Filters








13,853 Hits in 8.7 sec

The whole is more than its parts? From explicit to implicit pose normalization

Marcel Simon, Erik Rodner, Trevor Darrell, Joachim Denzler
2019 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Furthermore, we show that our approaches for fine-grained recognition are beneficial for other fields like action recognition.  ...  Fine-grained classification describes the automated recognition of visually similar object categories like birds species.  ...  ACKNOWLEDGMENTS Part of this research was supported by grant RO 5093/1-1 of the German Research Foundation (DFG). The authors thank Nvidia for GPU donations.  ... 
doi:10.1109/tpami.2018.2885764 pmid:30575529 fatcat:xndr4xtvd5dzdnpzade2hq6xty

Do not Lose the Details: Reinforced Representation Learning for High Performance Visual Tracking

Qiang Wang, Mengdan Zhang, Junliang Xing, Jin Gao, Weiming Hu, Steve Maybank
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Moreover, the correlation filter layer working on the fine-grained representations leverages a global context constraint for accurate object appearance modeling.  ...  Therefore, the proposed tracker benefits from two complementary effects: the adaptability of the fine-grained correlation analysis and the generalization capability of the semantic embedding.  ...  Acknowledgements Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2018/137 dblp:conf/ijcai/WangZXGHM18 fatcat:vuixvii3hfdw5pp5snso2kxaom

DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis [article]

Yueming Lyu, Peibin Chen, Jingna Sun, Xu Wang, Jing Dong, Tieniu Tan
2021 arXiv   pre-print
Although recent works have achieved realistic results, most of them fail to handle fine-grained styles with subtle details.  ...  To address this problem, a novel normalization module, named DRAN, is proposed. It learns fine-grained style representation, while maintaining the robustness to general styles.  ...  eral style while losing fine-grained details.  ... 
arXiv:2109.14525v3 fatcat:iayrldmpevfzbaenhlejh74icy

Radiologist-Level COVID-19 Detection Using CT Scans with Detail-Oriented Capsule Networks [article]

Aryan Mobiny, Pietro Antonio Cicalese, Samira Zare, Pengyu Yuan, Mohammadsajad Abavisani, Carol C. Wu, Jitesh Ahuja, Patricia M. de Groot, Hien Van Nguyen
2020 arXiv   pre-print
The network then uses the activation maps to focus on regions of interest and combines both coarse and fine-grained representations of the data.  ...  Motivated by this challenge, our paper proposes a novel learning architecture, called Detail-Oriented Capsule Networks (DECAPS), for the automatic diagnosis of COVID-19 from Computed Tomography (CT) scans  ...  Activation-Guided Training (Peekaboo): To further promote DECAPS to focus on fine-grained details, we propose the Peekaboo strategy for capsule networks.  ... 
arXiv:2004.07407v1 fatcat:mknnn5vykzfjrb5dpdjybmtz2a

Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos [article]

Serena Yeung, Olga Russakovsky, Ning Jin, Mykhaylo Andriluka, Greg Mori, Li Fei-Fei
2017 arXiv   pre-print
Every moment counts in action recognition.  ...  To study this problem we extend the existing THUMOS dataset and introduce MultiTHUMOS, a new dataset of dense labels over unconstrained internet videos.  ...  Acknowledgments We would like to thank Andrej Karpathy and Amir Zamir for helpful comments and discussion.  ... 
arXiv:1507.05738v3 fatcat:ny352raimrcadpvp2uggei2miq

Detailed 2D-3D Joint Representation for Human-Object Interaction [article]

Yong-Lu Li, Xinpeng Liu, Han Lu, Shiyi Wang, Junqi Liu, Jiefeng Li, Cewu Lu
2020 arXiv   pre-print
First, we utilize the single-view human body capture method to obtain detailed 3D body, face and hand shapes.  ...  However, rough 3D body joints just carry sparse body information and are not sufficient to understand complex interactions. Thus, we need detailed 3D body shape to go further.  ...  These information would largely help the HOI learning, especially on actions related to face and hands. jects. Thus we need holistic and fine-grained 3D body information as a clue.  ... 
arXiv:2004.08154v2 fatcat:cqzebkv4ijbs7gpez4wpuq5sra

Detailed Exploration of Face-related Processing in Congenital Prosopagnosia: 1. Behavioral Findings

Marlene Behrmann, Galia Avidan, Jonathan J. Marotta, Rutie Kimchi
2005 Journal of Cognitive Neuroscience  
& We show that five individuals with congenital prosopagnosia (CP) are impaired at face recognition and discrimination and do not exhibit the normal superiority for upright over inverted faces despite  ...  Interestingly, the deficit is not limited to faces: The CP individuals were also impaired at discriminating common objects and novel objects although to a lesser extent than discriminating faces.  ...  This study was funded by grants from the National Institutes of Mental Health to MB (MH54246), from the US-Israel Binational Science Foundation to MB and RK, and from the McDonnell Pew Program in Cognitive  ... 
doi:10.1162/0898929054475154 pmid:16102241 fatcat:2dlaiycxx5amxac6dgxrn6vifu

Right anterior temporal lobe atrophy and person-based semantic defect: A detailed case study

Thomas Busigny, Laurence Robaye, Laurence Dricot, Bruno Rossion
2009 Neurocase  
We also thank Dr Eric Mormont from the Cliniques Universitaires de Mont-Godinne for his collaboration, and Gwenaelle Feyers for having conducted the language assessment, Valerie Goffaux for the making  ...  case of a right temporal pole variant of frontotemporal dementia (Rtv-FTLD), MD, who presented a slowly progressive deterioration of the recognition of familiar and famous people.  ...  Precisely, MD was able to make fine-grained discriminations between exemplars of different classes of objects (including faces), and to match faces, even when they were presented in different viewpoints  ... 
doi:10.1080/13554790902971141 pmid:19568984 fatcat:u6evtyt4y5epza2s2bhbd4yiam

Brain regions involved in the retrieval of spatial and episodic details associated with a familiar environment: An fMRI study

Marnie Hirshhorn, Cheryl Grady, R. Shayna Rosenbaum, Gordon Winocur, Morris Moscovitch
2012 Neuropsychologia  
Functional magnetic resonance imaging (fMRI) was used to compare brain activity during the retrieval of coarse-and fine-grained spatial details and episodic details associated with a familiar environment  ...  To examine whole-brain patterns of activity, Partial Least Squares (PLS) analysis was used to identify sets of brain regions whose activity covaried with the three conditions.  ...  Acknowledgments The preparation of this paper, as well as some of the research reported therein was supported by a Grant to the authors by the Canadian Institutes for Health Research (Grant number: MGP  ... 
doi:10.1016/j.neuropsychologia.2012.08.008 pmid:22910274 fatcat:627dc3wbvngjdchye263sscsfa

The Visual Perception of Fine Detail

H. Hartridge
1947 Philosophical Transactions of the Royal Society of London. Biological Sciences  
This is described in Part X . I would like to thank my colleagues; those in the Cambridge laboratories; those evacuated with us from London; and particularly those who belong to Bart's.  ...  The position, so far as apparatus is concerned, has changed recently for the better, as a special instrument has now been constructed, which has shown itself to be suitable for the tasks for which it was  ...  for the high acuity of the eye for fine detail.  ... 
doi:10.1098/rstb.1947.0004 fatcat:25lnrekhznamxir23to7aco2ui

Cascade one-vs-rest detection network for fine-grained recognition without part annotations [article]

Long Chen, Junyu Dong, ShengKe Wang, Kin-Man Lam, Muwei Jian, Hua Zhang, XiaoChun Cao
2017 arXiv   pre-print
In this paper, we propose a novel cascaded deep CNN detection framework for fine-grained recognition which is trained to detect the whole object without considering parts.  ...  Fine-grained recognition is a challenging task due to the small intra-category variances. Most of top-performing fine-grained recognition methods leverage parts of objects for better performance.  ...  Different from [19] , we propose a novel cascaded detection framework for fine-grained recognition tasks and improve some details for better performance.  ... 
arXiv:1702.08692v2 fatcat:xowfgfs6dzgandbj4s52f4opgm

Contour-aware Polyp Segmentation in Colonoscopy Images using Detailed Upsamling Encoder-Decoder Networks

Ngoc-Quang Nguyen, Duc My Vo, Sang-Woong Lee
2020 IEEE Access  
Additionally, the potential of some common polyp types to progress to colorectal cancer is considered high. Colonoscopy is the most common method for finding and removing polyps.  ...  NGOC-QUANG NGUYEN received the bachelor's degree from the University of Engineering and Technology-Vietnam National University, Hanoi, in 2017, and the master's degree from the Pattern Recognition and  ...  to capture the fine-grained information lost by convolution and pooling operations in CNNs.  ... 
doi:10.1109/access.2020.2995630 fatcat:xjkuu7pjlvabhd3uqscss2zcza

Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement [article]

Yibing Song, Jiawei Zhang, Lijun Gong, Shengfeng He, Linchao Bao, Jinshan Pan, Qingxiong Yang, Ming-Hsuan Yang
2018 arXiv   pre-print
from the input face image.  ...  We address the problem of restoring a high-resolution face image from a blurry low-resolution input. This problem is difficult as super-resolution and deblurring need to be tackled simultaneously.  ...  Meanwhile, we synthesize fine-grained structures from HR exemplar images and transfer their high-frequency details back to the base image for enhancement.  ... 
arXiv:1811.09019v1 fatcat:zhaokqukyjfl5ocamyz67cbd4i

Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition [article]

Hao Li, Xiaopeng Zhang, Hongkai Xiong, Qi Tian
2020 arXiv   pre-print
In this paper, we propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples.  ...  Collecting fine-grained labels usually requires expert-level domain knowledge and is prohibitive to scale up.  ...  However, we argue that for fine-grained recognition, the most critical challenge arises from the limited training samples, since collecting labels for fine-grained samples often requires expert-level domain  ... 
arXiv:2004.02684v2 fatcat:vususbkgpvcc7ebm3gwqa5bm6u

Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition [article]

Xinda Liu, Lili Wang, Xiaoguang Han
2021 arXiv   pre-print
Fine-grained image recognition is challenging because discriminative clues are usually fragmented, whether from a single image or multiple images.  ...  In this paper, we analyze the difficulties of fine-grained image recognition from a new perspective and propose a transformer architecture with the peak suppression module and knowledge guidance module  ...  Discriminative parts are annotated by red boxes. The details in the red boxes of (a) and (b) are magnified next to the image.  ... 
arXiv:2107.06538v2 fatcat:p4bjvwr45vh3fm2cfjm5byjxdm
« Previous Showing results 1 — 15 out of 13,853 results