Filters








1,518 Hits in 4.1 sec

Zero-shot object recognition by semantic manifold distance

Zhenyong Fu, Tao A Xiang, Elyor Kodirov, Shaogang Gong
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Object recognition by zero-shot learning (ZSL) aims to recognise objects without seeing any visual examples by learning knowledge transfer between seen and unseen object classes.  ...  The semantic manifold structure is used to redefine the distance metric in the semantic embedding space for more effective ZSL.  ...  Acknowledgments The authors were funded by the European Research Council under the FP7 Project SUNNY (grant agreement no. 313243).  ... 
doi:10.1109/cvpr.2015.7298879 dblp:conf/cvpr/FuXKG15 fatcat:2ophdrj72vfcffimbzrjbighgi

Zero-Shot Learning on Semantic Class Prototype Graph

Zhenyong Fu, Tao Xiang, Elyor Kodirov, Shaogang Gong
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Zero-Shot Learning (ZSL) for visual recognition is typically achieved by exploiting a semantic embedding space.  ...  To overcome these problems, a novel manifold distance computed on a semantic class prototype graph is proposed which takes into account the rich intrinsic semantic structure, i.e., semantic manifold, of  ...  ACKNOWLEDGEMENT The authors were funded in part by the European Research Council under the FP7 Project SUNNY (grant agreement no. 313243).  ... 
doi:10.1109/tpami.2017.2737007 pmid:28796607 fatcat:glg5peo2h5gytp6fyktg6j7bay

Zero-Shot Recognition using Dual Visual-Semantic Mapping Paths [article]

Yanan Li, Donghui Wang, Huanhang Hu, Yuetan Lin, Yueting Zhuang
2017 arXiv   pre-print
Zero-shot recognition aims to accurately recognize objects of unseen classes by using a shared visual-semantic mapping between the image feature space and the semantic embedding space.  ...  Motivated by this, we propose a novel framework for zero-shot recognition, which contains dual visual-semantic mapping paths.  ...  Supplementary Material: Zero-Shot Recog- nition using Dual Visual-Semantic Mapping Paths  ... 
arXiv:1703.05002v2 fatcat:ua44xjbg5rgzzlm6ahg4vfl65i

Transductive Zero-Shot Action Recognition by Word-Vector Embedding [article]

Xun Xu, Timothy Hospedales, Shaogang Gong
2016 arXiv   pre-print
Instead of collecting ever more data and labelling them exhaustively for all categories, an attractive alternative approach is zero-shot learning" (ZSL).  ...  In this work, we explore word-vectors as the shared semantic space to embed videos and category labels for ZSL action recognition.  ...  Another line of work towards zero-shot action recognition have been studied by Jain et al (2015) who proposed to exploit the vast object annotations, images and textual descriptions, e.g.  ... 
arXiv:1511.04458v2 fatcat:yxfn52pdhjfatedmixz4evtiay

Transductive Zero-Shot Action Recognition by Word-Vector Embedding

Xun Xu, Timothy Hospedales, Shaogang Gong
2017 International Journal of Computer Vision  
The results demonstrate that our approach achieves the state-of-the-art zero-shot action recognition performance with a simple and efficient pipeline, and without supervised annotation of attributes.  ...  Finally, we present in-depth analysis into why and when zero-shot works, including demonstrating the ability to predict cross-category transferability in advance.  ...  zero-shot recognition is performed.  ... 
doi:10.1007/s11263-016-0983-5 fatcat:c6rn4jpg3ff5pbks52ohlcafny

Recent Advances in Zero-shot Recognition [article]

Yanwei Fu, Tao Xiang, Yu-Gang Jiang, Xiangyang Xue, Leonid Sigal, and Shaogang Gong
2017 arXiv   pre-print
or when zero-shot recognition is implemented in a real-world setting.  ...  We also overview related recognition tasks including one-shot and open set recognition which can be used as natural extensions of zero-shot recognition when limited number of class samples become available  ...  Yanwei Fu is supported by The Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning.  ... 
arXiv:1710.04837v1 fatcat:u3mp6dgj2rgqrarjm4dcywegmy

Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition [article]

Huajie Jiang, Ruiping Wang, Shiguang Shan, Xilin Chen
2018 arXiv   pre-print
Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets.  ...  Then, zero-shot recognition can be performed in different spaces by the simple nearest neighbor approach using the learned class prototypes.  ...  Related Work In this section, we review related works on zero-shot learning in three aspects, i.e. semantic information, visual-semantic embeddings, zero-shot recognition.  ... 
arXiv:1807.09123v1 fatcat:b7vpuqfua5aklfjvbutosu5kmy

A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion [article]

Jingcai Guo, Song Guo
2020 arXiv   pre-print
Under such a paradigm, most existing methods easily suffer from the domain shift problem and weaken the performance of zero-shot recognition.  ...  One common practice in zero-shot learning is to train a projection between the visual and semantic feature spaces with labeled seen classes examples.  ...  Recently, SAE [26] used a semantic autoencoder to regularize zero-shot recognition. Xian et al.  ... 
arXiv:2004.14795v1 fatcat:wy6hv3orgnbjzo4ejumbtua5eq

Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition [chapter]

Huajie Jiang, Ruiping Wang, Shiguang Shan, Xilin Chen
2018 Lecture Notes in Computer Science  
Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets.  ...  Then, zero-shot recognition can be performed in different spaces by the simple nearest neighbor approach using the learned class prototypes.  ...  Related Work In this section, we review related works on zero-shot learning in three aspects, i.e. semantic information, visual-semantic embeddings, zero-shot recognition.  ... 
doi:10.1007/978-3-030-01249-6_8 fatcat:kwlsx742ffe7xi3okrnloqj74u

Learning Robust Visual-semantic Mapping for Zero-shot Learning [article]

Jingcai Guo
2021 arXiv   pre-print
Zero-shot learning (ZSL) aims at recognizing unseen class examples (e.g., images) with knowledge transferred from seen classes.  ...  This is typically achieved by exploiting a semantic feature space shared by both seen and unseen classes, e.g., attributes or word vectors, as the bridge.  ...  space for zero-shot recognition.  ... 
arXiv:2104.05668v1 fatcat:uq5msriuovettbwar46qzjfcbm

Matrix Tri-Factorization with Manifold Regularizations for Zero-Shot Learning

Xing Xu, Fumin Shen, Yang Yang, Dongxiang Zhang, Heng Tao Shen, Jingkuan Song
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Zero-shot learning (ZSL) aims to recognize objects of unseen classes with available training data from another set of seen classes.  ...  By additionally introducing manifold regularizations on visual data and semantic embeddings, the learned projection can effectively capture the geometrical manifold structure residing in both visual and  ...  This work was supported in part by the National Natural Science Foundation of China under Project 61602089, Project 61502081, Project 61572108, Project 61632007, and the Fundamental Research Funds for  ... 
doi:10.1109/cvpr.2017.217 dblp:conf/cvpr/XuS0ZSS17 fatcat:6msmdsf7fjcjxikwl5xdhyz5ee

Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning [article]

Jared Markowitz, Aurora C. Schmidt, Philippe M. Burlina, I-Jeng Wang
2017 arXiv   pre-print
We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation.  ...  with those of posteriors based on semantic attribute estimation.  ...  zero-shot object recognition via hierarchical transfer of semantic attributes. In: IEEE Winter Conference on Applications of Computer Vision. pp.  ... 
arXiv:1712.03151v1 fatcat:maz4josz7baehms6ixbscowf2e

Semi-supervised Vocabulary-informed Learning [article]

Yanwei Fu, Leonid Sigal
2016 arXiv   pre-print
Specifically, we propose a maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms, ensuring that  ...  We show that resulting model shows improvements in supervised, zero-shot, and large open set recognition, with up to 310K class vocabulary on AwA and ImageNet datasets.  ...  Zero-shot learning (ZSL) has now been widely studied in a variety of research areas including neural decoding by fMRI images [31] , character recognition [26] , face verification [24] , object recognition  ... 
arXiv:1604.07093v1 fatcat:exieu23qirdw7g3owza6ymucri

AMS-SFE: Towards an Alignment of Manifold Structures via Semantic Feature Expansion for Zero-shot Learning [article]

Jingcai Guo, Song Guo
2019 arXiv   pre-print
It considers the Alignment of Manifold Structures by Semantic Feature Expansion.  ...  Zero-shot learning (ZSL) aims at recognizing unseen classes with knowledge transferred from seen classes.  ...  CONCLUSION In this paper, we proposed a novel model (AMS-SFE) for zero-shot learning that considers aligning the manifold structures of the semantic and visual feature spaces by jointly conducting semantic  ... 
arXiv:1904.06254v1 fatcat:nust2hf5ozdthbvv3m62v7ungu

Zero-Shot Domain Adaptation via Kernel Regression on the Grassmannian [article]

Yongxin Yang, Timothy Hospedales
2015 arXiv   pre-print
Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing.  ...  In this paper, we propose a new domain adaptation method that has no need to access either data or labels of the target domain when it can be described by a parametrised vector and there exits several  ...  Related Work Zero-Shot Learning Zero-Shot Learning (ZSL) has received extensive attention in the computer vision community, such as character [18] , object [8, 17] , and action [19] recognition.  ... 
arXiv:1507.07830v2 fatcat:b2ttnev7fncktokmkqasogu7ai
« Previous Showing results 1 — 15 out of 1,518 results