Filters








646,799 Hits in 6.4 sec

Image semantics in the description and categorization of journalistic photographs

Mari Laine-Hernandez, Stina Westman
2007 Proceedings of the American Society for Information Science and Technology  
The effect of different tasks on image description and categorization was also studied.  ...  The aim of the study was to evaluate existing indexing frameworks in the context of reportage photographs and to find out how the use of this particular image genre influences the results.  ...  Acknowledgements The authors wish to acknowledge the support of The National Technology Agency of Finland for this research project.  ... 
doi:10.1002/meet.1450430148 fatcat:kgojqhz4qnbt3lvlbr3po6uflm

Reasoning about Fine-grained Attribute Phrases using Reference Games [article]

Jong-Chyi Su, Chenyun Wu, Huaizu Jiang, Subhransu Maji
2017 arXiv   pre-print
The goal of a speaker is to describe attributes of an image that allows the listener to correctly identify it within a pair.  ...  We then learn to describe and ground these phrases to images in the context of a *reference game* between a speaker and a listener.  ...  Acknowledgement: This research was supported in part by the NSF grants 1617917 and 1661259, and a faculty gift from Facebook.  ... 
arXiv:1708.08874v1 fatcat:dlxudfbeqnadzai3bjtxiz4pnm

Lesion Analysis and Diagnosis with Mask-RCNN [article]

Andrey Sorokin
2018 arXiv   pre-print
This project applies Mask R-CNN method to ISIC 2018 challenge tasks: lesion boundary segmentation (task1), lesion attributes detection (task 2), lesion diagnosis (task 3), a solution to the latter is using  ...  a trained model for task 1 and a simple voting procedure.  ...  Task 3: Disease Classification Hybrid approach For this task, a set of lesion images and a CSV file describing disease type is provided for training.  ... 
arXiv:1807.05979v2 fatcat:5m5mtullcndipbkvwayc4wtt54

An ordering of secondary task display attributes

David Tessendorf, C. M. Chewar, Ali Ndiwalana, Jon Pryor, D. Scott McCrickard, Chris North
2002 CHI '02 extended abstracts on Human factors in computing systems - CHI '02  
Secondary task attribute ordering varies with the level of degradation in the primary task.  ...  This paper describes an experiment that determines a new ordering guideline for secondary task image attributes according to human cognitive ability to extract information.  ...  They recognize visual data as elementary perceptual tasks, described as graph attributes, some of which convey information better than others.  ... 
doi:10.1145/506443.506503 dblp:conf/chi/TessendorfCNPMN02 fatcat:5ubtzcx4lbestfbkqg44xvnmyu

An ordering of secondary task display attributes

David Tessendorf, C. M. Chewar, Ali Ndiwalana, Jon Pryor, D. Scott McCrickard, Chris North
2002 CHI '02 extended abstracts on Human factors in computer systems - CHI '02  
Secondary task attribute ordering varies with the level of degradation in the primary task.  ...  This paper describes an experiment that determines a new ordering guideline for secondary task image attributes according to human cognitive ability to extract information.  ...  They recognize visual data as elementary perceptual tasks, described as graph attributes, some of which convey information better than others.  ... 
doi:10.1145/506486.506503 fatcat:mg66cwkylzdfngcu6fzcflswxa

Feature Level Fusion from Facial Attributes for Face Recognition [article]

Mohammad Rasool Izadi
2021 arXiv   pre-print
In this method, we use facial attributes as an auxiliary source of information to assist CNN features extracted from the face images to improve the face recognition performance.  ...  Specifically, we use a shared CNN architecture that jointly predicts facial attributes and recognize face images simultaneously via a shared learning parameters, and then we use facial attribute features  ...  We select 60 identity facial attributes out of 73 attributes describing people without concerning if these attributes change in different images Figure 1 . 1 shows Face Recognition (FRTL) and Attribute  ... 
arXiv:1909.13126v2 fatcat:avbyxyrrb5bcvdqnyzwupsbt7a

How Do We Talk About Other People? Group (Un)Fairness in Natural Language Image Descriptions

Jahna Otterbacher, Pinar Barlas, Styliani Kleanthous, Kyriakos Kyriakou
2019 Zenodo  
Yet such elicitation tasks are susceptible to human biases, including stereotyping people depicted in images.  ...  We conduct experiments at Figure Eight using a controlled set of people images. Men and women of various races are positioned in the same manner, wearing a grey t-shirt.  ...  the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.  ... 
doi:10.5281/zenodo.3401880 fatcat:teidcff5evclbfiqjnis6qjylq

Swap Retrieval

Amir Ghodrati, Xu Jia, Marco Pedersoli, Tinne Tuytelaars
2015 Proceedings of the 5th ACM on International Conference on Multimedia Retrieval - ICMR '15  
For instance, starting from an image of a dog in a certain situation/context, the goal is to find images of cats with a similar situation/context.  ...  Query-by-example remains popular in image retrieval because it can exploit contextual information encoded in the image, that is difficult to express in a traditional textual query.  ...  effective tool to describe different aspects of an image.  ... 
doi:10.1145/2671188.2749373 dblp:conf/mir/GhodratiJPT15 fatcat:6lj7bicgyvaxbj6b726vwusg2u

Describing Textures using Natural Language [article]

Chenyun Wu, Mikayla Timm, Subhransu Maji
2020 arXiv   pre-print
Textures in natural images can be characterized by color, shape, periodicity of elements within them, and other attributes that can be described using natural language.  ...  In this paper, we study the problem of describing visual attributes of texture on a novel dataset containing rich descriptions of textures, and conduct a systematic study of current generative and discriminative  ...  The project is supported in part by NSF grants #1749833 and #1617917. Our experiments were performed in the UMass GPU cluster obtained under the Collaborative Fund managed by the Mass.  ... 
arXiv:2008.01180v1 fatcat:mod3tmfajrhcplfm4vwzuefaqe

Dual Purpose Hashing [article]

Haomiao Liu, Ruiping Wang, Shiguang Shan, Xilin Chen
2016 arXiv   pre-print
Recent years have seen more and more demand for a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes.  ...  With such a framework, the binary codes of new-coming images can be readily obtained by quantizing the network outputs of a binary-like layer, and the attributes can be recovered from the codes easily.  ...  Evaluation of Attribute Retrieval In this subsection, we test the effectiveness of our DPH method on the second task described in Section 1.  ... 
arXiv:1607.05529v1 fatcat:jyy3ggcnjnd65pbamrcpxm7hlq

A Deep Face Identification Network Enhanced by Facial Attributes Prediction [article]

Fariborz Taherkhani, Nasser M. Nasrabadi, Jeremy Dawson
2018 arXiv   pre-print
Contrary to the existing multi-task methods which only use a shared CNN feature space to train these two tasks jointly, we fuse the predicted attributes with the features from the face modality in order  ...  Experimental results show that our model brings benefits to both face identification as well as facial attribute prediction performance, especially in the case of identity facial attributes such as gender  ...  The rest of this paper is organized as follows: The CNN architecture is described in section 2, fusion of attribute and face modalities is described in section 3, model training parameters are described  ... 
arXiv:1805.00324v1 fatcat:dd4c64zjczfflj6uhal5tf7qe4

Scene Recognition with Objectness, Attribute and Category Learning [article]

Ji Zhang, Jean-Paul Ainam, Li-hui Zhao, Wenai Song, Xin Wang
2022 arXiv   pre-print
Compared to images of individual objects, scene images could be much more semantically complex and abstract. Their difference mainly lies in the level of granularity of recognition.  ...  Based on the complementarity of attribute and category labels, we propose a Multi-task Attribute-Scene Recognition (MASR) network which learns a category embedding and at the same time predicts scene attributes  ...  It is useful in solving specific image retrieval problems, in which the query image is missing and can be described by attributes.  ... 
arXiv:2207.10174v1 fatcat:ejodtwsq2ja65o5atw2uacxh5y

An Exploration of Needs for Connotative Messages during Image Search Process

JungWon Yoon
2007 Proceedings of the American Society for Information Science and Technology  
For this purpose, this study attempted to investigate and compare three stages of the image search process in terms of use of image attributes.  ...  The three stages of the image search process are identified as initiation, representation and selection, and image attribute levels are defined as color, denotative, and connotative attributes.  ...  Jörgensen (1995) categorized image attributes into twelve classes, and then compared the usage of classes in three different tasks: 1) In describing tasks, participants wrote descriptions of six images  ... 
doi:10.1002/meet.14504301102 fatcat:hgkf3ntjffgijmhinugy4e4jgm

Towards Building Large Scale Multimodal Domain-Aware Conversation Systems

Amrita Saha, Mitesh Khapra, Karthik Sankaranarayanan
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We also propose two multimodal neural models in the encode-attend-decode paradigm and demonstrate their performance on two of the sub-tasks, namely text response generation and best image response selection  ...  To overcome this bottleneck, in this paper we introduce the task of multimodal, domain-aware conversations, and propose the MMD benchmark dataset.  ...  We describe each of these tasks and explain the technical challenges involved: 1. Text Response: Given a context of k turns the task here is to generate the next text response. 2.  ... 
doi:10.1609/aaai.v32i1.11331 fatcat:tpdlptn44zem3iuk5sebnzdtz4

Task-based assessment of binned and list-mode SPECT systems [article]

Md Ashequr Rahman, Abhinav K. Jha
2021 arXiv   pre-print
task of absolute quantification of region-of-interest (ROI) uptake in comparison to processing the data in binned format.  ...  An ordered-subset expectation-maximization algorithm was used to reconstruct images from data acquired in LM format, including the scatter-window data, and including the energy attribute of each LM event  ...  These SPECT images were acquired using a 2D acquisition protocol, as described in more detail in the next section.  ... 
arXiv:2102.03971v2 fatcat:cufolmq66rfhhnv6hnmrlkborm
« Previous Showing results 1 — 15 out of 646,799 results