74 citations · 235 across the 19 of their papers we have counts for
21 papers
Learning from Multimodal Pseudo-Labels for Robust Open-Vocabulary Instance and Panoptic Segmentation
Duy Tran Thanh, Yeejin Lee, Byeongkeun Kang
This work addresses the challenge of open-vocabulary instance segmentation (OVIS) and open-set panoptic segmentation (OSPS), which aim to recognize both predefined and unseen objec…
Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic Calibration
Hyeonseok Kim, Byeongkeun Kang, Yeejin Lee
Generalized zero-shot semantic segmentation of 3D point clouds aims to classify each point into both seen and unseen classes. A significant challenge with these models is their ten…
Unsupervised Contrastive Learning Using Out-Of-Distribution Data for Long-Tailed Dataset
Cuong Manh Hoang, Yeejin Lee, Byeongkeun Kang
This work addresses the task of self-supervised learning (SSL) on a long-tailed dataset that aims to learn balanced and well-separated representations for downstream tasks such as…
Generalized Class Discovery in Instance Segmentation
Cuong Manh Hoang, Yeejin Lee, Byeongkeun Kang
This work addresses the task of generalized class discovery (GCD) in instance segmentation. The goal is to discover novel classes and obtain a model capable of segmenting instances…
Content-Aware Preserving Image Generation
Giang H. Le, Anh Q. Nguyen, Byeongkeun Kang +1
Remarkable progress has been achieved in image generation with the introduction of generative models. However, precisely controlling the content in generated images remains a chall…
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation
Duc Dang Trung Tran, Byeongkeun Kang, Yeejin Lee
Recently, transformer-based techniques incorporating superpoints have become prevalent in 3D instance segmentation. However, they often encounter an over-segmentation problem, espe…
Enhancing Long-Term Person Re-Identification Using Global, Local Body Part, and Head Streams
Duy Tran Thanh, Yeejin Lee, Byeongkeun Kang
This work addresses the task of long-term person re-identification. Typically, person re-identification assumes that people do not change their clothes, which limits its applicatio…
Pixel-Level Clustering Network for Unsupervised Image Segmentation
Cuong Manh Hoang, Byeongkeun Kang
While image segmentation is crucial in various computer vision applications, such as autonomous driving, grasping, and robot navigation, annotating all objects at the pixel-level f…
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization
Sejin Park, Taehyung Lee, Yeejin Lee +1
This work addresses the task of class-incremental weakly supervised object localization (CI-WSOL). The goal is to incrementally learn object localization for novel classes using on…
Sampling Agnostic Feature Representation for Long-Term Person Re-identification
Seongyeop Yang, Byeongkeun Kang, Yeejin Lee
Person re-identification is a problem of identifying individuals across non-overlapping cameras. Although remarkable progress has been made in the re-identification problem, it is…
The set of partial isometries as a quotient Finsler space
Esteban Andruchow
A known general program, designed to endow the quotient space of the unitary groups , of the C al…
Incremental Class Discovery for Semantic Segmentation with RGBD Sensing
Yoshikatsu Nakajima, Byeongkeun Kang, Hideo Saito +1
This work addresses the task of open world semantic segmentation using RGBD sensing to discover new semantic classes over time. Although there are many types of objects in the real…
Toward Joint Image Generation and Compression using Generative Adversarial Networks
Byeongkeun Kang, Subarna Tripathi, Truong Q. Nguyen
In this paper, we present a generative adversarial network framework that generates compressed images instead of synthesizing raw RGB images and compressing them separately. In the…
Random Forest with Learned Representations for Semantic Segmentation
Byeongkeun Kang, Truong Q. Nguyen
In this work, we present a random forest framework that learns the weights, shapes, and sparsities of feature representations for real-time semantic segmentation. Typical filters (…
Accurate and efficient video de-fencing using convolutional neural networks and temporal information
Chen Du, Byeongkeun Kang, Zheng Xu +2
De-fencing is to eliminate the captured fence on an image or a video, providing a clear view of the scene. It has been applied for many purposes including assisting photographers a…
Depth Adaptive Deep Neural Network for Semantic Segmentation
Byeongkeun Kang, Yeejin Lee, Truong Q. Nguyen
In this work, we present the depth-adaptive deep neural network using a depth map for semantic segmentation. Typical deep neural networks receive inputs at the predetermined locati…
LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems
Subarna Tripathi, Gokce Dane, Byeongkeun Kang +2
Deep convolutional Neural Networks (CNN) are the state-of-the-art performers for object detection task. It is well known that object detection requires more computation and memory…
Hand Segmentation for Hand-Object Interaction from Depth map
Byeongkeun Kang, Kar-Han Tan, Nan Jiang +3
Hand segmentation for hand-object interaction is a necessary preprocessing step in many applications such as augmented reality, medical application, and human-robot interaction. Ho…
Efficient Hand Articulations Tracking using Adaptive Hand Model and Depth map
Byeongkeun Kang, Yeejin Lee, Truong Q. Nguyen
Real-time hand articulations tracking is important for many applications such as interacting with virtual / augmented reality devices or tablets. However, most of existing algorith…
Real-time Sign Language Fingerspelling Recognition using Convolutional Neural Networks from Depth map
Byeongkeun Kang, Subarna Tripathi, Truong Q. Nguyen
Sign language recognition is important for natural and convenient communication between deaf community and hearing majority. We take the highly efficient initial step of automatic…
Long-Range Motion Trajectories Extraction of Articulated Human Using Mesh Evolution
Yuanyuan Wu, Xiaohai He, Byeongkeun Kang +2
This letter presents a novel approach to extract reliable dense and long-range motion trajectories of articulated human in a video sequence. Compared with existing approaches that…