Temporal Knowledge Graph (TKG) is an extension of traditional Knowledge ...
The goal of scene text image super-resolution is to reconstruct
high-res...
The Class Incremental Semantic Segmentation (CISS) extends the tradition...
Entity Matching (EM), which aims to identify all entity pairs referring ...
Directed grey-box fuzzing (DGF) is a target-guided fuzzing intended for
...
Temporal knowledge graph (TKG) reasoning aims to predict the future miss...
Recently, Visual Information Extraction (VIE) has been becoming increasi...
Non-autoregressive translation (NAT) model achieves a much faster infere...
Feature transformation for AI is an essential task to boost the effectiv...
The problem of testing the equality of mean vectors for high-dimensional...
Urban traffic speed prediction aims to estimate the future traffic speed...
The problems of large-scale multiple testing are often encountered in mo...
In this paper, we propose to compute Voronoi diagrams over mesh surfaces...
Graph contrastive learning (GCL) has been an emerging solution for graph...
Consider words of length n. The set of all periods of a word of length n...
Entity Matching (EM), which aims to identify whether two entity records ...
Domain generalization (DG) for person re-identification (ReID) is a
chal...
Entity alignment (EA) aims at finding equivalent entities in different
k...
Occlusion poses a major challenge for person re-identification (ReID).
E...
In this paper, we propose a single-agent Monte Carlo based reinforced fe...
Surface reconstruction from noisy, non-uniform, and unoriented point clo...
Unsupervised Domain Adaptive (UDA) object re-identification (Re-ID) aims...
Entity Resolution (ER) aims to identify whether two tuples refer to the ...
The reading of arbitrarily-shaped text has received increasing research
...
In recent years, there are a large number of recommendation algorithms
p...
Top-N item recommendation has been a widely studied task from implicit
f...
Existing part-aware person re-identification methods typically employ tw...
Fuzzing is one of the most efficient technology for vulnerability detect...
While Graph Neural Network (GNN) has shown superiority in learning node
...
How to learn a stable model under agnostic distribution shift between
tr...
Greybox fuzzing has been the most scalable and practical approach to sof...
Part-level representations are important for robust person re-identifica...
This paper introduces an accurate edge-based smoothed finite element met...
Detecting scene text of arbitrary shapes has been a challenging task ove...
Driven by great demands on low-latency services of the edge devices (EDs...
Extracting appropriate features to represent a corpus is an important ta...
This report summarises our method and validation results for the ISIC
Ch...
Leveraging the disparity information from both left and right views is
c...
State-of-the-art recommendation algorithms -- especially the collaborati...