Výsledky vyhľadávania - "Pattern Recognition and Graphics"

FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention Autor Xiao, Guangxuan, Yin, Tianwei, Freeman, William T., Durand, Frédo, Han, Song

“…Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images…”
Získať plný text

Realistic Speech-Driven Facial Animation with GANs Autor Vougioukas, Konstantinos, Petridis, Stavros, Pantic, Maja

“… This approach often requires post-processing using computer graphics techniques to produce realistic albeit subject dependent results…”
Získať plný text

Large Scale 3D Morphable Models Autor Booth, James, Roussos, Anastasios, Ponniah, Allan, Dunaway, David, Zafeiriou, Stefanos

“… The dataset that LSFM is trained on includes rich demographic information about each subject, allowing for the construction of not only a global 3DMM model but also models tailored for specific age…”
Získať plný text

Structure-Measure: A New Way to Evaluate Foreground Maps Autor Cheng, Ming-Ming, Fan, Deng-Ping

“…Foreground map evaluation is crucial for gauging the progress of object segmentation algorithms, in particular in the field of salient object detection where…”
Získať plný text

Statistical Modeling of Craniofacial Shape and Texture Autor Dai, Hang, Pears, Nick, Smith, William, Duncan, Christian

“…) of the full human head. Our approach is the first to employ a template that adapts to the dataset subject before dense morphing…”
Získať plný text

DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation Using Limited Data: DomainStudio: Fine-tuning Diffusion Models for Domain-driven Autor Zhu, Jingyuan, Ma, Huimin, Chen, Jiansheng, Yuan, Jian

“… Unfortunately, they are still vulnerable to overfitting when fine-tuned on limited data. Existing works have explored subject-driven generation with text-to-image (T2I…”
Získať plný text

Receding horizon path planning for 3D exploration and surface inspection Autor Bircher, Andreas, Kamel, Mina, Alexis, Kostas, Oleynikova, Helen, Siegwart, Roland

“… Application to rotorcraft Micro Aerial Vehicles is presented, although planning for other types of robotic platforms is possible, even in the absence of a boundary value solver and subject to nonholonomic constraints…”
Získať plný text

Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition Autor Takemura, Noriko, Makihara, Yasushi, Muramatsu, Daigo, Echigo, Tomio, Yagi, Yasushi

“… Specifically, we construct a gait dataset that includes 10,307 subjects (5114 males and 5193 females…”
Získať plný text

Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks Autor Zhang, He, Riggan, Benjamin S., Hu, Shuowen, Short, Nathaniel J., Patel, Vishal M.

“…The large domain discrepancy between faces captured in polarimetric (or conventional) thermal and visible domains makes cross-domain face verification a highly…”
Získať plný text

Unsupervised Multi-View CNN for Salient View Selection and 3D Interest Point Detection Autor Song, Ran, Zhang, Wei, Zhao, Yitian, Liu, Yonghuai

“…We present an unsupervised 3D deep learning framework based on a ubiquitously true proposition named by us view-object consistency as it states that a 3D…”
Získať plný text

Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition Autor Liu, Jian, Rahmani, Hossein, Akhtar, Naveed, Mian, Ajmal

“…We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes…”
Získať plný text

Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification Autor Yang, Meng, Zhang, Lei, Feng, Xiangchu, Zhang, David

“… A structured dictionary, whose atoms have correspondences to the subject class labels, is learned, with which not only the representation residual can be used to distinguish…”
Získať plný text

A survey on Bayesian network structure learning from data Autor Scanagatta, Mauro, Salmerón, Antonio, Stella, Fabio

“… A crucial aspect is learning the dependency graph of a Bayesian network from data. This task, called structure learning , is NP-hard and is the subject of intense, cutting-edge research…”
Získať plný text

HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion Autor Sigal, Leonid, Balan, Alexandru O., Black, Michael J.

“… The resulting HumanEva datasets contain multiple subjects performing a set of predefined actions with a number of repetitions…”
Získať plný text

Multi-modal RGB–Depth–Thermal Human Body Segmentation Autor Palmero, Cristina, Clapés, Albert, Bahnsen, Chris, Møgelmose, Andreas, Moeslund, Thomas B., Escalera, Sergio

“…This work addresses the problem of human body segmentation from multi-modal visual cues as a first stage of automatic human behavior analysis. We propose a…”
Získať plný text

Predicting Intentions from Motion: The Subject-Adversarial Adaptation Approach Autor Zunino, Andrea, Cavazza, Jacopo, Volpi, Riccardo, Morerio, Pietro, Cavallo, Andrea, Becchio, Cristina, Murino, Vittorio

“…This paper aims at investigating the action prediction problem from a pure kinematic perspective. Specifically, we address the problem of recognizing future…”
Získať plný text

View-Invariant Skeleton Action Representation Learning via Motion Retargeting Autor Yang, Di, Wang, Yaohui, Dantcheva, Antitza, Garattoni, Lorenzo, Francesca, Gianpiero, Brémond, François

“… When dealing with estimated skeleton data in real-world videos , such methods perform poorly due to the large variations across subjects and camera viewpoint…”
Získať plný text

3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation Autor Moschoglou, Stylianos, Ploumpis, Stylianos, Nicolaou, Mihalis A., Papaioannou, Athanasios, Zafeiriou, Stefanos

“…, few subjects, little diversity in race and gender), and (b) mesh convolutions for deep networks present several challenges that are not entirely tackled…”
Získať plný text

Crots: Cross-Domain Teacher–Student Learning for Source-Free Domain Adaptive Semantic Segmentation Autor Luo, Xin, Chen, Wei, Liang, Zhengfa, Yang, Longqi, Wang, Siwei, Li, Chen

“… However, these methods are subject to strict limitations: (1) The discrepancy between source and target domains results in intense noise and unreliable pseudo-labels…”
Získať plný text

AI-assisted mesh generation for subject-specific modeling of facial soft tissues: AI-Assisted Mesh Generation Autor Lampen, Nathan, Xu, Xuanang, Kim, Daeseung, Kuang, Tianshu, Lee, Jungwook, Deng, Hannah H., Gateno, Jaime, Yan, Pingkun

“… Conventional meshing methods rely on labor-intensive processes, including manual landmark digitization and mesh editing, and often lack point correspondence among subjects…”
Získať plný text