of cover scales, w...
-
Article
Open AccessCross-modal learning using privileged information for long-tailed image classification
The prevalence of long-tailed distributions in real-world data often results in classification models favoring the dominant classes, neglecting the less frequent ones. Current approaches address the issues in ...
-
Article
Semantic-alignment transformer and adversary hashing for cross-modal retrieval
Deep Cross-Modal Hashing (DCMH) has garnered significant attention in the field of cross-modal retrieval due to its advantages such as high computational efficiency and small storage space. However, existing D...
-
Article
Multi-label semantic sharing based on graph convolutional network for image-to-text retrieval
Cross-modal hashing has attracted widespread attention due to its ability to reduce the complexity of storage and retrieval. However, many existing methods use a symbolic function to map hash codes, which lead...
-
Article
Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-Wise Pseudo Labeling
The Audio-Visual Video Parsing task aims to identify and temporally localize the events that occur in either or both the audio and visual streams of audible videos. It often performs in a weakly-supervised man...
-
Article
Open AccessDynamic YOLO for small underwater object detection
The practical application of object detection inevitably encounters challenges posed by small objects. In underwater object detection, a crucial method for marine exploration, the presence of small objects in ...
-
Article
Retraction Note: Quality assessment for virtual reality technology based on real scene