C
Cong Zhang
Researcher at Shanghai Jiao Tong University
Publications - 5
Citations - 1906
Cong Zhang is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Object detection & Feature learning. The author has an hindex of 5, co-authored 5 publications receiving 1455 citations.
Papers
More filters
Proceedings ArticleDOI
Cross-scene crowd counting via deep convolutional neural networks
TL;DR: A deep convolutional neural network is proposed for crowd counting, and it is trained alternatively with two related learning objectives, crowd density and crowd count, to obtain better local optimum for both objectives.
Journal ArticleDOI
T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos
Kai Kang,Hongsheng Li,Junjie Yan,Zeng Xingyu,Bin Yang,Tong Xiao,Cong Zhang,Zhe Wang,Ruohui Wang,Xiaogang Wang,Wanli Ouyang +10 more
TL;DR: A deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos is proposed, called T-CNN.
Proceedings ArticleDOI
Factors in Finetuning Deep Model for Object Detection with Long-Tail Distribution
TL;DR: This paper investigates many factors that influence the performance in finetuning for object detection and proposes a hierarchical feature learning scheme that cluster objects into visually similar class groups and learn deep representations for these groups separately.
Journal ArticleDOI
Data-Driven Crowd Understanding: A Baseline for a Large-Scale Crowd Dataset
TL;DR: A data-driven approach is proposed as a baseline of crowd segmentation and estimation of crowd properties for the proposed dataset and extensive experiments demonstrate that the proposed method outperforms state-of-the-art approaches for crowd understanding.
Posted Content
Factors in Finetuning Deep Model for object detection.
TL;DR: In this paper, a hierarchical feature learning scheme is proposed to transfer knowledge from the group with large number of classes for learning features in its sub-groups, which shows 4.7% absolute mAP improvement on the ImageNet object detection dataset without increasing much computational cost at the testing stage.