When applied to autonomous vehicle settings, action recognition can help...
The two-stage methods for instance segmentation, e.g. Mask R-CNN, have
a...
Training a small student network with the guidance of a larger teacher
n...
In this paper we propose a novel network adaption method called
Differen...
Recently proposed decoupled training methods emerge as a dominant paradi...
One practice of employing deep neural networks is to apply the same
arch...
Modern object detection methods can be divided into one-stage approaches...
This article introduces the solutions of the team lvisTraveler for LVIS
...
Seeking effective neural networks is a critical and practical field in d...
Recent works imply that the channel pruning can be regarded as searching...
Object recognition techniques using convolutional neural networks (CNN) ...
Knowledge distillation (KD) is one of the most potent ways for model
com...
Recent object detection and instance segmentation tasks mainly focus on
...
Grid R-CNN is a well-performed objection detection framework. It transfo...
This paper presents a review of the 2018 WIDER Challenge on Face and
Ped...
Convolutional Neural Networks (CNNs) become deeper and deeper in recent
...
This paper proposes a novel object detection framework named Grid R-CNN,...
Detection and learning based appearance feature play the central role in...