9,735 Hits in 4.1 sec

On Learning Semantic Representations for Million-Scale Free-Hand Sketches [article]

Peng Xu, Yongye Huang, Tongtong Yuan, Tao Xiang, Timothy M. Hospedales, Yi-Zhe Song, Liang Wang
2020 arXiv   pre-print
knowledge for sketch zero-shot domain alignment.  ...  (ii) We propose a deep embedding model for sketch zero-shot recognition, via collecting a large-scale edge-map dataset and proposing to extract a set of semantic vectors from edge-maps as the semantic  ...  Region Embedding Network for zero-shot learning (AREN) [57] .  ... 
arXiv:2007.04101v1 fatcat:cng2cw6r5fg43p5erfisj57tu4

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

Zero-Shot Action Recognition from Diverse Object-Scene Compositions [article]

Carlo Bretti, Pascal Mettes
2021 arXiv   pre-print
This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available.  ...  For this challenging scenario, the current leading approach is to transfer knowledge from the image domain by recognizing objects in videos using pre-trained networks, followed by a semantic matching between  ...  Ablation III: Effect of sentence embeddings for semantic matching. Sentence embeddings have recently been shown to be beneficial for zero-shot recognition in the image domain [22] .  ... 
arXiv:2110.13479v1 fatcat:u4cq4cul3faqdftfjwtfnkjf6i

Learning Robust Visual-Semantic Embeddings [article]

Yao-Hung Hubert Tsai and Liang-Kang Huang and Ruslan Salakhutdinov
2017 arXiv   pre-print
We evaluate our method on Animals with Attributes and Caltech-UCSD Birds 200-2011 dataset with a wide range of applications, including zero and few-shot image recognition and retrieval, from inductive  ...  The proposed method combines representation learning models (i.e., auto-encoders) together with cross-domain learning criteria (i.e., Maximum Mean Discrepancy loss) to learn joint embeddings for semantic  ...  Thus, the focus of zero-shot image recognition is to derive joint embeddings of visual and textual data, so that the missing information of specific classes could be transferred from the textual domain  ... 
arXiv:1703.05908v2 fatcat:bmvr3bbvavepbg7k7gwgks7gne

Zero-Shot Learning via Joint Latent Similarity Embedding

Ziming Zhang, Venkatesh Saligrama
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In ICCV, pages 2120–2127, multi-view embedding for zero-shot recognition and annotation.  ...  Fig. 1 illustrates based zero-shot methods, our method learns a joint latent a specific scenario where visual and word embedding func- space for both domains using structured learning.  ... 
doi:10.1109/cvpr.2016.649 dblp:conf/cvpr/ZhangS16 fatcat:y45nsoismzcdzkqvdj5rlmnuje

Exploring synonyms as context in zero-shot action recognition

Ioannis Alexiou, Tao Xiang, Shaogang Gong
2016 2016 IEEE International Conference on Image Processing (ICIP)  
Zero shot learning (ZSL) provides a solution to recognising unseen classes without class labelled data for model learning.  ...  This is compounded further in zero-shot action recognition due to richer content variations among action classes.  ...  Synonym Search Zero-Shot Recognition Table 1 : 1 Conventional word vector embedding for ZSL action recognition.  ... 
doi:10.1109/icip.2016.7533149 dblp:conf/icip/AlexiouXG16 fatcat:xt3ipbrlmjbubchaoawxthjmy4

Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders [article]

Abhishek Banerjee, Uttaran Bhattacharya, Aniket Bera
2021 arXiv   pre-print
This improves the performance of current state-of-the-art algorithms for generalized zero-shot learning by 25–27% on the absolute.  ...  We present a novel generalized zero-shot algorithm to recognize perceived emotions from gestures. Our task is to map gestures to novel emotion categories not encountered in training.  ...  Generalized Zero-Shot Learning In the Generalized Zero-Shot Learning (GSZL) problem, the recognition task is executed for both seen and unseen classes.  ... 
arXiv:2009.08906v2 fatcat:riebcb2mr5c5rpqgyw7c3mssum

Convolutional Prototype Learning for Zero-Shot Recognition [article]

Zhizhe Liu, Xingxing Zhang, Zhenfeng Zhu, Shuai Zheng, Yao Zhao, Jian Cheng
2020 arXiv   pre-print
In this paper, we propose a simple yet effective convolutional prototype learning (CPL) framework for zero-shot recognition.  ...  Zero-shot learning (ZSL) has received increasing attention in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning.  ...  Let Ψ(x) denote a convolutional neural network based embedding module, which can learn feature representation for any input image x.  ... 
arXiv:1910.09728v3 fatcat:vebdwnncrvd75fzwae76u5wsr4

CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition [article]

Shreyank N Gowda, Laura Sevilla-Lara, Frank Keller, Marcus Rohrbach
2021 arXiv   pre-print
Zero-shot action recognition is the task of recognizingaction classes without visual examples, only with a seman-tic embedding which relates unseen to seen classes.  ...  We optimize theclustering using Reinforcement Learning which we show iscritical for our approach to work.  ...  We call our proposed method CLASTER, for CLustering for Action recognition in zero-ShoT lEaRning, and show that it significantly outperforms all existing methods across all standard zero-shot action recognition  ... 
arXiv:2101.07042v2 fatcat:w5qvvnv3rjdotaqadf5k4v6fvq

Low-resource Learning with Knowledge Graphs: A Comprehensive Survey [article]

Jiaoyan Chen and Yuxia Geng and Zhuo Chen and Jeff Z. Pan and Yuan He and Wen Zhang and Ian Horrocks and Huajun Chen
2021 arXiv   pre-print
In this survey, we very comprehensively reviewed over 90 papers about KG-aware research for two major low-resource learning settings – zero-shot learning (ZSL) where new classes for prediction have never  ...  Machine learning methods especially deep neural networks have achieved great success but many of them often rely on a number of labeled samples for training.  ...  DOZEN: Cross-domain zero shot named entity recognition with knowledge graph.  ... 
arXiv:2112.10006v3 fatcat:wkz6gjx4r5gvlhh673p3rqsmgi

A Large-scale Attribute Dataset for Zero-shot Learning [article]

Bo Zhao, Yanwei Fu, Rui Liang, Jiahong Wu, Yonggang Wang, Yizhou Wang
2018 arXiv   pre-print
The experimental results reveal the challenge of implementing zero-shot learning on our dataset.  ...  Zero-Shot Learning (ZSL) has attracted huge research attention over the past few years; it aims to learn the new concepts that have never been seen before.  ...  Zero-shot Recognition by Attributes We propose LAD as the new testbed for zero-shot recognition.  ... 
arXiv:1804.04314v2 fatcat:7lf5sdvzc5dlrbbusquwou7z54

Zero-Shot Human Activity Recognition Using Non-Visual Sensors

Fadi Al Machot, Mohammed R. Elkobaisi, Kyandoghere Kyamakya
2020 Sensors  
We show that sensor readings can lead to promising results for zero-shot learning, whereby the necessary knowledge can be transferred from seen to unseen activities by using semantic similarity.  ...  Activity recognition methods based on real-life settings should cover a growing number of activities in various domains, whereby a significant part of instances will not be present in the training data  ...  Acknowledgments: We thank the center of advanced studies in adaptive systems for sharing their dataset. Conflicts of Interest: The authors declare no conflicts of interest. Sensors 2020, 20, 825  ... 
doi:10.3390/s20030825 pmid:32033072 pmcid:PMC7038698 fatcat:qm32wvzcsneupmm42k7pe7djo4

Learning Visually Consistent Label Embeddings for Zero-Shot Learning [article]

Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
2019 arXiv   pre-print
In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end  ...  We evaluate the proposed approach on two benchmark datasets and the experimental results show that our method yields significant improvements in recognition accuracy.  ...  In this work, we have aimed to improve zero-shot recognition by using visually meaningful word vectors within the label embedding framework.  ... 
arXiv:1905.06764v1 fatcat:563enegx3rdh3avx6lggfall44

Supervised Contrastive Learning for Accented Speech Recognition [article]

Tao Han, Hantao Huang, Ziang Yang, Wei Han
2021 arXiv   pre-print
Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents.  ...  In this paper, we study the supervised contrastive learning framework for accented speech recognition.  ...  Introduction Recently, neural network based automatic speech recognition (ASR) has achieved impressive progress for real life applications.  ... 
arXiv:2107.00921v1 fatcat:ofxdq4x6yfbpxemod3tzfrshpm

Sketch-a-Classifier: Sketch-Based Photo Classifier Generation

Conghui Hu, Da Li, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
This approach doesn't require the category to be nameable or describable via attributes as per zero-shot learning.  ...  This has motivated investigation into zero-shot learning, which addresses the issue via knowledge transfer from other modalities such as text.  ...  Regression Networks Model to model regression: Binary For binary photo recognition problems, we input SVM parameters trained on sketch domain and predict the parameters of the corresponding SVM for the  ... 
doi:10.1109/cvpr.2018.00952 dblp:conf/cvpr/HuLSXH18 fatcat:73aplwu5gbcizhocmivyaqtgsm
« Previous Showing results 1 — 15 out of 9,735 results