Multi-task learning (MTL), a learning paradigm to learn multiple related...
Conditional diffusion models have demonstrated impressive performance in...
In DNA-based data storage, DNA codes with biochemical constraints and er...
Few-shot semantic segmentation (FSS) aims to form class-agnostic models
...
We consider the problem of efficient construction of q-ary 2-deletion
co...
In this work, we propose a numerical method to compute the Wasserstein
H...
Synthesizing photo-realistic images from a point cloud is challenging be...
Few-shot semantic segmentation (FSS) aims to form class-agnostic models
...
Semantic segmentation is still a challenging task for parsing diverse
co...
Neural implicit surface learning has shown significant progress in multi...
The core of out-of-distribution (OOD) detection is to learn the
in-distr...
Facial attractiveness prediction (FAP) aims to assess the facial
attract...
For codes equipped with metrics such as Hamming metric, symbol pair metr...
In this paper, we propose the Generalized Parametric Contrastive Learnin...
We study the optimal control formulation for stochastic nonlinear Schrod...
In coding theory, constructing codes with good parameters is one of the ...
In classical coding theory, it is common to construct new codes via
prop...
Unsupervised domain adaptation in semantic segmentation has been raised ...
Inverse text normalization (ITN) is used to convert the spoken form outp...
A locally repairable code is called Singleton-optimal if it achieves the...
Neural Radiance Fields (NeRF) has been wildly applied to various tasks f...
Camera-based 3D object detectors are welcome due to their wider deployme...
3D point cloud segmentation has made tremendous progress in recent years...
We revisit the one- and two-stage detector distillation tasks and presen...
The present paper mainly studies limits and constructions of insertion a...
Maximally recoverable local reconstruction codes (MR LRCs for short) hav...
Rapid progress in 3D semantic segmentation is inseparable from the advan...
Effectively structuring deep knowledge plays a pivotal role in transfer ...
We study the vision transformer structure in the mobile level in this pa...
In this paper, we propose Parametric Contrastive Learning (PaCo) to tack...
Point cloud registration is a fundamental problem in 3D computer vision....
Semantic segmentation has made tremendous progress in recent years. Howe...
Monge map refers to the optimal transport map between two probability
di...
Knowledge distillation transfers knowledge from the teacher network to t...
Deep neural networks may perform poorly when training datasets are heavi...
Unsupervised representation learning with contrastive learning achieved ...
Video instance segmentation (VIS) aims to segment and associate all inst...
We propose a new formulation and learning strategy for computing the
Was...
Deep learning algorithms face great challenges with long-tailed data
dis...
Previous adversarial training raises model robustness under the compromi...
Target-Based Sentiment Analysis aims to detect the opinion aspects (aspe...
Instance segmentation is an important task for scene understanding. Comp...
Currently, there have been many kinds of voxel-based 3D single stage
det...
Learning nonlinear dynamics of aggregate data is a challenging problem s...
Most state-of-the-art 3D object detectors heavily rely on LiDAR sensors ...
Current instance segmentation methods can be categorized into
segmentati...
We achieve 3D semantic scene labeling by exploring semantic relation bet...
Driver identification has emerged as a vital research field, where both
...
Insertion and deletion (insdel for short) errors are synchronization err...
Person re-identification aims to identify whether pairs of images belong...