Learning Efficient Single-Stage Pedestrian Detectors by Asymptotic Localization Fitting

By Wei David Liu, Shengcai Liao, Weidong Hu, Xuezhi Liang, Xiao Chen. 2018

243 citations recorded by the source corpus.

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. Ling Shao
2. Songtao Liu
3. Bernard Ghanem
4. Junsong Yuan
5. Ming Ding
6. Yunhong Wang
7. Yancheng Bai
8. Qian Zhang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ling Shao
3. Xiaogang Wang
4. Dacheng Tao
5. Bernard Ghanem
6. Ming-Hsuan Yang
7. Yi Yang
8. Andrew Zisserman

Citations in the corpus

• Pedestrian Detection: The Elephant In The Room (2020, methodology): “We evaluated recently proposed CSP [23], ALFNet [22] and FRCNN [42](tailored for pedestrian detection) 5 .”
• Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians (2020, background): “With the renaissance of convolutional neural networks, many deep learning based methods on pedestrian detection [27, 28, 10, 26, 24, 23, 19, 17, 25, 18, 48, 36] significantly outperform the hand-crafted feature based methods [55, 61, 21, 14].”
• KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild (2020, methodology): “1) CityPersons Data Set: We compare our proposed KGSNet with several state-of-the-art pedestrian detectors on the CityPersons validation set, including attention RCNN [40], adapted faster RCNN [24], TTL [41], repulsion loss [25], OR-RCNN [26], ALFNet [63], and Bi-box Reg [38].”
• High-Level Semantic Feature Detection: A New Perspective for Pedestrian Detection (2019, methodology): “0% MR upon the closest competitor (ALFNet [28]), while the speed is comparable on the same running environment with 0.”
• A Survey of Deep Learning-Based Object Detection (2019, methodology): “[97] W.”
• Adaptive NMS: Refining Pedestrian Detection in a Crowd (2019, background): “[24] explores the potential of single-stage detectors on pedestrian detection by stacking multi-step prediction for asymptotic localization.”
• M3D-RPN: Monocular 3D Region Proposal Network for Object Detection (2019, background): “2D Detection: Many recent works have addressed 2D detection in both generic domain [17, 20, 22, 25, 28] and in urban scenes [2, 3, 23, 29, 38, 41].”