Filters








187,195 Hits in 6.1 sec

Discriminative Region-based Multi-Label Zero-Shot Learning [article]

Sanath Narayan, Akshita Gupta, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Mubarak Shah
2021 arXiv   pre-print
Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification.  ...  Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image.  ...  State-of-the-art performance comparison for the standard multi-label classification on Open Images. The results are reported in terms of mAP and F1 score at K∈{10, 20}.  ... 
arXiv:2108.09301v1 fatcat:gptpifksxbddraov3jfg3owmq4

Deep Semantic Dictionary Learning for Multi-label Image Classification [article]

Fengtao Zhou and Sheng Huang and Yun Xing
2021 arXiv   pre-print
Compared with single-label image classification, multi-label image classification is more practical and challenging.  ...  Some recent studies attempted to leverage the semantic information of categories for improving multi-label image classification performance.  ...  Related work 2.1 Multi-label Image Classification Problem Transformation Methods In this kind of approaches, the straightforward way is to treat multi-label image classification as a set of binary classification  ... 
arXiv:2012.12509v2 fatcat:nrnca4wbkndvrm7iuodetod7lq

Happy and agreeable?

Gilberto Chávez-Martínez, Salvador Ruiz-Correa, Daniel Gatica-Perez
2015 Proceedings of the 14th International Conference on Mobile and Ubiquitous Multimedia - MUM '15  
Under a multi-label classification framework, we show that for both mood and personality trait binary label sets, not only the simultaneous inference of multiple labels is feasible, but also that classification  ...  The multi-label method we consider naturally exploits label correlations, which motivate our approach, and our results are consistent with models proposed in psychology to define human emotional states  ...  Best multi-label classification results. Top: Mood labels.  ... 
doi:10.1145/2836041.2836051 dblp:conf/mum/Chavez-Martinez15 fatcat:p5kx2utyizhipinzbpnax5mjgq

Audio-Visual Self-Supervised Terrain Type Discovery for Mobile Platforms [article]

Akiyoshi Kurobe, Yoshikatsu Nakajima, Hideo Saito, Kris Kitani
2020 arXiv   pre-print
The terrain cluster labels are then used to train an image-based convolutional neural network to predict changes in terrain types.  ...  from a mic attached to the underside of a mobile platform and image features extracted by a camera on the platform to cluster terrain types.  ...  Qualitative comparison of terrain type predictions. The results of CNN prediction and ground truth label are visualized with blue lines.  ... 
arXiv:2010.06318v1 fatcat:25rhvy3tlncdpbpyc5y4vmuiay

Visual Attention Consistency Under Image Transforms for Multi-Label Image Classification

Hao Guo, Kang Zheng, Xiaochuan Fan, Hongkai Yu, Song Wang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Human visual perception shows good consistency for many multi-label image classification tasks under certain spatial transforms, such as scaling, rotation, flipping and translation.  ...  This new loss is then combined with multi-label image classification loss for network training.  ...  Comparison with state of the arts To verify that our method can achieve state-of-the-art results, we compare multi-label image classification performance of the proposed network with several state-of-the-art  ... 
doi:10.1109/cvpr.2019.00082 dblp:conf/cvpr/0002ZFY019 fatcat:xcq3qzpa6nghhcxfvyckix2ngm

Query2Label: A Simple Transformer Way to Multi-Label Classification [article]

Shilong Liu, Lei Zhang, Xiao Yang, Hang Su, Jun Zhu
2021 arXiv   pre-print
This paper presents a simple and effective approach to solving the multi-label classification problem. The proposed approach leverages Transformer decoders to query the existence of a class label.  ...  We hope its compact structure, simple implementation, and superior performance serve as a strong baseline for multi-label classification tasks and future studies.  ...  Figure 5 : 5 Visualization of multi-head attention maps for the target label person.  ... 
arXiv:2107.10834v1 fatcat:pkt7nsdgyzdvfavcgs5wyah2my

Multi-Label Remote Sensing Image Scene Classification by Combining a Convolutional Neural Network and a Graph Neural Network

Yansheng Li, Ruixian Chen, Yongjun Zhang, Mi Zhang, Ling Chen
2020 Remote Sensing  
As one of the fundamental tasks in remote sensing (RS) image understanding, multi-label remote sensing image scene classification (MLRSSC) is attracting increasing research interest.  ...  However, most of existing methods are limited by only perceiving visual elements but disregarding the spatio-topological relationships of visual elements.  ...  Results on the AID Multi-Label Dataset Table 2 shows the experimental results on the AID multi-label dataset.  ... 
doi:10.3390/rs12234003 fatcat:nv3a55bhcre6xbd6lr2xbw4a7e

Learning Structured Semantic Embeddings for Visual Recognition [article]

Dong Li, Hsin-Ying Lee, Jia-Bin Huang, Shengjin Wang, Ming-Hsuan Yang
2017 arXiv   pre-print
Extensive evaluations demonstrate the effectiveness of the proposed structured embeddings for single-label classification, multi-label classification, and zero-shot recognition.  ...  Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition.  ...  Extensive experimental results show that learning with the two complementary structured constraints signif-icantly improves visual recognition tasks, including singlelabel classification, multi-label classification  ... 
arXiv:1706.01237v1 fatcat:fdsvdt2ijjawpludyjyfjt6ucy

Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation [article]

Yulei Niu, Zhiwu Lu, Ji-Rong Wen, Tao Xiang, Shih-Fu Chang
2018 arXiv   pre-print
Image annotation aims to annotate a given image with a variable number of class labels corresponding to diverse visual concepts.  ...  To address the first issue, we propose a novel multi-scale deep model for extracting rich and discriminative features capable of representing a wide range of visual concepts.  ...  The results of multi-class classification and label quantity prediction are finally merged for image annotation.  ... 
arXiv:1709.01220v2 fatcat:huzz5wivjzccthitux7imzcgpa

Audio-Visual Self-Supervised Terrain Type Recognition for Ground Mobile Platforms

Akiyoshi Kurobe, Yoshikatsu Nakajima, Kris Kitani, Hideo Saito
2021 IEEE Access  
The terrain cluster labels are then used to train an image-based real-time CNN (Convolutional Neural Network) to predict terrain types changes.  ...  from a microphone attached to the underside of a mobile platform and image features extracted by a camera on the platform to cluster terrain types.  ...  FIGURE 7 . 7 Qualitative comparison of terrain type predictions. The results of CNN prediction and ground truth label are visualized with blue lines.  ... 
doi:10.1109/access.2021.3059620 fatcat:rkgokxxk4nesnobhsueoyibxsy

Visual Attention in Multi-Label Image Classification

Yan Luo, Ming Jiang, Qi Zhao
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
One of the most significant challenges in multi-label image classification is the learning of representative features that capture the rich semantic information in a cluttered scene.  ...  In this work, we study the correlation between visual attention and multi-label image classification, and exploit an extra attention pathway for improving multilabel image classification performance.  ...  Acknowledgment This research was funded by the NSF under Grants 1849107 and 1763761, and the University of Minnesota Department of Computer Science and Engineering Start-up Fund (QZ).  ... 
doi:10.1109/cvprw.2019.00110 dblp:conf/cvpr/LuoJZ19 fatcat:75xq6un35vad3dw5o4odosfxaa

Multi-phase liver lesions classification using relevant visual words based on mutual information

Idit Diamant, Jacob Goldberger, Eyal Klang, Michal Amitai, Hayit Greenspan
2015 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI)  
The shift from single-phase liver data to a multi-phase representation is shown to substantially improve classification results.  ...  We present a novel method for automated diagnosis of liver lesions in multi-phase CT images. Our approach is a variant of the Bag-of-Visual-Words (BoVW) method.  ...  Additionally, we investigated the influence of multi versus single phase data. Table 2 shows performance comparison using BoVW-MI between single and multi phase data.  ... 
doi:10.1109/isbi.2015.7163898 dblp:conf/isbi/DiamantGKAG15 fatcat:2nv4pt7d6bdapimbc4l3v4u6fa

Multi-Label Image Classification with Regional Latent Semantic Dependencies [article]

Junjie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu
2017 arXiv   pre-print
Recent state-of-the-art approaches to multi-label image classification exploit the label dependencies in an image, at global level, largely improving the labeling capacity.  ...  Deep convolution neural networks (CNN) have demonstrated advanced performance on single-label image classification, and various progress also have been made to apply CNN methods on multi-label image classification  ...  c is the number of total labels, N c i is the number of images that are accurately labeled for i th label,N p i is the The comparison results between the object bounding box and generated multi-label  ... 
arXiv:1612.01082v3 fatcat:dsvb6xw5lzgejbqhss7fre66zq

Multi-view face pose classification by boosting with weak hypothesis fusion using visual and infrared images

Yixiao Yun, Irene Y.H. Gu
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
The main contribution of this paper is a multi-class AdaBoost classification framework where information obtained from visual and infrared bands interactively complement each other.  ...  Results have shown significant increase in classification rate as compared with an existing multi-class AdaBoost algorithm SAMME trained on visual or infrared images alone, as well as a simple baseline  ...  Results and comparisons: Table 3 and 4 show the classification results from the proposed scheme on the testing set by using visual and thermal IR images as compared with (a) SAMME using visual images  ... 
doi:10.1109/icassp.2012.6288287 dblp:conf/icassp/YunG12 fatcat:kilqx7fyszc4xhjolhgc7ehbk4

ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning [article]

Chaofan Chen, Xiaoshan Yang, Changsheng Xu, Xuhui Huang, Zhe Ma
2021 arXiv   pre-print
We conduct extensive experiments on four few-shot classification benchmarks, and the experimental results show that the proposed ECKPN significantly outperforms the state-of-the-art methods.  ...  Then, we squeeze the instance-level graph to generate the class-level graph, which can help obtain the class-level visual knowledge and facilitate modeling the relations of different classes.  ...  Classification Results We compare the classification results of the proposed ECKPN with the recent state-of-the-art few-shot methods and report the classification results of the 5-way 1-shot and 5-shot  ... 
arXiv:2106.08523v1 fatcat:a57y7vujvve4zn7kanwodyjdem
« Previous Showing results 1 — 15 out of 187,195 results