activity
20172022
most citedDETR for Crowd Pedestrian Detection

38 citations · 52 across the 7 of their papers we have counts for

collaborators

6 papers

cs.CV2021

GAIA: A Transfer Learning System of Object Detection that Fits Your Needs

Xingyuan Bu, Junran Peng, Junjie Yan +2

Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently. However, as the…

cs.CV202038 cited

DETR for Crowd Pedestrian Detection

Matthieu Lin, Chuming Li, Xingyuan Bu +5

Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped…

cs.CV20204 cited

Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels

Junran Peng, Xingyuan Bu, Ming Sun +3

Training with more data has always been the most stable and effective way of improving performance in deep learning era. As the largest object detection dataset so far, Open Images…

cs.CV20193 cited

Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019

Xingyuan Bu, Junran Peng, Changbao Wang +2

This report details our solution to the Google AI Open Images Challenge 2019 Object Detection Track. Based on our detailed analysis on the Open Images dataset, it is found that the…

cs.CV2018

Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance

Yuan Gao, Xingyuan Bu, Yang Hu +4

This report demonstrates our solution for the Open Images 2018 Challenge. Based on our detailed analysis on the Open Images Datasets (OID), it is found that there are four typical…

cs.CV20175 cited

Learning a Robust Representation via a Deep Network on Symmetric Positive Definite Manifolds

Zhi Gao, Yuwei Wu, Xingyuan Bu +1

Recent studies have shown that aggregating convolutional features of a pre-trained Convolutional Neural Network (CNN) can obtain impressive performance for a variety of visual task…