Filters








21 Hits in 2.1 sec

YOLSE: Egocentric Fingertip Detection from Single RGB Images

Wenbin Wu, Chenyang Li, Zhuo Cheng, Xin Zhang, Lianwen Jin
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
In this paper, we build a new dataset named EgoGesture and propose a heatmap-based solution for fingertip detection.  ...  With the development of wearable device and augmented reality (AR), the human device interaction in egocentric vi sion, especially the hand gesture based interaction, has attracted lots of attention among  ...  We believe our dataset is diverse and representative as a benchmark dataset for the fingertip and hand related research in the egocentric vision.  ... 
doi:10.1109/iccvw.2017.79 dblp:conf/iccvw/WuLCZJ17 fatcat:cf3ovn5nfff7ndfka755qxj75u

Real-time Egocentric Gesture Recognition on Mobile Head Mounted Displays [article]

Rohit Pandey, Marie White, Pavel Pidlypenskyi, Xue Wang, Christine Kaeser-Chen
2017 arXiv   pre-print
Our main contributions are: 1) A novel mixed-reality data collection tool to automatic annotate bounding boxes and gesture labels; 2) The largest-to-date egocentric hand gesture and bounding box dataset  ...  In this work, we demonstrate real-time egocentric hand gesture detection and localization on mobile HMDs.  ...  There is limited dataset available on egocentric hand gestures and bounding boxes. 2.  ... 
arXiv:1712.04961v1 fatcat:ib6zldqqgjdofh6izbxmkx2f2i

Simultaneous Segmentation and Recognition: Towards More Accurate Ego Gesture Recognition

Tejo Chalasani, Aljosa Smolic
2019 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)  
art on the EgoGesture dataset [31].  ...  While the context of an image is important for tasks like scene understanding, object recognition, image caption generation and activity recognition, it plays a minimal role in ego hand gesture recognition  ...  It also captures both RGB and depth modalities. These properties of the EgoGesture dataset makes it a valid candidate for testing and benchmarking ego gesture recognition algorithms.  ... 
doi:10.1109/iccvw.2019.00537 dblp:conf/iccvw/ChalasaniS19 fatcat:ovgczj4zzfclphjzuu4invmpry

Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks [article]

Okan Köpüklü, Ahmet Gunduz, Neslihan Kose, Gerhard Rigoll
2019 arXiv   pre-print
We evaluate our architecture on two publicly available datasets - EgoGesture and NVIDIA Dynamic Hand Gesture Datasets - which require temporal detection and classification of the performed hand gestures  ...  Real-time recognition of dynamic hand gestures from video streams is a challenging task since (i) there is no indication when a gesture starts and ends in the video, (ii) performed gestures should only  ...  ACKNOWLEDGEMENTS We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.  ... 
arXiv:1901.10323v3 fatcat:dndlkm2mczbijfrgrwpskrixqi

Editorial IEEE Transactions on Multimedia Special Section on Video Analytics: Challenges, Algorithms, and Applications

B. Prabhakaran, Y.-G Jiang, H. Kalva, S.-F. Chang
2018 IEEE transactions on multimedia  
After 2 rounds of rigorous review, we have 3 high quality research papers as part of this special section: r Another work on "EgoGesture: A New Dataset and Benchmark for Egocentric Hand Gesture Recognition  ...  " presents a dataset with more than 24,000 gesture samples and 3,000,000 frames for both color and depth modalities from 50 distinct subjects giving 80+ different gestures in 6 diverse indoor and outdoor  ... 
doi:10.1109/tmm.2018.2821959 fatcat:54figgi6tfgjvizszssj7i7oqq

Multi-Task and Multi-Modal Learning for RGB Dynamic Gesture Recognition

Dinghao Fan, Hengjie Lu, Shugong Xu, Shan Cao
2021 IEEE Sensors Journal  
Our framework is trained to learn a representation for multi-task learning: gesture segmentation and gesture recognition.  ...  Experimental results on three public gesture recognition datasets show that our proposed method provides superior performance compared with existing gesture recognition frameworks.  ...  (a) is the EgoGesture dataset, including indoor and outdoor environments for egocentric hand gesture recognition.  ... 
doi:10.1109/jsen.2021.3123443 fatcat:4biyoph3xbe6dksji53pzpcc6i

Simultaneous Segmentation and Recognition: Towards more accurate Ego Gesture Recognition [article]

Tejo Chalasani, Aljosa Smolic
2019 arXiv   pre-print
art on the EgoGesture dataset  ...  While the context of an image is important for tasks like scene understanding, object recognition, image caption generation and activity recognition, it plays a minimal role in ego hand gesture recognition  ...  It also captures both RGB and depth modalities. These properties of the EgoGesture dataset makes it a valid candidate for testing and benchmarking ego gesture recognition algorithms.  ... 
arXiv:1909.08606v1 fatcat:h3jctvaxlrbjda2rtb6homtily

Enhanced Self-Perception in Mixed Reality: Egocentric Arm Segmentation and Database with Automatic Labelling [article]

Ester Gonzalez-Sosa, Pablo Perez, Ruben Tolosana, Redouane Kachach, Alvaro Villegas
2020 arXiv   pre-print
of this database, we report results on different real egocentric hand datasets, including GTEA Gaze+, EDSH, EgoHands, Ego Youtube Hands, THU-Read, TEgO, FPAB, and Ego Gesture, which allow for direct comparisons  ...  The main contributions of this work are: i) a comprehensive survey of segmentation algorithms for AV; ii) an Egocentric Arm Segmentation Dataset, composed of more than 10, 000 images, comprising variations  ...  For instance, The EPIC-KITCHENS Dataset is not providing segmentation masks [16] ; the Egocentric Gesture Recognition dataset [10] only provide segmentation masks for chroma-key hand gesture images;  ... 
arXiv:2003.12352v1 fatcat:gfnhmhhijjhn7d66fzmsdimj7u

Content-Adaptive and Attention-Based Network for Hand Gesture Recognition

Zongjing Cao, Yan Li, Byeong-Seok Shin
2022 Applied Sciences  
The proposed network achieved 83.2% and 93.8% recognition accuracy on two publicly available benchmark datasets, NVGesture and EgoGesture datasets, respectively.  ...  For hand gesture recognition, recurrent neural networks and 3D convolutional neural networks are the most commonly used methods for learning the spatial–temporal features of gestures.  ...  The EgoGesture dataset is a large-scale dataset for egocentric hand gesture recognition, consisting of 83 classes collected from four indoor and two outdoor scenes.  ... 
doi:10.3390/app12042041 fatcat:whjvcjomtnc55ofubqg6ioessy

IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition [article]

Gibran Benitez-Garcia, Jesus Olivares-Mercado, Gabriel Sanchez-Perez, Keiji Yanai
2020 arXiv   pre-print
In this paper, we introduce a new benchmark dataset named IPN Hand with sufficient size, variety, and real-world elements able to train and evaluate deep neural networks.  ...  The experimental results show that the state-of-the-art ResNext-101 model decreases about 30% accuracy when using our real-world dataset, demonstrating that the IPN Hand dataset can be used as a benchmark  ...  ACKNOWLEDGMENT This work was supported by JSPS KAKENHI Grant Number 15H05915, 17H01745, 17H06100 and 19H04929.  ... 
arXiv:2005.02134v2 fatcat:qclawbhdxrd33nucnktpdrkwy4

Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition [article]

Zitong Yu, Benjia Zhou, Jun Wan, Pichao Wang, Haoyu Chen, Xin Liu, Stan Z. Li, Guoying Zhao
2020 arXiv   pre-print
Comprehensive experiments are performed on three benchmark datasets (IsoGD, NvGesture, and EgoGesture), demonstrating the state-of-the-art performance in both single- and multi-modality settings.The code  ...  gesture recognition.  ...  For fair evaluations with SOTA methods, infrared modality is not used in our experiments. The EgoGesture dataset [4] is a large multi-modal egocentric hand gesture dataset.  ... 
arXiv:2008.09412v1 fatcat:vphe2saxbjhxtee2twdkbby3yi

Real Time Egocentric Object Segmentation: THU-READ Labeling and Benchmarking Results [article]

E. Gonzalez-Sosa, G. Robledo, D. Gonzalez-Morin, P. Perez-Garcia, A. Villegas
2021 arXiv   pre-print
Due to the lack of datasets of pixel-wise annotations of egocentric objects, in this paper we contribute with a semantic-wise labeling of a subset of 2124 images from the RGB-D THU-READ Dataset.  ...  While most previous works have been focused on segmenting egocentric human body parts (mainly hands), little attention has been given to egocentric objects.  ...  To the best of our knowledge, there exist only three published egocentric and RGB-D datasets including human body parts (and) objects: Ego Gesture [11] , created for the task of hand gesture recognition  ... 
arXiv:2106.04957v1 fatcat:snjrhnz6zbdzre5bo2tu3yw3gu

Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition With Multimodal Training

Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition.  ...  Experimental results show that our framework improves the test time recognition accuracy of unimodal networks, and provides the state-of-the-art performance on various dynamic hand gesture recognition  ...  , 51] is a large multimodal hand gesture dataset collected for the task of egocentric gesture recognition.  ... 
doi:10.1109/cvpr.2019.00126 dblp:conf/cvpr/AbavisaniJP19 fatcat:wmodjfndpzcaxb32ntq7xyxk44

Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training [article]

Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel
2019 arXiv   pre-print
We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition.  ...  Experimental results show that our framework improves the test time recognition accuracy of unimodal networks, and provides the state-of-the-art performance on various dynamic hand gesture recognition  ...  The incorporation of our method for multimodal learning in other applications is a topic of further research.  ... 
arXiv:1812.06145v2 fatcat:zxvwvfb34zfs7d47qbtldb3sri

Predicting the Future from First Person (Egocentric) Vision: A Survey [article]

Ivan Rodin, Antonino Furnari, Dimitrios Mavroedis, Giovanni Maria Farinella
2021 arXiv   pre-print
The research in egocentric video analysis is developing rapidly thanks to the increasing availability of wearable devices and the opportunities offered by new large-scale egocentric datasets.  ...  Egocentric videos can bring a lot of information about how humans perceive the world and interact with the environment, which can be beneficial for the analysis of human behaviour.  ...  The dataset also provides hand masks and gaze annotations. EgoGesture [96] : A dataset designed for gesture recognition, consisting of 24.161 videos of 50 subjects performing 83 different gestures.  ... 
arXiv:2107.13411v1 fatcat:viullzimvzc33espfjurvdisia
« Previous Showing results 1 — 15 out of 21 results