6,231 Hits in 4.8 sec

Pedestrian Detection by Exemplar-Guided Contrastive Learning [article]

Zebin Lin, Wenjie Pei, Fanglin Chen, David Zhang, Guangming Lu
2021 arXiv   pre-print
training pairs and thus guide contrastive learning.  ...  dictionary.  ...  dictionary, we compare the performance of contrastive learning using and not using the exemplar dictionary for constructing the training pairs.  ... 
arXiv:2111.08974v2 fatcat:bf7odgui5zcwlo2epttuvyntr4

Convolutional Neural Networks for Multimedia Sentiment Analysis [chapter]

Guoyong Cai, Binbin Xia
2015 Lecture Notes in Computer Science  
Two individual CNN architectures are used for learning textual features and visual features, which can be combined as input of another CNN architecture for exploiting the internal relation between text  ...  Motivated by this rationale, we propose a method based on convolutional neural networks (CNN) for multimedia (tweets consist of text and image) sentiment analysis.  ...  Dictionary based method for sentiment analysis usually depends on the pre-defined sentiment dictionaries.  ... 
doi:10.1007/978-3-319-25207-0_14 fatcat:qtim3nkrmnegpjzsxl273ligie

Unsupervised Feature Learning by Deep Sparse Coding [chapter]

Yunlong He, Koray Kavukcuoglu, Yun Wang, Arthur Szlam, Yanjun Qi
2014 Proceedings of the 2014 SIAM International Conference on Data Mining  
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks  ...  As a result, the new method is able to learn multiple layers of sparse representations of the image which capture features at a variety of abstraction levels and simultaneously preserve the spatial smoothness  ...  Recent progress in deep learning [2] has shown that the multi-layer architecture of deep learning system, such as that of deep belief networks, is helpful for learning feature hierarchies from data,  ... 
doi:10.1137/1.9781611973440.103 dblp:conf/sdm/HeKWSQ14 fatcat:5m5tbo5tkbc77du4vw3z3p2olu

Unsupervised Feature Learning by Deep Sparse Coding [article]

Yunlong He, Koray Kavukcuoglu, Yun Wang, Arthur Szlam, Yanjun Qi
2013 arXiv   pre-print
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks  ...  The main innovation of the framework is that it connects the sparse-encoders from different layers by a sparse-to-dense module.  ...  For the LLC method proposed from [16] , it reported to achieve 73.44% for Caltech-101 when using K = 2048 and 47.68% when using K = 4096.  ... 
arXiv:1312.5783v1 fatcat:gv4ptwdh4fccdezwq42quuk5h4

Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning [article]

Zhicheng Huang, Zhaoyang Zeng, Yupan Huang, Bei Liu, Dongmei Fu, Jianlong Fu
2021 arXiv   pre-print
We study joint learning of Convolutional Neural Network (CNN) and Transformer for vision-language pre-training (VLPT) which aims to learn cross-modal alignments from millions of image-text pairs.  ...  In particular, SOHO learns to extract comprehensive yet compact image features through a visual dictionary (VD) that facilitates cross-modal understanding.  ...  We model VQA as a classification problem by learning multi-layer perception from the [CLS] token.  ... 
arXiv:2104.03135v2 fatcat:ipergnpirzhblnwg2epmptmasa

Unsupervised Feature Learning for Dense Correspondences across Scenes [article]

Chao Zhang, Chunhua Shen, Tingzhi Shen
2015 arXiv   pre-print
The learned features are then seamlessly embedded into a multi-layer match- ing framework.  ...  Pixel-layer features are obtained by encoding over the dictionary, followed by spatial pooling to obtain patch-layer features.  ...  Our multi-layer matching model, designed for fast and accurate matching, is suitable for the multi-layer unsupervised feature learning pipeline.  ... 
arXiv:1501.00642v2 fatcat:tmrxi23wpvblxfyofpxyhlccoe

Sentiment Analysis for Social Media

Carlos A. Iglesias, Antonio Moreno
2019 Applied Sciences  
The field has reached a level of maturity that paves the way for its exploitation in many different fields such as marketing, health, banking or politics.  ...  The latest technological advancements, such as deep learning techniques, have solved some of the traditional challenges in the area caused by the scarcity of lexical resources.  ...  Acknowledgments: The Guest Editors would like to thank all the authors that have participated in this Special Issue and also the reference contact in MDPI, Nyssa Yuan, for all the support and work dedicated  ... 
doi:10.3390/app9235037 fatcat:jg4fgxwnqneuhohyuwxmjndzsu

Progressive Dictionary Learning With Hierarchical Predictive Structure for Low Bit-Rate Scalable Video Coding

Wenrui Dai, Yangmei Shen, Hongkai Xiong, Xiaoqian Jiang, Junni Zou, David Taubman
2017 IEEE Transactions on Image Processing  
This paper proposes a progressive dictionary learning framework with hierarchical predictive structure for scalable video coding, especially in low bitrate region.  ...  For pyramidal layers, sparse representation based on spatio-temporal dictionary is adopted to improve the coding efficiency of enhancement layers with a guarantee of reconstruction performance.  ...  Spatio-temporal dictionary learning for inter-layer prediction. 2-D sub-dictionary and 3-D dictionary pairs are trained for the base and enhancement layer.  ... 
doi:10.1109/tip.2017.2692882 pmid:28422683 pmcid:PMC5638692 fatcat:yrf6mgcpojezvjhmiuvmvqklne

A Transfer Model Based on Supervised Multi-Layer Dictionary Learning for Brain Tumor MRI Image Recognition

Yi Gu, Kang Li
2021 Frontiers in Neuroscience  
To solve this problem, we propose a transfer model based on supervised multi-layer dictionary learning (TSMDL) for brain tumor MRI image recognition in this paper.  ...  Based on the framework of multi-layer dictionary learning, the proposed model learns the common shared dictionary of source and target domains in each layer to explore the intrinsic connections and shared  ...  A learning method combining discriminate sub-dictionary and projective dictionary pair learning was developed for classifying proton magnetic resonance spectroscopy of brain gliomas tumor (Adebileje et  ... 
doi:10.3389/fnins.2021.687496 pmid:34122003 pmcid:PMC8193061 fatcat:z3njbccagnc4nhzfca3glljpsa

A comprehensive study on mid-level representation and ensemble learning for emotional analysis of video material

Esra Acar, Frank Hopfgartner, Sahin Albayrak
2016 Multimedia tools and applications  
support vector machines (SVMs) for video affective content analysis.  ...  More specifically, audio and static visual representations are automatically learned from raw data using convolutional neural networks (CNNs).  ...  We learn a separate dictionary for each dense trajectory descriptor (i.e., each one of HoG, HoF, MBHx and MBHy). We employ the sparse dictionary learning technique presented in [26] .  ... 
doi:10.1007/s11042-016-3618-5 fatcat:6675o5rxefcavkr2vo6nq4zote

Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks [article]

Li Wang, Ting Liu, Bing Wang, Xulei Yang, Gang Wang
2018 arXiv   pre-print
In addition, we online update two dictionaries to handle appearance changes of target objects.  ...  In this paper, we propose to learn hierarchical features for visual object tracking by using tree structure based Recursive Neural Networks (RNN), which have fewer parameters than other deep neural networks  ...  In addition, we online update two dictionaries every 5 frames.  ... 
arXiv:1801.02021v1 fatcat:7dsoje5c2rdfbcjkg2qtd7fove

Breast image feature learning with adaptive deconvolutional networks

Andrew R. Jamieson, Karen Drukker, Maryellen L. Giger, Bram van Ginneken, Carol L. Novak
2012 Medical Imaging 2012: Computer-Aided Diagnosis  
We trained the ADNs to learn multiple layers of representation for two breast image data sets on two different modalities (739 full field digital mammography (FFDM) and 2393 ultrasound images).  ...  the task of binary classification between cancer and non-cancer breast mass lesions.  ...  The authors are grateful to Matthew Zeiler and Migeul Carreira-Perpiñán for making their useful code available online.  ... 
doi:10.1117/12.910710 dblp:conf/micad/JamiesonDG12 fatcat:25h5a4zfe5dizlnrdse4vfgyua

Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations [article]

Josh Beal, Hao-Yu Wu, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk
2021 arXiv   pre-print
to general representation learning for all visual content (e.g. embeddings for retrieval).  ...  We consider the case of a popular visual discovery product, where these representations are trained with multi-task learning, from use-case specific visual understanding (e.g. skin tone classification)  ...  The authors would like to thank Eric Tzeng, Raymond Shiau, Kofi Boakye, Vahid Kazemi, and Chuck Rosenberg for valuable discussions regarding the paper, and the anonymous reviewers and ACs for their helpful  ... 
arXiv:2108.05887v1 fatcat:gm5lzf4pkrg3zez7unuq7epp3a

Weakly Supervised Visual Dictionary Learning by Harnessing Image Attributes

Yue Gao, Rongrong Ji, Wei Liu, Qionghai Dai, Gang Hua
2014 IEEE Transactions on Image Processing  
Index Terms-Bag-of-features, visual dictionary, image attribute, weakly supervised learning, hidden Markov random field, image classification, image search.  ...  While most existing visual dictionary learning approaches are engaged with unsupervised feature quantization, the latest trend has turned to supervised learning by harnessing the semantic labels of images  ...  . • Weakly supervised dictionary learning step learns a visual dictionary by using a constrained local feature clustering.  ... 
doi:10.1109/tip.2014.2364536 pmid:25361504 fatcat:vfuulvkvbvd6pjpn3libbzria4

Medical Concept Normalization for Online User-Generated Texts

Kathy Lee, Sadid A Hasan, Oladimeji Farri, Alok Choudhary, Ankit Agrawal
2017 2017 IEEE International Conference on Healthcare Informatics (ICHI)  
Social media has become an important tool for sharing content in the last decade.  ...  Due to the colloquial nature of the languages used in the social media, it is often difficult for an automated system to accurately interpret them for appropriate clinical understanding.  ...  Second, the normalization task should be cast as a multi-class multi-label classification problem since each phrase can be mapped to multiple concepts (as shown in Tables III and VIII) and each concept  ... 
doi:10.1109/ichi.2017.59 dblp:conf/ichi/LeeHFCA17 fatcat:kzpngm2g5nefjmp63cqw3mcp5i
« Previous Showing results 1 — 15 out of 6,231 results