Black-box unsupervised domain adaptation (UDA) learns with source predic...
Traditional domain adaptation assumes the same vocabulary across source ...
Document-level neural machine translation (NMT) has outperformed
sentenc...
Most visual recognition studies rely heavily on crowd-labelled data in d...
Few-shot class-incremental learning (FSCIL) has recently attracted exten...
Multi-modal image registration spatially aligns two images with differen...
Blind image quality assessment (BIQA) remains challenging due to the
div...
Most existing scene text detectors require large-scale training data whi...
Cybersecurity breaches are the common anomalies for distributed
cyber-ph...
Rooted in genetics, human complex diseases are largely influenced by
env...
Multi-scale features have been proven highly effective for object detect...
DBSCAN is widely used in many scientific and engineering fields because ...
Domain adaptive panoptic segmentation aims to mitigate data annotation
c...
Subsampling methods aim to select a subsample as a surrogate for the obs...
Existing motion capture datasets are largely short-range and cannot yet ...
The divide-and-conquer method has been widely used for estimating large-...
Unsupervised domain adaptation (UDA) aims to learn a well-performed mode...
This paper studies the estimation of large-scale optimal transport maps
...
Background: Extensive clinical evidence suggests that a preventive scree...
Graph Neural Networks (GNNs) have been widely used for the representatio...
This paper presents a matching network to establish point correspondence...
The prevalent approach in domain adaptive object detection adopts a two-...
To generate "accurate" scene graphs, almost all existing methods predict...
Although current face anti-spoofing methods achieve promising results un...
Visual scene graph generation is a challenging task. Previous works have...
Sufficient dimension reduction is used pervasively as a supervised dimen...
Optimal transport has been one of the most exciting subjects in mathemat...
The Transformer translation model (Vaswani et al., 2017) based on a
mult...
We consider the problem of approximating smoothing spline estimators in ...
Distant Supervised Relation Extraction (DSRE) is usually formulated as a...
The Transformer translation model employs residual connection and layer
...
One of the difficulties of neural machine translation (NMT) is the recal...
Compared to traditional statistical machine translation (SMT), neural ma...