Search Results for author:
Found 20 papers, 4 papers with code
Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Training
The teacher network is trained using both the available labeled and unlabeled samples.
Ranked #3 on
Hand Pose Estimation
on MSRA Hands
TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation
The second innovation is PixDropout, which is, to the best of our knowledge, the first appearance-based data augmentation method for hand depth images.
Ranked #1 on
Hand Pose Estimation
on MSRA Hands
All You Need In Sign Language Production
To make an easy and mutual communication between the hearing-impaired and the hearing communities, building a robust system capable of translating the spoken language into sign language and vice versa is fundamental.
Cultural Vocal Bursts Intensity Prediction
Sign Language Production
+2
A Survey on Deep learning based Document Image Enhancement
Digitized documents such as scientific articles, tax forms, invoices, contract papers, historic texts are widely used nowadays.
Cross Your Body: A Cognitive Assessment System for Children
It is our goal that this system will be useful in advancing research in cognitive assessment of kids.
Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos
This paper focuses on task recognition and action segmentation in weakly-labeled instructional videos, where only the ordered sequence of video-level actions is available during training.
Gated Fusion Network for SAO Filter and Inter Frame Prediction in Versatile Video Coding
To achieve higher coding efficiency, Versatile Video Coding (VVC) includes several novel components, but at the expense of increasing decoder computational complexity.
Multi-scale Deep Learning Architecture for Nucleus Detection in Renal Cell Carcinoma Microscopy Image
Clear cell renal cell carcinoma (ccRCC) is one of the most common forms of intratumoral heterogeneity in the study of renal cancer.
Action Duration Prediction for Segment-Level Alignment of Weakly-Labeled Videos
This paper focuses on weakly-supervised action alignment, where only the ordered sequence of video-level actions is available for training.
Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization
We perform our experiment on six challenging and commonly used FGVC datasets, and we show competitive improvement on accuracies by using attention-aware data augmentation techniques with features derived from deep learning model InceptionV3, pre-trained on large scale datasets.
Ranked #1 on
Fine-Grained Image Classification
on FGVC Aircraft
(Top-1 metric)
Evaluating Single Image Dehazing Methods Under Realistic Sunlight Haze
Most existing methods assume that haze has a uniform/homogeneous distribution and haze can have a single color, i. e. grayish white color similar to smoke, while in reality haze can be distributed non-uniformly with different patterns and colors.
Dehaze-GLCGAN: Unpaired Single Image De-hazing via Adversarial Training
Most current solutions require paired image datasets that include both hazy images and their corresponding haze-free ground-truth images.
Generative Adversarial Network
Image-to-Image Translation
+1
A Realistic Dataset and Baseline Temporal Model for Early Drowsiness Detection
We present a large and public real-life dataset of 60 subjects, with video segments labeled as alert, low vigilant, or drowsy.
Direct Shape Regression Networks for End-to-End Face Alignment
In this paper, we propose the direct shape regression network (DSRN) for end-to-end face alignment by jointly handling the aforementioned challenges in a unified framework.
Ranked #16 on
Face Alignment
on AFLW-19
Towards Deep Learning based Hand Keypoints Detection for Rapid Sequential Movements from RGB Images
Hand keypoints detection and pose estimation has numerous applications in computer vision, but it is still an unsolved problem in many aspects.
Context-Aware Single-Shot Detector
SSD is one of the state-of-the-art object detection algorithms, and it combines high detection accuracy with real-time speed.
Improving the Accuracy of the CogniLearn System for Cognitive Behavior Assessment
As a result of these improvements, the accuracy in recognizing cases where subjects touch their toes has gone from 76. 46% in our previous work to 97. 19% in this paper.
Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN)
Selective Convolutional Neural Network (S-CNN) is a simple and fast algorithm, it introduces a new way to do unsupervised feature learning, and it provides discriminative features which generalize well.
Ranked #103 on
Image Classification
on STL-10
Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition
Human body pose estimation and hand detection are two important tasks for systems that perform computer vision-based sign language recognition(SLR).
Principal motion components for gesture recognition using a single-example
In the considered scenario a single training-video is available for each gesture to be recognized, which limits the application of traditional techniques (e. g., HMMs).
