Semantic segmentation usually suffers from a long-tail data distribution...
Most existing learning-based pose estimation methods are typically devel...
Domain adaptive semantic segmentation aims to transfer knowledge from a
...
Self-supervised pre-training and transformer-based networks have
signifi...
Inspired by masked language modeling (MLM) in natural language processin...
Multimodal machine translation (MMT) aims to improve translation quality...
Autoregressive language modeling (ALM) have been successfully used in
se...
Visual anomaly detection plays a crucial role in not only manufacturing
...
Unlike indirect methods that usually require time-consuming post-process...
Visual tasks vary a lot in their output formats and concerned contents,
...
Self-training has shown great potential in semi-supervised learning. Its...
Few prior 6D pose estimation methods use a backbone network to extract
f...
Unsupervised anomaly detection and localization, as of one the most prac...
In this paper, a modified intermediately homogenized peridynamic (IH-PD)...
As RGB-D sensors become more affordable, using RGB-D images to obtain
hi...
Self-supervised learning (SSL) holds promise in leveraging large amounts...
The crux of semi-supervised semantic segmentation is to assign adequate
...
The punctuation restoration task aims to correctly punctuate the output
...
Unsupervised anomaly detection and localization is crucial to the practi...
The essence of unsupervised anomaly detection is to learn the compact
di...
Multilingual Neural Machine Translation (MNMT) has aroused widespread
in...
Transformer has been widely used for self-supervised pre-training in Nat...
Existing multilingual machine translation approaches mainly focus on
Eng...
Multilingual neural machine translation aims at learning a single transl...
This paper describes our VolcTrans system on WMT20 shared news translati...
Recent developments in image classification and natural language process...
In this dissertation, we cover some recent advances in collaborative
fil...
The collaborative ranking problem has been an important open research
qu...
In this paper, we consider recommender systems with side information in ...
In deep neural nets, lower level embedding layers account for a large po...
In this paper, we propose a listwise approach for constructing user-spec...