HandSeg: A Dataset for Hand Segmentation from Depth Images
Explore this paper's citation graph
Summary
This work introduces a large-scale RGBD hand segmentation dataset, with detailed and automatically generated high-quality ground-truth annotations, and proposes a novel architecture employing strided convolution/deconvolutions in place of max-pooling and unpooling layers.
- Type
- article
- Published
- 2017-11-16
- Cited by
- 8
- References
- 50
- Access
- Open access
- OpenAlex
- https://openalex.org/W2768176507
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:36671376
Keywords
Computer science, Pipeline (software), Ground truth, Segmentation, Artificial intelligence
References
- Depth-Based Hand Pose Estimation: Methods, Data, and Challenges
- Dynamics based 3D skeletal hand tracking
- Hands Deep in Deep Learning for Hand Pose Estimation
- Learning Deconvolution Network for Semantic Segmentation
- Fully convolutional networks for semantic segmentation
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- Feedforward semantic segmentation with zoom-out features
- Fast and robust hand tracking using detection-guided optimization
- An adaptive skin model and its application to objectionable image filtering
- Tell Me What You See and I Will Show You Where It Is
- Spatial-based skin detection using discriminative skin-presence features
- Hand detection using multiple proposals
- Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data
- Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts
- Accurate, Robust, and Flexible Real-time Hand Tracking
- Structured class-labels in random forests for semantic image labelling
- Real-time human pose recognition in parts from single depth images
- Skin segmentation using color pixel classification: analysis and comparison
- Real-Time Continuous Pose Recovery of Human Hands Using Convolutional Networks
- Markerless Motion Capture of Multiple Characters Using Multiview Image Segmentation
Cited by
- Contributions to deep learning methodologies
- BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation
- Contextual Attention for Hand Detection in the Wild
- DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
- WorkingHands: A Hand-Tool Assembly Dataset for Image Segmentation and Activity Mining
- Semiparallel deep neural network hybrid architecture: first application on depth from monocular camera
- Optimized hand pose estimation CrossInfoNet-based architecture for embedded devices
- Forward Propagation, Backward Regression, and Pose Association for Hand Tracking in the Wild
Related papers
- HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images
- DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
- Deep Representation Learning for Domain Adaptation of Semantic Image Segmentation
- Ego2Hands: A Dataset for Egocentric Two-hand Segmentation and Detection
- Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence
- Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset
- Learning to segment from misaligned and partial labels