Filters








543 Hits in 6.7 sec

Zero-Shot Hashing via Transferring Supervised Knowledge [article]

Yang Yang, Weilun Chen, Yadan Luo, Fumin Shen, Jie Shao, Heng Tao Shen
2016 arXiv   pre-print
Extensive experiments conducted on various real-life datasets show the superior zero-shot image retrieval performance of ZSH as compared to several state-of-the-art hashing methods.  ...  In this paper, we propose a novel hashing scheme, termed zero-shot hashing (ZSH), which compresses images of "unseen" categories to binary codes with hash functions learned from limited training data of  ...  Image Retrieval in Related Categories In zero-shot image retrieval scenario, we expect that even though we fail to retrieve relevant images of the same category, we can still obtain semantically related  ... 
arXiv:1606.05032v1 fatcat:prm5zg5hrveedaizb466hq5kqu

Transductive Zero-Shot Hashing for Multi-Label Image Retrieval [article]

Qin Zou, Zheng Zhang, Ling Cao, Long Chen, Song Wang
2019 arXiv   pre-print
In this paper, for the first time, a novel transductive zero-shot hashing method is proposed for multi-label unseen image retrieval.  ...  Hash coding has been widely used in approximate nearest neighbor search for large-scale image retrieval.  ...  For image retrieval under the circumstance of unseen images, some zero-shot hashing (ZSH) methods [23] - [27] have also been proposed.  ... 
arXiv:1911.07192v1 fatcat:mr5kdlsi5faxpn2a2obakha3se

Zero-Shot Hashing via Transferring Supervised Knowledge

Yang Yang, Yadan Luo, Weilun Chen, Fumin Shen, Jie Shao, Heng Tao Shen
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
Extensive experiments conducted on various real-life datasets show the superior zero-shot image retrieval performance of ZSH as compared to several state-of-the-art hashing methods.  ...  In this paper, we propose a novel hashing scheme, termed zero-shot hashing (ZSH), which compresses images of "unseen" categories to binary codes with hash functions learned from limited training data of  ...  Image Retrieval in Related Categories In zero-shot image retrieval scenario, we expect that even though we fail to retrieve relevant images of the same category, we can still obtain semantically related  ... 
doi:10.1145/2964284.2964319 dblp:conf/mm/0002LCSSS16 fatcat:h62t7jgh3vh7ljdcf2nh47xvfa

Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval [article]

Zhipeng Wang, Hao Wang, Jiexi Yan, Aming Wu, Cheng Deng
2021 arXiv   pre-print
Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a novel cross-modal retrieval task, where abstract sketches are used as queries to retrieve natural images under zero-shot scenario.  ...  Toward this end, we propose a novel Domain-Smoothing Network (DSN) for ZS-SBIR.  ...  Acknowledgments Our work was supported in part by the National Natural Science Foundation of China under Grant 62071361, and in part by the Fundamental Research Funds for the Central Universities ZDRC2102  ... 
arXiv:2106.11841v1 fatcat:qgddlkknvneg3hxiqh2pxrq6ee

Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval [article]

Anjan Dutta, Zeynep Akata
2019 arXiv   pre-print
Zero-shot sketch-based image retrieval (SBIR) is an emerging task in computer vision, allowing to retrieve natural images relevant to sketch queries that might not been seen in the training phase.  ...  In this work, we propose a semantically aligned paired cycle-consistent generative (SEM-PCYC) model for zero-shot SBIR, where each branch maps the visual information to a common semantic space via an adversarial  ...  The Titan Xp and Titan V used for this research were donated by the NVIDIA Corporation.  ... 
arXiv:1903.03372v1 fatcat:ig3bjce4kfeefjnqyhgmujp7dy

Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval [article]

Anjan Dutta, Zeynep Akata
2020 arXiv   pre-print
In this paper, we address any-shot, i.e. zero-shot and few-shot, sketch-based image retrieval (SBIR) tasks, where we introduce the few-shot setting for SBIR.  ...  Low-shot sketch-based image retrieval is an emerging task in computer vision, allowing to retrieve natural images relevant to hand-drawn sketch queries that are rarely seen during the training phase.  ...  The TITAN Xp and TITAN V used for this research were donated by the NVIDIA Corporation.  ... 
arXiv:2006.11397v1 fatcat:4tkatm4h5jdzjacdx23x7jbd7y

Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-Based Image Retrieval

Anjan Dutta, Zeynep Akata
2020 International Journal of Computer Vision  
In this paper, we address any-shot, i.e. zero-shot and few-shot, sketch-based image retrieval (SBIR) tasks, where we introduce the few-shot setting for SBIR.  ...  Low-shot sketch-based image retrieval is an emerging task in computer vision, allowing to retrieve natural images relevant to hand-drawn sketch queries that are rarely seen during the training phase.  ...  The TITAN Xp and TITAN V used for this research were donated by the NVIDIA Corporation.  ... 
doi:10.1007/s11263-020-01350-x fatcat:chi7krnz3zhmbbyw7huiosh3ey

Meta Cross-Modal Hashing on Long-Tailed Data [article]

Runmin Wang, Guoxian Yu, Carlotta Domeniconi, Xiangliang Zhang
2021 arXiv   pre-print
Due to the advantage of reducing storage while speeding up query time on big heterogeneous data, cross-modal hashing has been extensively studied for approximate nearest neighbor search of multi-modal  ...  For samples of the head classes of the long tail distribution, the weight of the direct features is larger, because there are enough training data to learn them well; while for rare classes, the weight  ...  For example, we may want to find images or videos semantically related to the text of a query or to keywords.  ... 
arXiv:2111.04086v1 fatcat:gtbk4b2qivfxxd2cvwd2jgdkpi

Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval [article]

Qing Liu, Lingxi Xie, Huiyu Wang, Alan Yuille
2019 arXiv   pre-print
for photo images.  ...  Sketch-based image retrieval (SBIR) is widely recognized as an important vision problem which implies a wide range of real-world applications.  ...  We thank Chenxi Liu for helping design Figure 1 and proofreading. We thank Chenglin Yang for discussions on knowledge distillation.  ... 
arXiv:1904.03208v3 fatcat:ovs6hdklwnhanogtm7wdvsi5ay

Deep Zero-Shot Learning for Scene Sketch [article]

Yao Xie and Peng Xu and Zhanyu Ma
2019 arXiv   pre-print
To overcome these challenges, we propose a deep embedding model for scene sketch zero-shot learning.  ...  In particular, we propose the augmented semantic vector to conduct domain alignment by fusing multi-modal semantic knowledge (e.g., cartoon image, natural image, text description), and adopt attention-based  ...  All the following zero-shot experiments are performed for scene sketch, while natural images (I), cartoons images (C) and text descriptions (T) are used to obtain our augmented semantic vector.  ... 
arXiv:1905.04510v1 fatcat:wkfghirrtneilh24rnrb6ouzwm

MESH: A Flexible Manifold-Embedded Semantic Hashing for Cross-Modal Retrieval

Fangming Zhong, Guangze Wang, Zhikui Chen, Feng Xia
2020 IEEE Access  
Hashing based methods for cross-modal retrieval has been widely explored in recent years.  ...  To address these issues, in this article, we propose a two-step cross-modal retrieval method named Manifold-Embedded Semantic Hashing (MESH).  ...  Recently, zero-shot cross-modal hashing has drawn considerable interests, our model cannot handle the zero-shot problem currently.  ... 
doi:10.1109/access.2020.3015528 fatcat:k42zalqde5afbk5hlw3sj736im

Zero-Shot Deep Hashing and Neural Network Based Error Correction for Face Template Protection [article]

Veeru Talreja, Matthew C. Valenti, Nasser M. Nasrabadi
2019 arXiv   pre-print
The efficacy of our approach with zero-shot, one-shot, and multi-shot enrollments is shown for CMU-PIE, Extended Yale B, WVU multimodal and Multi-PIE face databases.  ...  The proposed architecture consists of two major components: a deep hashing (DH) component, which is used for robust mapping of face images to their corresponding intermediate binary codes, and a NND component  ...  For this reason, we use several augmented images (as described in Sec. 4.1) of each image presented for authentication, and T p is calculated for each augmented image, yielding a set of templates T .  ... 
arXiv:1908.02706v1 fatcat:hivldf2bcvaolbq7djjbmihh3m

A Zero-Shot Framework for Sketch-based Image Retrieval [article]

Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal
2018 arXiv   pre-print
Sketch-based image retrieval (SBIR) is the task of retrieving images from a natural image database that correspond to a given hand-drawn sketch.  ...  In this paper, we propose a new benchmark for zero-shot SBIR where the model is evaluated in novel classes that are not seen during training.  ...  Thus, the Zero-Shot Sketch Based Image Retrieval (ZS-SBIR) task introduced in this paper provides a more realistic setup for the sketch-based retrieval task.  ... 
arXiv:1807.11724v1 fatcat:l37g3e7oazdthl2rbacocii2b4

A Decade Survey of Content Based Image Retrieval using Deep Learning [article]

Shiv Ram Dubey
2020 arXiv   pre-print
Generally, the similarity between the representative features of the query image and dataset images is used to rank the images for retrieval.  ...  This paper presents a comprehensive survey of deep learning based developments in the past decade for content based image retrieval.  ...  A zero-shot sketch-based image retrieval (ZS-SBIR) is proposed for retrieval of photos from unseen categories [167] .  ... 
arXiv:2012.00641v1 fatcat:2zcho2szpzcc3cs6uou3jpcley

From Traditional to Modern: Domain Adaptation for Action Classification in Short Social Video Clips [chapter]

Aditya Singh, Saurabh Saini, Rajvi Shah, P. J. Narayanan
2016 Lecture Notes in Computer Science  
Additionally, we utilise a multi-modal representation that incorporates noisy semantic information available in form of hash-tags.  ...  To this end, we use a data augmentation based simple domain adaptation strategy.  ...  For learning the embedding function, we use publicly available implementations of word2vec 2 and zero-shot learning 3 .  ... 
doi:10.1007/978-3-319-45886-1_20 fatcat:ncbydmluwrcjfaohxjosicwdw4
« Previous Showing results 1 — 15 out of 543 results