653 Result(s)
-
Article
Open AccessKnowledge graph embedding closed under composition
Knowledge Graph Embedding (KGE) has attracted increasing attention. Relation patterns, such as symmetry and inversion, have received considerable focus. Among them, composition patterns are particularly import...
-
Article
Transmission-guided multi-feature fusion Dehaze network
Image dehazing is an important direction of low-level visual tasks, and its quality and efficiency directly affect the quality of high-level visual tasks. Therefore, how to quickly and efficiently process hazy...
-
Article
Incorporating self-attentions into robust spatial-temporal graph representation learning against dynamic graph perturbations
This paper proposes a Robust Spatial-Temporal Graph Neural Network (RSTGNN), which overcomes the limitations faced by graph-based models against dynamic graph perturbations using robust spatial-temporal self-a...
-
Article
A Multi-task Shared Cascade Learning for Aspect Sentiment Triplet Extraction Using BERT-MRC
The aspect sentiment triplet extraction (Triplet) aims at extracting aspect terms (AE), extracting aspect-oriented opinion terms (AOE), and discriminating aspect-level sentiment polarity (ASC) from the comment...
-
Article
Single-Temporal Supervised Learning for Universal Remote Sensing Change Detection
Bitemporal supervised learning paradigm always dominates remote sensing change detection using numerous labeled bitemporal image pairs, especially for high spatial resolution (HSR) remote sensing imagery. Howe...
-
Article
On Robust Cross-view Consistency in Self-supervised Monocular Depth Estimation
Remarkable progress has been made in self-supervised monocular depth estimation (SS-MDE) by exploring cross-view consistency, e.g., photometric consistency and 3D point cloud consistency. However, they are ver...
-
Article
RaSTFormer: region-aware spatiotemporal transformer for visual homogenization recognition in short videos
With the surge in network traffic, the homogenization of short video content is becoming increasingly prominent, resulting in low-quality entertainment due to proliferation and infringement. Therefore, recogni...
-
Article
Online binary classification from similar and dissimilar data
Similar-dissimilar (SD) classification aims to train a binary classifier from only similar and dissimilar data pairs, which indicate whether two instances belong to the same class (similar) or not (dissimilar). A...
-
Article
Unpaved road segmentation of UAV imagery via a global vision transformer with dilated cross window self-attention for dynamic map
Road segmentation is a fundamental task for dynamic map in unmanned aerial vehicle (UAV) path navigation. In unplanned, unknown and even damaged areas, there are usually unpaved roads with blurred edges, defor...
-
Article
Open AccessMCAD: Multi-classification anomaly detection with relational knowledge distillation
With the wide application of deep learning in anomaly detection (AD), industrial vision AD has achieved remarkable success. However, current AD usually focuses on anomaly localization and rarely investigates a...
-
Article
FSODv2: A Deep Calibrated Few-Shot Object Detection Network
Traditional methods for object detection typically necessitate a substantial amount of training data, and creating high-quality training data is time-consuming. We propose a novel Few-Shot Object Detection net...
-
Article
Unbiased scene graph generation using the self-distillation method
Scene graph generation (SGG) aims to build a structural representation for the image with the object instance and the relations between object pairs. Due to the long-tail distribution of the dataset labeling, ...
-
Article
A mutually enhanced multi-scale relation-aware graph convolutional network for argument pair extraction
Argument pair extraction (APE) is a fine-grained task of argument mining which aims to identify arguments offered by different participants in some discourse and detect interaction relationships between argume...
-
Article
MVTr: multi-feature voxel transformer for 3D object detection
Convolutional neural networks have become a powerful tool for partial 3D object detection. However, their power has not been fully realized for focusing on global information, which is crucial for object detec...
-
Article
HDUD-Net: heterogeneous decoupling unsupervised dehaze network
Haze reduces the imaging effectiveness of outdoor vision systems, significantly degrading the quality of images; hence, reducing haze has been a focus of many studies. In recent years, decoupled representation...
-
Chapter and Conference Paper
Semantic Preferences of Biran and Yiding: A Distinctive Collexeme Analysis of Chinese Near-Synonymous Constructions of “Mod + Verb”
The Chinese modals biran ‘must be, definitely’ and yiding ‘must be, definitely’ can both express the sense of epistemic necessity. “Modal + verb” is a representative construction that expresses modal judgment. Th...
-
Chapter and Conference Paper
HiFiHR: Enhancing 3D Hand Reconstruction from a Single Image via High-Fidelity Texture
We present HiFiHR, a high-fidelity hand reconstruction approach that utilizes render-and-compare in the learning-based framework from a single image, capable of generating visually plausible and accurate 3D ha...
-
Chapter and Conference Paper
Research on Comprehensive Blockchain Regulation and Anti-fraud System
The blockchain technology has attracted attention due to its characteristics of anonymity, openness, decentralization, traceability, and tamper-resistance. However, with the development of the blockchain indus...
-
Chapter and Conference Paper
Rearranging Inv Message in the Bitcoin to Construct Covert Channels
Covert channels aim to conceal the communication behaviors and are widely applied to transmit sensitive data. Blockchains are well-suited for building state-of-the-art covert channels due to their decentraliza...
-
Chapter and Conference Paper
PtbStolen: Pre-trained Encoder Stealing Through Perturbed Samples
Recent years have witnessed the huge success of adopting the self-supervised learning paradigm into pre-train effective encoders [1].
