A Caltech Library Service

Contextual Attention for Hand Detection in the Wild

Narasimhaswamy, Supreeth and Wei, Zhengwei and Wang, Yang and Zhang, Justin and Hoai, Minh (2019) Contextual Attention for Hand Detection in the Wild. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE , Piscataway, NJ, pp. 9566-9575. ISBN 9781728148038.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


We present Hand-CNN, a novel convolutional network architecture for detecting hand masks and predicting hand orientations in unconstrained images. Hand-CNN extends MaskRCNN with a novel attention mechanism to incorporate contextual cues in the detection process. This attention mechanism can be implemented as an efficient network module that captures non-local dependencies between features. This network module can be inserted at different stages of an object detection network, and the entire detector can be trained end-to-end. We also introduce large-scale annotated hand datasets containing hands in unconstrained images for training and evaluation. We show that Hand-CNN outperforms existing methods on the newly collected datasets and the publicly available PASCAL VOC human layout dataset. Data and code:

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Additional Information:© 2019 IEEE. This work is partially supported by VinAI Research and NSF IIS-1763981. Many thanks to Tomas Simon for his suggestion about the COCO dataset and Rakshit Gautam for his contribution to the data annotation process.
Funding AgencyGrant Number
Record Number:CaltechAUTHORS:20200306-124356519
Persistent URL:
Official Citation:S. Narasimhaswamy, Z. Wei, Y. Wang, J. Zhang and M. H. Nguyen, "Contextual Attention for Hand Detection in the Wild," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 9566-9575. doi: 10.1109/ICCV.2019.00966
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:101740
Deposited By: Tony Diaz
Deposited On:06 Mar 2020 20:51
Last Modified:16 Nov 2021 18:05

Repository Staff Only: item control page