45 citations · 93 across the 18 of their papers we have counts for
Showing 2019 · cs.CVShow all
3 papers · 2 filters
cs.CV2019
Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting
Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai +3
Tremendous variation in the scale of people/head size is a critical problem for crowd counting. To improve the scale invariance of feature representation, recent works extensively…
cs.CV2019
Learning Spatial Awareness to Improve Crowd Counting
Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai +2
The aim of crowd counting is to estimate the number of people in images by leveraging the annotation of center positions for pedestrians' heads. Promising progresses have been made…
cs.CV2019★ 4 cited
Decoupling Localization and Classification in Single Shot Temporal Action Detection
Yupan Huang, Qi Dai, Yutong Lu
Video temporal action detection aims to temporally localize and recognize the action in untrimmed videos. Existing one-stage approaches mostly focus on unifying two subtasks, i.e.,…