research
∙
12/07/2022
AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation
The weakly supervised instance segmentation is a challenging task. The e...
share
research
∙
06/10/2022
R4D: Utilizing Reference Objects for Long-Range Distance Estimation
Estimating the distance of objects is a safety-critical task for autonom...
research
∙
06/08/2022
Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking
Monocular image-based 3D perception has become an active research area i...
research
∙
11/25/2021
Learning from Temporal Gradient for Semi-supervised Action Recognition
Semi-supervised video action recognition tends to enable deep neural net...
research
∙
08/08/2020
Cross-modal Center Loss
Cross-modal retrieval aims to learn discriminative and modal-invariant f...
research
∙
05/28/2020
Self-supervised Modal and View Invariant Feature Learning
Most of the existing self-supervised feature learning methods for 3D dat...
research
∙
05/01/2020
Recognizing American Sign Language Nonmanual Signal Grammar Errors in Continuous Videos
As part of the development of an educational tool that can help students...
research
∙
04/13/2020
Self-supervised Feature Learning by Cross-modality and Cross-view Correspondences
The success of supervised learning requires large-scale ground truth lab...
research
∙
02/29/2020
VideoSSL: Semi-Supervised Learning for Video Classification
We propose a semi-supervised learning approach for video classification,...
research
∙
06/07/2019
Recognizing American Sign Language Manual Signs from RGB-D Videos
In this paper, we propose a 3D Convolutional Neural Network (3DCNN) base...
research
∙
02/16/2019
Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
Large-scale labeled data are generally required to train deep neural net...
research
∙
01/11/2019
LGAN: Lung Segmentation in CT Scans Using Generative Adversarial Network
Lung segmentation in computerized tomography (CT) images is an important...
research
∙
12/28/2018
Coarse-to-fine Semantic Segmentation from Image-level Labels
Deep neural network-based semantic segmentation generally requires large...
research
∙
11/28/2018