Search Results - "Yamazaki, Kashu"

Deep reinforcement learning in computer vision: a comprehensive survey by Le, Ngan, Rathour, Vidhiwar Singh, Yamazaki, Kashu, Luu, Khoa, Savvides, Marios

“…Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have…”
Get full text

Spiking Neural Networks and Their Applications: A Review by Yamazaki, Kashu, Vo-Ho, Viet-Khoa, Bulsara, Darshan, Le, Ngan

“…The past decade has witnessed the great success of deep neural networks in various domains. However, deep neural networks are very resource-intensive in terms…”
Get full text

AerialFormer: Multi-Resolution Transformer for Aerial Image Segmentation by Hanyu, Taisei, Yamazaki, Kashu, Tran, Minh, McCann, Roy A., Liao, Haitao, Rainwater, Chase, Adkins, Meredith, Cothren, Jackson, Le, Ngan

“…When performing remote sensing image segmentation, practitioners often encounter various challenges, such as a strong imbalance in the foreground–background,…”
Get full text

Narrow Band Active Contour Attention Model for Medical Segmentation by Le, Ngan, Bui, Toan, Vo-Ho, Viet-Khoa, Yamazaki, Kashu, Luu, Khoa

“…Medical image segmentation is one of the most challenging tasks in medical image analysis and widely developed for many clinical applications. While deep…”
Get full text

ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation by Vo, Khoa, Yamazaki, Kashu, Truong, Sang, Tran, Minh-Triet, Sugimoto, Akihiro, Le, Ngan

“…Temporal action proposal generation (TAPG) aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet plays an important…”
Get full text

Development of a Soft Robot Based Photodynamic Therapy for Pancreatic Cancer by Li, Yucheng, Liu, Yang, Yamazaki, Kashu, Bai, Mingfeng, Chen, Yue

“…Photodynamic therapy (PDT) has received increased attention over the past decades with the potential to noninvasively treat cancer via light exposure. Due to…”
Get full text

Towards Multi-Modal Explainable Video Understanding by Yamazaki, Kashu

“…This thesis presents a novel approach to video understanding by emulating human perceptual processes and creating an explainable and coherent storytelling…”
Get full text

AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation by Vo, Khoa, Truong, Sang, Yamazaki, Kashu, Raj, Bhiksha, Tran, Minh-Triet, Le, Ngan

“…Temporal action proposal generation (TAPG) is a challenging task, which requires localizing action intervals in an untrimmed video. Intuitively, we as humans,…”
Get full text

CLIP-TSA: Clip-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection by Joo, Hyekang Kevin, Vo, Khoa, Yamazaki, Kashu, Le, Ngan

“…Video anomaly detection (VAD) - commonly formulated as a multiple-instance learning problem in a weakly-supervised manner due to its labor-intensive nature -…”
Get full text

VLCAP: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning by Yamazaki, Kashu, Truong, Sang, Vo, Khoa, Kidd, Michael, Rainwater, Chase, Luu, Khoa, Le, Ngan

“…In this paper, we leverage the human perceiving process, that involves vision and language interaction, to generate a coherent paragraph description of…”
Get full text

A Multi-task Contextual Atrous Residual Network for Brain Tumor Detection & Segmentation by Le, Ngan, Yamazaki, Kashu, Quach, Kha Gia, Truong, Dat, Savvides, Marios

“…In recent years, deep neural networks have achieved state-of-the-art performance in a variety of recognition and segmentation tasks in medical imaging…”
Get full text

Contextual Explainable Video Representation: Human Perception-based Understanding by Vo, Khoa, Yamazaki, Kashu, Nguyen, Phong X., Nguyen, Phat, Luu, Khoa, Le, Ngan

“…Video understanding is a growing field and a subject of intense research, which includes many interesting tasks to understanding both spatial and temporal…”
Get full text

Offset Curves Loss for Imbalanced Problem in Medical Segmentation by Le, Ngan, Le, Trung, Yamazaki, Kashu, Bui, Toan, Luu, Khoa, Savides, Marios

“…Medical image segmentation has played an important role in medical analysis and widely developed for many clinical applications. Deep learning-based approaches…”
Get full text

HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model by Vo, Khoa, Phan, Thinh, Yamazaki, Kashu, Tran, Minh, Le, Ngan

“…Current video-language models (VLMs) rely extensively on instance-level alignment between video and language modalities, which presents two major limitations:…”
Get full text

CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection by Joo, Hyekang Kevin, Vo, Khoa, Yamazaki, Kashu, Le, Ngan

“…Video anomaly detection (VAD) -- commonly formulated as a multiple-instance learning problem in a weakly-supervised manner due to its labor-intensive nature --…”
Get full text

VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning by Yamazaki, Kashu, Vo, Khoa, Truong, Sang, Raj, Bhiksha, Le, Ngan

“…Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling…”
Get full text

Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation by Yamazaki, Kashu, Hanyu, Taisei, Vo, Khoa, Pham, Thang, Tran, Minh, Doretto, Gianfranco, Nguyen, Anh, Le, Ngan

“…Precise 3D environmental mapping with semantics is essential in robotics. Existing methods often rely on pre-defined concepts during training or are…”
Get full text

DNA: Deformable Neural Articulations Network for Template-free Dynamic 3D Human Reconstruction from Monocular RGB-D Video by Vo, Khoa, Pham, Trong-Thang, Yamazaki, Kashu, Tran, Minh, Le, Ngan

“…In this paper, we present a novel Deformable Neural Articulations Network (DNA-Net), which is a template-free learning-based method for dynamic 3D human…”
Get full text

Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation by Yamazaki, Kashu, Hanyu, Taisei, Vo, Khoa, Pham, Thang, Tran, Minh, Doretto, Gianfranco, Nguyen, Anh, Le, Ngan

“…Precise 3D environmental mapping is pivotal in robotics. Existing methods often rely on predefined concepts during training or are time-intensive when…”
Get full text

Contextual Explainable Video Representation: Human Perception-based Understanding by Vo, Khoa, Yamazaki, Kashu, Nguyen, Phong X, Nguyen, Phat, Luu, Khoa, Le, Ngan

“…Video understanding is a growing field and a subject of intense research, which includes many interesting tasks to understanding both spatial and temporal…”
Get full text