Contextual Attention for Hand Detection in the Wild

By Supreeth Narasimhaswamy, Zheng Wei, Yang Wang, Justin Zhang, Minh Hoai. 2019

65 citations recorded by the source corpus.

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: https://www3.cs.stonybrook.edu/~cvl/projects/hand_det_attention/

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations (2022, background): “Multiple past datasets have provided similar data for hands [1, 3, 27, 29] as well as hands in contact with objects [28, 34, 35].”
Understanding Human Hands in Contact at Internet Scale (2020, methodology): “In this area, our data and approach sit between image-based hand detection datasets like [1, 25, 5, 14, 28] and efforts at understanding contact with richer annotation but requiring more specialized devices or more constrained environments such as [7, 35, 30, 15, 36].”
WorkingHands: A Hand-Tool Assembly Dataset for Image Segmentation and Activity Mining (2019, unknown): “Garcia et al. [12] 0 105K N 26 TV-Hand [25] 9.5K N Man.”
Detecting Hands and Recognizing Physical Contact in the Wild (2020, methodology): “For this purpose, we use the training and validation split of the Oxford Hand dataset [19] and TV-Hand [21] dataset.”
First-Person View Hand Segmentation of Multi-Modal Hand Activity Video Dataset (2020, methodology): “Researchers create hand segmentation datasets by manually drawing polygon or coloring the hand on RGB frames [33, 38, 48, 48, 50].”