Rail detection, essential for railroad anomaly detection, aims to identi...
Semantic segmentation usually benefits from global contexts, fine
locali...
Studies have proven that domain bias and label bias exist in different F...
The paper describes our proposed methodology for the six basic expressio...
Automatic smoky vehicle detection in videos is a superior solution to th...
Video frame interpolation task has recently become more and more prevale...
Stereo matching is crucial for binocular stereo vision. Existing methods...
Recently 3D point cloud learning has been a hot topic in computer vision...
The paper describes our proposed methodology for the seven basic express...
Face recognition has achieved significant progress in deep-learning era ...
Reasoning the human-object interactions (HOI) is essential for deeper sc...
Human-Object Interaction (HOI) detection, inferring the relationships be...
Although unsupervised person re-identification (Re-ID) has drawn increas...
The audio-video based emotion recognition aims to classify a given video...
The domain diversities including inconsistent annotation and varied imag...
Deep networks achieve excellent results on large-scale clean data but de...
Human-Object interaction (HOI) detection aims to localize and infer
rela...
Video action anticipation aims to predict future action categories from
...
Annotating a qualitative large-scale facial expression dataset is extrem...
Online action detection (OAD) is a practical yet challenging task, which...
Multi-label image recognition is a task that predicts a set of object la...
This paper considers recognizing products from daily photos, which is an...
This paper presents our approach for the engagement intensity regression...
The video-based facial expression recognition aims to classify a given v...
Occlusion and pose variations, which can change facial appearance
signif...
Deep convolutional neural networks have recently proven extremely effect...
Video based action recognition is one of the important and challenging
p...
Many efforts have been devoted to develop alternative methods to traditi...