Filters








1,797 Hits in 5.4 sec

Deep Multiple Instance Learning for Zero-shot Image Tagging [article]

Shafin Rahman, Salman Khan
2018 arXiv   pre-print
We experiment with the NUS-WIDE dataset and achieve superior performance across conventional, zero-shot and generalized zero-shot tagging tasks.  ...  ., Selective Search or EdgeBoxes) for bag generation. (2) During test time, it can process any number of unseen labels given their semantic embedding vectors. (3) Using only seen labels per image as weak  ...  An early attempt of such kind extended a work for zero-shot recognition [29] to perform zero-shot tagging by proposing a hierarchical semantic embedding to make the label embedding more reliable [11  ... 
arXiv:1803.06051v1 fatcat:hgctrovivrcohc35g5a2yksi6m

Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts [article]

Shafin Rahman, Salman Khan, Fatih Porikli
2018 arXiv   pre-print
Current Zero-Shot Learning (ZSL) approaches are restricted to recognition of a single dominant unseen object category in a test image.  ...  To address this limitation, we introduce a new 'Zero-Shot Detection' (ZSD) problem setting, which aims at simultaneously recognizing and locating object instances belonging to novel categories without  ...  Zero-shot image tagging: Instead of assigning one unseen label to an image during recognition task, zero-shot tagging allows to tag multiple unseen tags to an image and/or ranking the array of unseen tags  ... 
arXiv:1803.06049v1 fatcat:qpyx5k6nt5f6let2dklm5xdmfy

Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection [article]

Meng Ye, Yuhong Guo
2018 arXiv   pre-print
We conduct experiments for zero-shot multi-label image classification. The results demonstrate the efficacy of the proposed approach.  ...  In this paper we propose a transfer-aware embedding projection approach to tackle multi-label zero-shot learning.  ...  In [Fu et al., 2014] , the authors proposed to address multi-label zero-shot learning by mapping images into the semantic word space.  ... 
arXiv:1808.02474v1 fatcat:dov2w7ofbvdg3kdfiprkb5sm3i

Inductive Zero-Shot Image Annotation via Embedding Graph

Fangxin Wang, Jie Liu, Shuwu Zhang, Guixuan Zhang, Yuejun Li, Fei Yuan
2019 IEEE Access  
INDEX TERMS Contextualized word embeddings, graph convolutional network, image annotation, Node2Vec, zero-shot.  ...  In this paper, we focus on the two big challenges of zero-shot image annotation: polysemous words and a strong bias in the generalized zero-shot setting.  ...  ZERO-SHOT IMAGE ANNOTATION USING GCN In [45] , the transfer ability was improved by formatting superclasses in the semantic space.  ... 
doi:10.1109/access.2019.2925383 fatcat:2wiwjg2wj5ac3bva44kyn3ou5u

Visual Classifier Prediction by Distributional Semantic Embedding of Text Descriptions

Mohamed Elhoseiny, Ahmed Elgammal
2015 Proceedings of the Fourth Workshop on Vision and Language  
Sharing knowledge can by achieved by enforcing a hierarchical structure on the classes, general to specific. Such hierarchy is used to impose constraints on the classifier parameters.  ...  In this talk/presentation, we will present our new zero-shot learning framework for predicting kernelized classifiers in the visual domain for categories with no training images where the knowledge comes  ... 
doi:10.18653/v1/w15-2809 dblp:conf/acl-vl/ElhoseinyE15 fatcat:mpwypurymzhdnlimq2nch4q3pm

A Survey on Visual Transfer Learning using Knowledge Graphs [article]

Sebastian Monka, Lavdim Halilaj, Achim Rettinger
2022 arXiv   pre-print
Especially, approaches that augment image data using auxiliary knowledge encoded in language embeddings or knowledge graphs (KGs) have achieved promising results in recent years.  ...  We explain the notion of feature extractor, while specifically referring to visual and semantic features.  ...  [101] try to reduce the bias of semantic embedding spaces, by proposing a transductive multi-view embedding framework that aligns novel features with the semantic embedding space for zero-shot learning  ... 
arXiv:2201.11794v1 fatcat:tapql5h4j5dvrnxjkaxek2cquu

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

A survey on visual transfer learning using knowledge graphs

Sebastian Monka, Lavdim Halilaj, Achim Rettinger, Mehwish Alam, Davide Buscaldi, Michael Cochez, Francesco Osborne, Diego Reforgiato Recupero, Harald Sack
2022 Semantic Web Journal  
Especially, approaches that augment image data using auxiliary knowledge encoded in language embeddings or knowledge graphs (KGs) have achieved promising results in recent years.  ...  We explain the notion of feature extractor, while specifically referring to visual and semantic features.  ...  basis of a decision by the German Bundestag.  ... 
doi:10.3233/sw-212959 fatcat:f4s43if3nbcxxfvrbtpdrrs2ry

Label Embedding for Zero-shot Fine-grained Named Entity Typing

Yukun Ma, Erik Cambria, Sa Gao
2016 International Conference on Computational Linguistics  
We perform evaluation on three benchmark datasets with two settings: 1) few-shots recognition where all types are covered by the training set; and 2) zero-shot recognition where fine-grained types are  ...  In this paper, we present a label embedding method that incorporates prototypical and hierarchical information to learn pre-trained label embeddings.  ...  Zero-shot FNET Extension A zero-shot extension of above WSABIE method can be done by introducing pre-trained label embeddings into the framework.  ... 
dblp:conf/coling/MaCG16 fatcat:zvu2nrdpvrf6lbl3ilrqhvv7ou

A Large-Scale Attribute Dataset for Zero-Shot Learning

Bo Zhao, Yanwei Fu, Rui Liang, Jiahong Wu, Yonggang Wang, Yizhou Wang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Each concept (class) is embedded in two or more modalities, e.g., the image features and semantic embeddings.  ...  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.  ...  Pixel-CNN is utilized to model images conditioned on labels, tags or latent embeddings [36] .  ... 
doi:10.1109/cvprw.2019.00053 dblp:conf/cvpr/ZhaoFLWWW19 fatcat:rqiwul46w5g5dakjb24npyvdka

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
We analyze our dataset by conducting both supervised learning and zero-shot learning tasks. Seven state-of-the-art ZSL algorithms are tested on this new dataset.  ...  The experimental results reveal the challenge of implementing zero-shot learning on our dataset.  ...  Pixel-CNN is utilized to model images conditioned on labels, tags or latent embeddings [48] .  ... 
arXiv:1804.04314v2 fatcat:7lf5sdvzc5dlrbbusquwou7z54

Zero-Shot Object Recognition System Based on Topic Model

Wai Lam Hoo, Chee Seng Chan
2015 IEEE Transactions on Human-Machine Systems  
We propose a novel zero-shot learning strategy that utilizes the topic model and hierarchical class concept.  ...  In this paper, we study the problem of object recognition where the training samples are missing during the classifier learning stage, a task also known as zero-shot learning.  ...  Visual-Semantic Embedding Model (DeViSE).  ... 
doi:10.1109/thms.2014.2358649 fatcat:byamfnuto5apviihl5rwzhxbgu

RUC-Tencent at ImageCLEF 2015: Concept Detection, Localization and Sentence Generation

Xirong Li, Qin Jin, Shuai Liao, Junwei Liang, Xixi He, Yujia Huo, Weiyu Lan, Bin Xiao, Yanxiong Lu, Jieping Xu
2015 Conference and Labs of the Evaluation Forum  
For concept detection, we experiments with automated approaches to gather high-quality training examples from the Web, in particular, visual disambiguation by Hierarchical Semantic Embedding.  ...  Per concept, an ensemble of linear SVMs is trained by Negative Bootstrap, with CNN features as image representation.  ...  To compute the relevance score between the given concept and a specific image, we embed them into a common semantic space by the Hierarchical Semantic Embedding (HierSE) algorithm [4] .  ... 
dblp:conf/clef/LiJLLHHLXLX15 fatcat:oubhke3babhitb4pkbwdacithm

Flexible Interactive Retrieval SysTem 3.0 for Visual Lifelog Exploration at LSC 2022

Nhat Hoang-Xuan, Hoang-Phuc Trang-Trung, E-Ro Nguyen, Thanh-Cong Le, Mai-Khiem Tran, Tu-Khiem Le, Van-Tu Ninh, Cathal Gurrin, Minh-Triet Tran
2022 Proceedings of the 5th Annual on Lifelog Search Challenge  
Our system aims to adaptively capture the semantics of an image at different levels of detail.  ...  Finally, we organize image data in hierarchical clusters based on their visual similarity and location to assist users in data exploration.  ...  The adaptive semantic embedding set is the collection of semantic embedding vectors of the full-size image and its exciting patches.  ... 
doi:10.1145/3512729.3533013 fatcat:coaiyhbhlbh6hgzdpxf7eqsjo4

PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining [article]

Yuting Gao, Jinfeng Liu, Zihan Xu, Jun Zhang, Ke Li, Rongrong Ji, Chunhua Shen
2022 arXiv   pre-print
In particular, with the same amount of 15 million pre-training image-text pairs, PyramidCLIP exceeds CLIP on ImageNet zero-shot classification top-1 accuracy by 10.6%/13.2%/10.0% with ResNet50/ViT-B32/  ...  In particular, the results of PyramidCLIP-ResNet50 trained on 143M image-text pairs surpass that of CLIP using 400M data on ImageNet zero-shot classification task, significantly improving the data efficiency  ...  Method Image Encoder MS-COCO ImageNet I2T R@1 I2T R@5 T2I R@1 T2I R@5 ZS Top1 9 : Zero-shot image-text retrieval results on MS-COCO and zero-shot top1 accuracy on ImageNet.  ... 
arXiv:2204.14095v2 fatcat:sa23oporjjhnpjkeujcwywzpc4
« Previous Showing results 1 — 15 out of 1,797 results