2013 IEEE International Conference on Computer Vision 2013
DOI: 10.1109/iccv.2013.192
|View full text |Cite
|
Sign up to set email alerts
|

Fingerspelling Recognition with Semi-Markov Conditional Random Fields

Abstract: Recognition of gesture sequences is in general a very difficult problem, but in certain domains the difficulty may be mitigated by exploiting the domain's "grammar". One such grammatically constrained gesture sequence domain is sign language. In this paper we investigate the case of fingerspelling recognition, which can be very challenging due to the quick, small motions of the fingers. Most prior work on this task has assumed a closed vocabulary of fingerspelled words; here we study the more natural open-voca… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
34
1

Year Published

2017
2017
2023
2023

Publication Types

Select...
5
3
1

Relationship

3
6

Authors

Journals

citations
Cited by 27 publications
(35 citation statements)
references
References 34 publications
0
34
1
Order By: Relevance
“…Much previous work on sign language recognition, and the vast majority of previous work on fingerspelling recognition, uses some form of hand detection or segmentation to localize the region(s) of interest as an initial step. Kim et al [18,19,17] estimate a signerdependent skin color model using manually annotated hand regions for fingerspelling recognition. Huang et al [15] learn a hand detector based on Faster R-CNN [33] using manually annotated signing hand bounding boxes, and apply it to general sign language recognition.…”
Section: Related Workmentioning
confidence: 99%
“…Much previous work on sign language recognition, and the vast majority of previous work on fingerspelling recognition, uses some form of hand detection or segmentation to localize the region(s) of interest as an initial step. Kim et al [18,19,17] estimate a signerdependent skin color model using manually annotated hand regions for fingerspelling recognition. Huang et al [15] learn a hand detector based on Faster R-CNN [33] using manually annotated signing hand bounding boxes, and apply it to general sign language recognition.…”
Section: Related Workmentioning
confidence: 99%
“…Hand gesture recognition provides a means to decode the information expressed by the reported categories which are always more used to interact with innovative applications, such as interactive games [3], [4], serious games [5], [6], sign language recognition [7]- [10], emotional expression identification [11], [12], remote control in robotics [13], [14] or alternative computer interfaces [15]- [18]. In general, the approaches used in hand gesture recognition can be divided into two main classes: 3D model-based [19] and appearancebased [20].…”
Section: Introductionmentioning
confidence: 99%
“…As in a number of other domains, convolutional neural networks (CNNs) have recently been replacing engineered features in sign language recognition research [17,18,19,11,8]. For sequence modeling, most previous work has used hidden Markov models (HMMs) [20,17,18,13], and some has used segmental conditional random fields [21,22,13]. Much of this work relies on frame-level labels for the training data.…”
Section: Related Workmentioning
confidence: 99%
“…Most fingerspelling recognition approaches begin by extracting the signing hand from the image frames [21,13,11]. Due to the high quality of video used in prior work, hand detection (or segmentation) is usually treated as a preprocessing step with high accuracy, with little analysis of its impact on performance.…”
Section: Related Workmentioning
confidence: 99%