Large-scale well-annotated datasets are of great importance for training...
Despite that the segment anything model (SAM) achieved impressive result...
Video-grounded dialogue understanding is a challenging problem that requ...
We present our submission to the ICASSP-SPGC-2023 ADReSS-M Challenge Tas...
Data augmentation is an effective regularization strategy for mitigating...
Emotion recognition is essential in the diagnosis and rehabilitation of
...
Many recent named entity recognition (NER) studies criticize flat NER fo...
Decoding human visual neural representations is a challenging task with ...
Span-based models are one of the most straightforward methods for named
...
The convolutional-based methods provide good segmentation performance in...
Long-term vertebral fractures severely affect the life quality of patien...
In recent years, several works have adopted the convolutional neural net...
Computed tomography (CT) samples with pathological annotations are diffi...
This paper presents a Refinement Pyramid Transformer (RePFormer) for rob...
Although deep learning algorithms have been intensively developed for
co...
This paper describes the THUEE team's speech recognition system for the ...
Neural named entity recognition (NER) models may easily encounter the
ov...
Electroencephalography (EEG) based emotion recognition has demonstrated
...
Medical information extraction consists of a group of natural language
p...
Pedestrian detection is the cornerstone of many vision based application...
Person search aims to simultaneously localize and identify a query perso...
Objective and Impact Statement. With the renaissance of deep learning,
a...
Most polyp segmentation methods use CNNs as their backbone, leading to t...
As an essential element for the diagnosis and rehabilitation of psychiat...
Locating diseases in chest X-ray images with few careful annotations sav...
Transformers have demonstrated great potential in computer vision tasks....
Person search has recently emerged as a challenging task that jointly
ad...
In recent years, significant progress has been made in the research of f...
We exploit liver cancer prediction model using machine learning algorith...
Locating lesions is important in the computer-aided diagnosis of X-ray
i...
Pedestrian detection is used in many vision based applications ranging f...
Traditional neural objection detection methods use multi-scale features ...
There are threefold challenges in emotion recognition. First, it is diff...
In emotion recognition, it is difficult to recognize human's emotional s...