Detection in Crowded Scenes: One Proposal, Multiple Predictions

By Xuangeng Chu, Anlin Zheng, X. Zhang. 2020

219 citations recorded by the source corpus.

We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes. The key of our approach is to let each proposal predict a set of correlated instances rather than a single one in previous proposal-based frameworks. Equipped with new techniques such as EMD Loss and Set NMS, our detector can effectively handle the difficulty of detecting highly overlapped objects. On a FPN-Res50 baseline, our detector can obtain 4.9\% AP gains on challenging CrowdHuman dataset and 1.0\% $\text{MR}^{-2}$ improvements on CityPersons dataset, without bells and whistles. Moreover, on less crowed datasets like COCO, our approach can still achieve moderate improvement, suggesting the proposed method is robust to crowdedness.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jiashi Feng
2. Chunhua Shen
3. Shuicheng Yan
4. Li Yuan
5. Hao Chen
6. Zhi Tian
7. Francis E. H. Tay
8. Tong He

In Computer Vision and Pattern Recognition

1. Chunhua Shen
2. Jiashi Feng
3. Shuicheng Yan
4. Dacheng Tao
5. Luc Van Gool
6. Xiaogang Wang
7. Alan L. Yuille
8. Ming-Hsuan Yang

Citations in the corpus

• Occluded Video Instance Segmentation: A Benchmark (2021, neutral): “[10] predicts multiple instances in one proposal.”
• FCOS: A Simple and Strong Anchor-Free Object Detector (2020, methodology): “h high confidence. By using the center-ness, MR 2 can be significantly reduced from 59 :04% to 51 34%. As a result, FCOS can achieve better results under all the three metrics. Furthermore, as shown in [4], it is more reasonable to let one proposal make multiple predictions under the highly crowded sc”
• Toward Accurate Person-level Action Recognition in Videos of Crowed Scenes (2020, methodology): “We apply a method aiming to predict instances in crowded scenes [3], named as “CrowdDet”.”
• Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge (2021, unknown): “[9] predicts multiple instances in one proposal.”
• A Simple Baseline for Pose Tracking in Videos of Crowed Scenes (2020, methodology): “We apply a method aiming to predict instances in crowded scenes [2], named as “CrowdDet”.”