Improve Crowd Size Estimation by Leveraging Deformable Convolutional Neural Network and Deformable Region of Interest

Eric, Lubamba Kasangu; Cheng, Kevang; Tahir, Rabia; Khokhar, Mohammad Saddam

doi:10.1109/icsai48974.2019.9010125

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To handle position variation and achieve various shapes' self‐adaptive localization, dilated deformable offsets are added to RoI pooling's regular location to construct MMRP 15–17 …”

Section: Invisionmentioning

confidence: 99%

“…To handle position variation and achieve various shapes' self-adaptive localization, dilated deformable offsets are added to RoI pooling's regular location to construct MMRP. [15][16][17] For the input representation x, RoI is segmented by RoI pooling into k k × bins and generates an output representation y. In MMRP, for the s(i,j)-th bin, we have where n ij is the number of pixels in the bin, binning locations are enlarged by the offsets…”

Section: Mmrpmentioning

confidence: 99%

See 1 more Smart Citation

Robot target recognition using deep federated learning

Xue

Feng

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Robot target recognition is a critical and fundamental machine vision task. In this paper, InVision, a robot target recognition approach is proposed using deep federated learning. Particularly, deep geometric learning is developed to improve the perception capabilities of convolutional neural networks, and promote the representation maps' resolutions while achieving good recognition performance. Moreover, federated metric learning is constructed to protect user data privacy across multiple devices and relieve the problem of inadequate available labeled training data. To improve the speed of the recognition system, a lightweight deep neural network is presented. Extensive experiments are performed, showing that InVision significantly outperforms the outstanding comparison approaches.

show abstract

“…To handle position variation and achieve various shapes' self‐adaptive localization, dilated deformable offsets are added to RoI pooling's regular location to construct MMRP 15–17 …”

Section: Invisionmentioning

confidence: 99%

Section: Mmrpmentioning

confidence: 99%