Hand detection using multiple proposals

By Arpit Mittal, Andrew Zisserman, Philip H. S. Torr. 2011

292 citations recorded by the source corpus.

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].”
Coherent Multi-sentence Video Description with Variable Level of Detail (2014, background): “Our detector also signiﬁcantly improves over the hand detector of [16] that in addition to hand appearance also relies on color and context features.”
From Lifestyle Vlogs to Everyday Interactions (2017, background): “As further evidence, on a third dataset [27], training on VLOG far surpasses using EgoHands (56.”
Understanding Human Hands in Contact at Internet Scale (2020, methodology): “Here we show our results on 100DOH as well as generalizing (untrained) to VIVA [1], EgoHands [5], and VGG [25].”
Analysis of Hand Segmentation in the Wild (2018, methodology): “[21] used deformable part models and skin heuristics to detect hands.”
Robot Learning Manipulation Action Plans by "Watching" Unconstrained Videos from the World Wide Web (2015, methodology): “For localizing hands on the testing data, we first applied the hand detector from (Mittal, Zisserman, and Torr 2011) and picked the top two hand patch proposals (left hand and right hand, if present).”
WorkingHands: A Hand-Tool Assembly Dataset for Image Segmentation and Activity Mining (2019, methodology): “Hand image analysis datasets [2, 16, 21, 22, 38] were proposed for segmentation of hands, but many do not involve hand-object interactions or other body parts.”
Detecting Hands and Recognizing Physical Contact in the Wild (2020, methodology): “e images form our still images group. To complement the still photos, we also collect frames sampled from videos. For this purpose, we use the training and validation split of the Oxford Hand dataset [19] and TV-Hand [21] dataset. Altogether, our dataset has 21,637 images. 6 Annotation and Quality C”
Pixel-Level Hand Detection with Shape-Aware Structured Forests (2014, methodology): “All images are collected from various sources as cataloged in [10], of different resolution and imaging condition.”
Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions (2015, methodology): “[24] developed a system that uses deformable part models and skin heuristics to detect hands in the PASCAL VOC Person Layout challenge [10].”
Touch-less interactive augmented reality game on vision-based wearable device (2015, methodology): “The touch-less interaction algorithm uses dynamic programming-based CTM algo-rithm [59] to localize the finger/shoe-contour for hand/foot, complemented optimally by lightweight skin detection [52], and employs TLD [27] framework to strengthen the tracking process in every frame.”
Contextual Attention for Hand Detection in the Wild (2019, methodology): “Mittal et al. [24] proposed to combine shape, skin, and context cues to build a multi-stage detector.”