Search Results for author:
Found 16 papers, 4 papers with code
MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views
MonoSelfRecon is not restricted by specific model design, which can be used to any models with voxel-SDF for purely self-supervised manner.
AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement
Our experiments demonstrate AUEditNet's superior accuracy in editing AU intensities, affirming its capability in disentangling facial attributes and identity within a limited subject pool.
ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection
Then both the initial and edited embeddings are projected back (deprojected) to the initial latent space as residuals to modify the input latent vectors by subtraction and addition, representing old status removal and new status addition.
Localizing Scan Targets from Human Pose for Autonomous Lung Ultrasound Imaging
Ultrasound is progressing toward becoming an affordable and versatile solution to medical imaging.
A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification
In this paper, we present a robust and low complexity deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the scene of a remote sensing image.
SM3D: Simultaneous Monocular Mapping and 3D Detection
In 3D Detection module, the depth estimation is projected into 3D space to generate "Pseudo-LiDAR" point cloud, where LiDAR-based 3D detector can be leveraged on point cloud for vehicular 3D detection and localization.
MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular Images
Our real-scale scene flow estimation outperforms all state-of-the-art monocular-image based works recovered to real scale by ground truth, and is comparable to LiDAR approaches.
Deep Learning Framework Applied for Predicting Anomaly of Respiratory Sounds
This paper proposes a robust deep learning framework used for classifying anomaly of respiratory cycles.
An Adaptive EM Accelerator for Unsupervised Learning of Gaussian Mixture Models
We propose an Anderson Acceleration (AA) scheme for the adaptive Expectation-Maximization (EM) algorithm for unsupervised learning a finite mixture model from multivariate data (Figueiredo and Jain 2002).
Accurate and efficient video de-fencing using convolutional neural networks and temporal information
To overcome these problems, we propose a novel method consisting of segmentation using convolutional neural networks and a fast/robust recovery algorithm.
LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems
Thus the consolidation of a CNN-based object detection for an embedded system is more challenging.
Context Matters: Refining Object Detection in Video with Recurrent Neural Networks
Then we train a recurrent neural network that takes as input sequences of pseudo-labeled frames and optimizes an objective that encourages both accuracy on the target frame and consistency across consecutive frames.
Detecting Temporally Consistent Objects in Videos through Object Class Label Propagation
We further propose a clustering of VOPs which can efficiently be used for detecting objects in video in a streaming fashion.
Semantic Video Segmentation : Exploring Inference Efficiency
We explore the efficiency of the CRF inference beyond image level semantic segmentation and perform joint inference in video frames.
Beyond Semantic Image Segmentation : Exploring Efficient Inference in Video
We explore the efficiency of the CRF inference module beyond image level semantic segmentation.
Improving Streaming Video Segmentation with Early and Mid-Level Visual Processing
Despite recent advances in video segmentation, many opportunities remain to improve it using a variety of low and mid-level visual cues.
