Visual retrieval tasks such as image retrieval and person re-identificat...
To promote the development of Vision-Language Pre-training (VLP) and
mul...
In this paper, we present ChatPLUG, a Chinese open-domain dialogue syste...
Fine-tuning a pre-trained model can leverage the semantic information fr...
Recent years have witnessed a big convergence of language, vision, and
m...
Video-language pre-training has advanced the performance of various
down...
Domain generalization (DG) aims to learn a model on one or more differen...
As a fundamental problem in computer vision, 3D object detection is
expe...
Pruning well-trained neural networks is effective to achieve a promising...
Supervised learning based object detection frameworks demand plenty of
l...
Knowledge distillation is an effective way for model compression in deep...
A standard one-stage detector is comprised of two tasks: classification ...
With the tremendous success of deep learning in visual tasks, the
repres...
Distance metric learning (DML) is to learn the embeddings where examples...
Most of object detection algorithms can be categorized into two classes:...
Satellite-based positioning system such as GPS often suffers from large
...
Factorization machine (FM) is a popular machine learning model to captur...
Distance metric learning (DML) has been studied extensively in the past
...
Recently, machine learning becomes important for the cloud computing ser...
Fine-grained visual categorization (FGVC) is to categorize objects into
...