With recent advancements in natural language processing, Large Language
...
Few-shot object detection (FSOD) aims to expand an object detector for n...
Self-supervised pre-training and transformer-based networks have
signifi...
Few-shot object detection (FSOD) aims to expand an object detector for n...
The generalization power of the pre-trained model is the key for few-sho...
Conventional training of deep neural networks usually requires a substan...
The recently proposed pseudo-LiDAR based 3D detectors greatly improve th...
Real-world object detectors are often challenged by the domain gaps betw...
Monocular 3D object detection task aims to predict the 3D bounding boxes...
We present an efficient 3D object detection framework based on a single ...
The visual cues from multiple support regions of different sizes and
res...
The state-of-the-art performance for object detection has been significa...
In existing works that learn representation for object detection, the
re...
In this paper, we propose deformable deep convolutional neural networks ...
In this paper, we propose multi-stage and deformable deep convolutional
...