Search Results for author:
Found 11 papers, 6 papers with code
Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label
This paper investigates a framework for weakly-supervised object localization, which aims to train a neural network capable of predicting both the object class and its location using only images and their image-level class labels.
Enhancing Long-Term Person Re-Identification Using Global, Local Body Part, and Head Streams
The proposed framework consists of three streams: global, local body part, and head streams.
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization
To the best of our knowledge, we are the first to address this task.
Sampling Agnostic Feature Representation for Long-Term Person Re-identification
Although remarkable progress has been made in the re-identification problem, it is still a challenging problem due to appearance variations of the same person as well as other people of similar appearance.
Ranked #5 on
Person Re-Identification
on LTCC
Modeling, Quantifying, and Predicting Subjectivity of Image Aesthetics
We use the probability of being uncertain to define an intuitive metric of subjectivity.
Dense Depth Estimation from Multiple 360-degree Images Using Virtual Depth
In this paper, we propose a dense depth estimation pipeline for multiview 360{\deg} images.
Image-to-Image Translation-based Data Augmentation for Robust EV Charging Inlet Detection
Towards robust EV charging inlet detection, we propose a new dataset (EVCI dataset) and a novel data augmentation method that is based on image-to-image translation where typical image-to-image translation methods synthesize a new image in a different domain given an image.
Lossless White Balance For Improved Lossless CFA Image and Video Compression
We propose to use this white balance as a pre-processing step to lossless CFA subsampled image/video compression, improving the overall coding efficiency of the raw sensor data.
Automatic Prostate Zonal Segmentation Using Fully Convolutional Network with Feature Pyramid Attention
Expert 1) were 0. 71 (PZ) and 0. 75 (TZ).
Depth Adaptive Deep Neural Network for Semantic Segmentation
To overcome this challenge, we develop a neural network which is able to adapt the receptive field not only for each layer but also for each neuron at the spatial location.
Efficient Hand Articulations Tracking using Adaptive Hand Model and Depth map
In our system, we track hand articulations by minimizing discrepancy between depth map from sensor and computer-generated hand model.
