Object detection via inaccurate bounding boxes supervision has boosted a...
Pedestrian detection in the wild remains a challenging problem especiall...
Referring video object segmentation aims to segment the object referred ...
Point-based object localization (POL), which pursues high-performance ob...
Bounding-box annotation form has been the most frequently used method fo...
Unsupervised person re-identification (re-ID) remains a challenging task...
Weakly supervised object localization (WSOL) is a challenging problem wh...
Detecting tiny objects ( e.g., less than 20 x 20 pixels) in large-scale
...
Unmanned Aerial Vehicle (UAV) offers lots of applications in both commer...
FPN-based detectors have made significant progress in general object
det...
The 1st Tiny Object Detection (TOD) Challenge aims toencourage research ...
Visual object detection has achieved unprecedented ad-vance with the ris...
Weakly supervised object detection is a challenging task when provided w...
In this paper, we explore the redundancy in convolutional neural network...