SlideShare ist ein Scribd-Unternehmen logo
1 von 24
Downloaden Sie, um offline zu lesen
EYE TRACKING
COMPUTER VISION
INFORMATION
RELEVANCE
Can AI say from our eyes
when we read relevant information?
Nilavra Bhattacharya1, Somnath Rakshit1, Jacek Gwizdka1, Paul Kogut2
ACM SIGIR CHIIR 2020 • VANCOUVER VIRTUAL
RELEVANCE PREDICTION
FROM EYE MOVEMENTS
Using Semi-interpretable Convolutional Neural Networks
1 School of Information, The University of Texas at Austin
2 Rotary and Mission Systems, Lockheed Martin Corporation
ixlab.ischool.utexas.edu
INTRODUCTION
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Two Worlds in the Information Field
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Image: Tefko Saracevic (https://studylib.net/doc/15399702)
• Situational relevance or utility:
“situationally relevant items of
information are those that
answer, or logically help to
answer, questions of concern”
(Wilson, 1973)
• This work: situational relevance
= users’ perceived-relevance of
the documents they examine for
answering a question
Image: https://www.noldus.com/applications/eye-tracking-
physiology
Eye-tracking
Background: Eye-tracking & Information Relevance
Introduction User Study Scanpath Image Classification Interpretability Conclusion
• Drawback 1: aggregate ET data at stimulus / trial / participant level
• aggregated fixation counts/durations (Fahey+ 2011; Frey+ 2013; Gwizdka 2014; Loboda+ 2011; Puolamäki+ 2008; Wenzel+ 2017; Wittek+ 2016)
• reading related preprocessing before aggregation (Buscher+ 2008; 2012; Gwizdka, 2014a; 2014b, 2017; Gwizdka+ 2017)
• ET features from 2-second windows near the end of trial has more discriminating power (Gwizdka+ 2017)
=> collapsing ET data leads to loss of information
• Drawback 2: lack of standard feature selection => varied prediction performance; accuracy rarely above 70%
(Simola+ 2008; Slanzi+ 2017; Wenzel+ 2017; Gwizdka+ 2017);
Eye Movement Scanpath 1 Eye Movement Scanpath 2
Similar? Different?
How Much?
Background: Convolutional Neural Networks
Introduction User Study Scanpath Image Classification Interpretability Conclusion
• image classification is a major application of CNNs
• take an input image and predict a label for the image (e.g. “cat” or “dog”?)
• transfer learning: training received by a CNN for solving one task can be re-used to solve another related task
• e.g. training from cat/dog classifier can be re-used to classify traffic symbols
• benchmark CNN models, pre-trained on millions of images for classification tasks (ImageNet challenge) are readily available
• e.g. VGG, ResNet, DenseNet, etc.
Image: https://towardsdatascience.com/covolutional-neural-network-cb0883dd6529
Proposed Approach
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Image: https://dev.to/frosnerd/handwritten-digit-recognition-using-convolutional-neural-networks-11g0
Scanpath - Image CNN Image Classifier
User
Perceived
Relevant?
Prediction
Eye movement
Scanpath
EYE-TRACKING
USER STUDY
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Experimental Design
Introduction User Study Scanpath Image Classification Interpretability Conclusion
• Participants (N = 25, college-age students)
Example Trigger Q: The submarine Kursk was part of which Russian fleet?
Perceived Relevant Perceived Irrelevant
Trigger
Question
TREC 2005
Q&A Task
Spacebar
Relevance
Judgement
(binary)
Y/N then
Spacebar
+
1s
Short News
Article
AQUAINT Corpus
of English News
Text
+
Fixation
>= 2s
GENERATING
SCANPATH-IMAGES
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Generating Scanpath-Images
Introduction User Study Scanpath Image Classification Interpretability Conclusion
SCANPATH - IMAGESCANPATH
Encode three attributes of eye fixations:
1. fixation location
2. fixation duration
3. fixation start time, for temporal ordering
Generating Scanpath-Images: Fixation Duration
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Generating Scanpath-Images: Fixation Start Time
Introduction User Study Scanpath Image Classification Interpretability Conclusion
First
Saccade
Last
Saccade
Matplotlib’s winter colourmap
• each linearized saccade has a solid colour
Saccade Colour
Scanpath-Images
Introduction User Study Scanpath Image Classification Interpretability Conclusion
PERCEIVED RELEVANT PERCEIVED IRRELEVANT
SCANPATH-IMAGE
CLASSIFICATION
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Scanpath-Image Classification
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Given only the scanpath-image of a user’s eye movements on
the news article, predict if the user perceived the article to be
relevant for answering the trigger question.
Image: https://dev.to/frosnerd/handwritten-digit-recognition-using-convolutional-neural-networks-11g0
Scanpath - Image CNN Image Classifier
Perceived
Relevance
Prediction
Scanpath-Image Classification: Neural Network Architecture
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Final hyperparameters:
epochs: 6, batch-size: 16, momentum: 0.9
Shallow(er) models:
VGG16, VGG19
Really Deep Models:
ResNet50
DenseNet121, DenseNet201
InceptionResNetV2
Optimizer: Stochastic Gradient Descent (SGD) with momentum
Pre-trained
CNN model
(ImageNet
Weights)
Fully
Connected
Layer
(256 nodes, ReLU,
with/without L1L2)
Dropout
(prob = 0.2)
Output Layer
(1 node, Sigmoid)
Scanpath-Image Classification: Results
Introduction User Study Scanpath Image Classification Interpretability Conclusion
For this specific task:
• Models do not overfit
• Shallow models classify better than deep models
Shallow
Deep
Table 1 from paper
CNN PREDICTION
INTERPRETABILITY
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Attempt to Interpret CNN Predictions
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Gradient-Weighted Class Activation Mapping (Grad-CAM)
Original Image CAM for “Cat” classCAM for “Dog” class
2017 IEEE International Conference on Computer Vision
Attempt to Interpret CNN Predictions
Introduction User Study Scanpath Image Classification Interpretability Conclusion
SCANPATH CLASS ACTIVATION MAP (CAM) AVERAGE CAM
Across all scanpath-images in this relevance class
Perceived Irrelevant
Perceived Relevant
CONCLUSION
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Conclusion
Limitations:
• very simple information search task
• short texts of similar type
• relatively uniform group of participants (college-age
students)
Future Directions:
• complex scenarios, e.g., freely searching on the open
web
• diverse participants, e.g., young vs. older adults
• Eye-movement scanpath-image
classification:
• no aggregate measures: all eye-tracking data is
used
• spatio-temporal aspects of eye-movements are
preserved
• knowledge of screen content not needed
• additional insights (e.g. reading / scanning) not
needed
• Proof of concept:
• promising results, even with small dataset, without
overfitting
• CNNs trained for a different task can detect
patterns in eye-movements which are concordant
with prior literature
Introduction User Study Scanpath Image Classification Interpretability Conclusion
Acknowledgements
Student Travel Grant
Experimental Design Contribution,
Data Collection
Prof. Bradley Hatfield
Dr. Rodolphe Gentili
Dr. Joe Dien
Hyuk Oh
Kyle James Jaquess
Li-Chuan Lo
Department of Kinesiology,
University of Maryland, College Park
For inspiration:
Blog post on using mouse
trajectories for fraud detection
Gleb Esman
Splunk Inc.
THANK
YOU
@NilavraBnilavra@ieee.org ixlab.ischool.utexas.edu
Full paper:
https://dl.acm.org/doi/10.1145/3343413.3377960
https://arxiv.org/abs/2001.05152

Weitere ähnliche Inhalte

Was ist angesagt?

[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-ResolutionTaegyun Jeon
 
DeepFix: a fully convolutional neural network for predicting human fixations...
DeepFix:  a fully convolutional neural network for predicting human fixations...DeepFix:  a fully convolutional neural network for predicting human fixations...
DeepFix: a fully convolutional neural network for predicting human fixations...Universitat Politècnica de Catalunya
 
Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019
Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019
Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019Universitat Politècnica de Catalunya
 
Parallel wisard object tracker a rambased tracking system
Parallel wisard object tracker a rambased tracking systemParallel wisard object tracker a rambased tracking system
Parallel wisard object tracker a rambased tracking systemcseij
 
Convolutional Neural Network
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural NetworkJunho Cho
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural NetworksPyData
 
Deep Learning Architectures for Video - Xavier Giro - UPC Barcelona 2019
Deep Learning Architectures for Video - Xavier Giro - UPC Barcelona 2019Deep Learning Architectures for Video - Xavier Giro - UPC Barcelona 2019
Deep Learning Architectures for Video - Xavier Giro - UPC Barcelona 2019Universitat Politècnica de Catalunya
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyNUPUR YADAV
 
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020Universitat Politècnica de Catalunya
 
Image Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine LearningImage Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine Learningijtsrd
 
IRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A SurveyIRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A SurveyIRJET Journal
 
Convolutional Neural Networks for Computer vision Applications
Convolutional Neural Networks for Computer vision ApplicationsConvolutional Neural Networks for Computer vision Applications
Convolutional Neural Networks for Computer vision ApplicationsAlex Conway
 
Dario izzo - Machine Learning methods and space engineering
Dario izzo - Machine Learning methods and space engineeringDario izzo - Machine Learning methods and space engineering
Dario izzo - Machine Learning methods and space engineeringAdvanced-Concepts-Team
 
Low complexity features for jpeg steganalysis using undecimated dct
Low complexity features for jpeg steganalysis using undecimated dctLow complexity features for jpeg steganalysis using undecimated dct
Low complexity features for jpeg steganalysis using undecimated dctPvrtechnologies Nellore
 

Was ist angesagt? (20)

[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
 
DeepFix: a fully convolutional neural network for predicting human fixations...
DeepFix:  a fully convolutional neural network for predicting human fixations...DeepFix:  a fully convolutional neural network for predicting human fixations...
DeepFix: a fully convolutional neural network for predicting human fixations...
 
Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019
Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019
Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019
 
Parallel wisard object tracker a rambased tracking system
Parallel wisard object tracker a rambased tracking systemParallel wisard object tracker a rambased tracking system
Parallel wisard object tracker a rambased tracking system
 
Convolutional Neural Network
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural Network
 
Deep Visual Saliency - Kevin McGuinness - UPC Barcelona 2017
Deep Visual Saliency - Kevin McGuinness - UPC Barcelona 2017Deep Visual Saliency - Kevin McGuinness - UPC Barcelona 2017
Deep Visual Saliency - Kevin McGuinness - UPC Barcelona 2017
 
Learning where to look: focus and attention in deep vision
Learning where to look: focus and attention in deep visionLearning where to look: focus and attention in deep vision
Learning where to look: focus and attention in deep vision
 
Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)
Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)
Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
 
Deep Learning Architectures for Video - Xavier Giro - UPC Barcelona 2019
Deep Learning Architectures for Video - Xavier Giro - UPC Barcelona 2019Deep Learning Architectures for Video - Xavier Giro - UPC Barcelona 2019
Deep Learning Architectures for Video - Xavier Giro - UPC Barcelona 2019
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
 
Medical Imaging at DCU - Kevin McGuinness - UPC Barcelona 2018
Medical Imaging at DCU - Kevin McGuinness - UPC Barcelona 2018Medical Imaging at DCU - Kevin McGuinness - UPC Barcelona 2018
Medical Imaging at DCU - Kevin McGuinness - UPC Barcelona 2018
 
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
 
Image Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine LearningImage Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine Learning
 
IRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A SurveyIRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A Survey
 
Intepretability / Explainable AI for Deep Neural Networks
Intepretability / Explainable AI for Deep Neural NetworksIntepretability / Explainable AI for Deep Neural Networks
Intepretability / Explainable AI for Deep Neural Networks
 
Object Detection (D2L5 Insight@DCU Machine Learning Workshop 2017)
Object Detection (D2L5 Insight@DCU Machine Learning Workshop 2017)Object Detection (D2L5 Insight@DCU Machine Learning Workshop 2017)
Object Detection (D2L5 Insight@DCU Machine Learning Workshop 2017)
 
Convolutional Neural Networks for Computer vision Applications
Convolutional Neural Networks for Computer vision ApplicationsConvolutional Neural Networks for Computer vision Applications
Convolutional Neural Networks for Computer vision Applications
 
Dario izzo - Machine Learning methods and space engineering
Dario izzo - Machine Learning methods and space engineeringDario izzo - Machine Learning methods and space engineering
Dario izzo - Machine Learning methods and space engineering
 
Low complexity features for jpeg steganalysis using undecimated dct
Low complexity features for jpeg steganalysis using undecimated dctLow complexity features for jpeg steganalysis using undecimated dct
Low complexity features for jpeg steganalysis using undecimated dct
 

Ähnlich wie Can AI say from our eyes when we read relevant information?

Obscenity Detection in Images
Obscenity Detection in ImagesObscenity Detection in Images
Obscenity Detection in ImagesAnil Kumar Gupta
 
CNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent AdvancesCNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent AdvancesDmytro Mishkin
 
Classification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its VariantsClassification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its VariantsIRJET Journal
 
Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.IRJET Journal
 
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
 
IRJET - Visual Question Answering – Implementation using Keras
IRJET -  	  Visual Question Answering – Implementation using KerasIRJET -  	  Visual Question Answering – Implementation using Keras
IRJET - Visual Question Answering – Implementation using KerasIRJET Journal
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesFellowship at Vodafone FutureLab
 
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019Universitat Politècnica de Catalunya
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術CHENHuiMei
 
improving Profile detection using Deep Learning
improving Profile detection using Deep Learningimproving Profile detection using Deep Learning
improving Profile detection using Deep LearningSahil Kaw
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - Hiroshi Fukui
 
NUMBER PLATE IMAGE DETECTION FOR FAST MOTION VEHICLES USING BLUR KERNEL ESTIM...
NUMBER PLATE IMAGE DETECTION FOR FAST MOTION VEHICLES USING BLUR KERNEL ESTIM...NUMBER PLATE IMAGE DETECTION FOR FAST MOTION VEHICLES USING BLUR KERNEL ESTIM...
NUMBER PLATE IMAGE DETECTION FOR FAST MOTION VEHICLES USING BLUR KERNEL ESTIM...paperpublications3
 
A Survey on Image Processing using CNN in Deep Learning
A Survey on Image Processing using CNN in Deep LearningA Survey on Image Processing using CNN in Deep Learning
A Survey on Image Processing using CNN in Deep LearningIRJET Journal
 
Scene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural NetworkScene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural NetworkDhirajGidde
 
Omni-Modeler: Rapid Adaptive Visual Recognition with Dynamic Learning
Omni-Modeler: Rapid Adaptive Visual Recognition with Dynamic LearningOmni-Modeler: Rapid Adaptive Visual Recognition with Dynamic Learning
Omni-Modeler: Rapid Adaptive Visual Recognition with Dynamic Learningsipij
 
TechnicalBackgroundOverview
TechnicalBackgroundOverviewTechnicalBackgroundOverview
TechnicalBackgroundOverviewMotaz El-Saban
 

Ähnlich wie Can AI say from our eyes when we read relevant information? (20)

Obscenity Detection in Images
Obscenity Detection in ImagesObscenity Detection in Images
Obscenity Detection in Images
 
CNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent AdvancesCNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent Advances
 
Classification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its VariantsClassification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its Variants
 
Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.
 
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
 
IRJET - Visual Question Answering – Implementation using Keras
IRJET -  	  Visual Question Answering – Implementation using KerasIRJET -  	  Visual Question Answering – Implementation using Keras
IRJET - Visual Question Answering – Implementation using Keras
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network Approaches
 
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
 
Mnist report
Mnist reportMnist report
Mnist report
 
IPT.pdf
IPT.pdfIPT.pdf
IPT.pdf
 
Mnist report ppt
Mnist report pptMnist report ppt
Mnist report ppt
 
improving Profile detection using Deep Learning
improving Profile detection using Deep Learningimproving Profile detection using Deep Learning
improving Profile detection using Deep Learning
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
 
NUMBER PLATE IMAGE DETECTION FOR FAST MOTION VEHICLES USING BLUR KERNEL ESTIM...
NUMBER PLATE IMAGE DETECTION FOR FAST MOTION VEHICLES USING BLUR KERNEL ESTIM...NUMBER PLATE IMAGE DETECTION FOR FAST MOTION VEHICLES USING BLUR KERNEL ESTIM...
NUMBER PLATE IMAGE DETECTION FOR FAST MOTION VEHICLES USING BLUR KERNEL ESTIM...
 
The Importance of Time in Visual Attention Models
The Importance of Time in Visual Attention ModelsThe Importance of Time in Visual Attention Models
The Importance of Time in Visual Attention Models
 
A Survey on Image Processing using CNN in Deep Learning
A Survey on Image Processing using CNN in Deep LearningA Survey on Image Processing using CNN in Deep Learning
A Survey on Image Processing using CNN in Deep Learning
 
Scene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural NetworkScene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural Network
 
Omni-Modeler: Rapid Adaptive Visual Recognition with Dynamic Learning
Omni-Modeler: Rapid Adaptive Visual Recognition with Dynamic LearningOmni-Modeler: Rapid Adaptive Visual Recognition with Dynamic Learning
Omni-Modeler: Rapid Adaptive Visual Recognition with Dynamic Learning
 
TechnicalBackgroundOverview
TechnicalBackgroundOverviewTechnicalBackgroundOverview
TechnicalBackgroundOverview
 

Kürzlich hochgeladen

(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...Scintica Instrumentation
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learninglevieagacer
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learninglevieagacer
 
Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Silpa
 
Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Silpa
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusNazaninKarimi6
 
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxPSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxSuji236384
 
Genetics and epigenetics of ADHD and comorbid conditions
Genetics and epigenetics of ADHD and comorbid conditionsGenetics and epigenetics of ADHD and comorbid conditions
Genetics and epigenetics of ADHD and comorbid conditionsbassianu17
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxseri bangash
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsSérgio Sacani
 
GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body Areesha Ahmad
 
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRingsTransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRingsSérgio Sacani
 
Chemistry 5th semester paper 1st Notes.pdf
Chemistry 5th semester paper 1st Notes.pdfChemistry 5th semester paper 1st Notes.pdf
Chemistry 5th semester paper 1st Notes.pdfSumit Kumar yadav
 
POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.Silpa
 
Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.Silpa
 
CYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxSilpa
 
Dr. E. Muralinath_ Blood indices_clinical aspects
Dr. E. Muralinath_ Blood indices_clinical  aspectsDr. E. Muralinath_ Blood indices_clinical  aspects
Dr. E. Muralinath_ Blood indices_clinical aspectsmuralinath2
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .Poonam Aher Patil
 
LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.Silpa
 

Kürzlich hochgeladen (20)

(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
 
Module for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learningModule for Grade 9 for Asynchronous/Distance learning
Module for Grade 9 for Asynchronous/Distance learning
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learning
 
Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.
 
Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.Proteomics: types, protein profiling steps etc.
Proteomics: types, protein profiling steps etc.
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virus
 
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptxPSYCHOSOCIAL NEEDS. in nursing II sem pptx
PSYCHOSOCIAL NEEDS. in nursing II sem pptx
 
Genetics and epigenetics of ADHD and comorbid conditions
Genetics and epigenetics of ADHD and comorbid conditionsGenetics and epigenetics of ADHD and comorbid conditions
Genetics and epigenetics of ADHD and comorbid conditions
 
The Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptxThe Mariana Trench remarkable geological features on Earth.pptx
The Mariana Trench remarkable geological features on Earth.pptx
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body GBSN - Microbiology (Unit 3)Defense Mechanism of the body
GBSN - Microbiology (Unit 3)Defense Mechanism of the body
 
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRingsTransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
TransientOffsetin14CAftertheCarringtonEventRecordedbyPolarTreeRings
 
Chemistry 5th semester paper 1st Notes.pdf
Chemistry 5th semester paper 1st Notes.pdfChemistry 5th semester paper 1st Notes.pdf
Chemistry 5th semester paper 1st Notes.pdf
 
POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.
 
Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.
 
CYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptx
 
Dr. E. Muralinath_ Blood indices_clinical aspects
Dr. E. Muralinath_ Blood indices_clinical  aspectsDr. E. Muralinath_ Blood indices_clinical  aspects
Dr. E. Muralinath_ Blood indices_clinical aspects
 
Site Acceptance Test .
Site Acceptance Test                    .Site Acceptance Test                    .
Site Acceptance Test .
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .
 
LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.LUNULARIA -features, morphology, anatomy ,reproduction etc.
LUNULARIA -features, morphology, anatomy ,reproduction etc.
 

Can AI say from our eyes when we read relevant information?

  • 1. EYE TRACKING COMPUTER VISION INFORMATION RELEVANCE Can AI say from our eyes when we read relevant information?
  • 2. Nilavra Bhattacharya1, Somnath Rakshit1, Jacek Gwizdka1, Paul Kogut2 ACM SIGIR CHIIR 2020 • VANCOUVER VIRTUAL RELEVANCE PREDICTION FROM EYE MOVEMENTS Using Semi-interpretable Convolutional Neural Networks 1 School of Information, The University of Texas at Austin 2 Rotary and Mission Systems, Lockheed Martin Corporation ixlab.ischool.utexas.edu
  • 3. INTRODUCTION Introduction User Study Scanpath Image Classification Interpretability Conclusion
  • 4. Two Worlds in the Information Field Introduction User Study Scanpath Image Classification Interpretability Conclusion Image: Tefko Saracevic (https://studylib.net/doc/15399702) • Situational relevance or utility: “situationally relevant items of information are those that answer, or logically help to answer, questions of concern” (Wilson, 1973) • This work: situational relevance = users’ perceived-relevance of the documents they examine for answering a question Image: https://www.noldus.com/applications/eye-tracking- physiology Eye-tracking
  • 5. Background: Eye-tracking & Information Relevance Introduction User Study Scanpath Image Classification Interpretability Conclusion • Drawback 1: aggregate ET data at stimulus / trial / participant level • aggregated fixation counts/durations (Fahey+ 2011; Frey+ 2013; Gwizdka 2014; Loboda+ 2011; Puolamäki+ 2008; Wenzel+ 2017; Wittek+ 2016) • reading related preprocessing before aggregation (Buscher+ 2008; 2012; Gwizdka, 2014a; 2014b, 2017; Gwizdka+ 2017) • ET features from 2-second windows near the end of trial has more discriminating power (Gwizdka+ 2017) => collapsing ET data leads to loss of information • Drawback 2: lack of standard feature selection => varied prediction performance; accuracy rarely above 70% (Simola+ 2008; Slanzi+ 2017; Wenzel+ 2017; Gwizdka+ 2017); Eye Movement Scanpath 1 Eye Movement Scanpath 2 Similar? Different? How Much?
  • 6. Background: Convolutional Neural Networks Introduction User Study Scanpath Image Classification Interpretability Conclusion • image classification is a major application of CNNs • take an input image and predict a label for the image (e.g. “cat” or “dog”?) • transfer learning: training received by a CNN for solving one task can be re-used to solve another related task • e.g. training from cat/dog classifier can be re-used to classify traffic symbols • benchmark CNN models, pre-trained on millions of images for classification tasks (ImageNet challenge) are readily available • e.g. VGG, ResNet, DenseNet, etc. Image: https://towardsdatascience.com/covolutional-neural-network-cb0883dd6529
  • 7. Proposed Approach Introduction User Study Scanpath Image Classification Interpretability Conclusion Image: https://dev.to/frosnerd/handwritten-digit-recognition-using-convolutional-neural-networks-11g0 Scanpath - Image CNN Image Classifier User Perceived Relevant? Prediction Eye movement Scanpath
  • 8. EYE-TRACKING USER STUDY Introduction User Study Scanpath Image Classification Interpretability Conclusion
  • 9. Experimental Design Introduction User Study Scanpath Image Classification Interpretability Conclusion • Participants (N = 25, college-age students) Example Trigger Q: The submarine Kursk was part of which Russian fleet? Perceived Relevant Perceived Irrelevant Trigger Question TREC 2005 Q&A Task Spacebar Relevance Judgement (binary) Y/N then Spacebar + 1s Short News Article AQUAINT Corpus of English News Text + Fixation >= 2s
  • 10. GENERATING SCANPATH-IMAGES Introduction User Study Scanpath Image Classification Interpretability Conclusion
  • 11. Generating Scanpath-Images Introduction User Study Scanpath Image Classification Interpretability Conclusion SCANPATH - IMAGESCANPATH Encode three attributes of eye fixations: 1. fixation location 2. fixation duration 3. fixation start time, for temporal ordering
  • 12. Generating Scanpath-Images: Fixation Duration Introduction User Study Scanpath Image Classification Interpretability Conclusion
  • 13. Generating Scanpath-Images: Fixation Start Time Introduction User Study Scanpath Image Classification Interpretability Conclusion First Saccade Last Saccade Matplotlib’s winter colourmap • each linearized saccade has a solid colour Saccade Colour
  • 14. Scanpath-Images Introduction User Study Scanpath Image Classification Interpretability Conclusion PERCEIVED RELEVANT PERCEIVED IRRELEVANT
  • 15. SCANPATH-IMAGE CLASSIFICATION Introduction User Study Scanpath Image Classification Interpretability Conclusion
  • 16. Scanpath-Image Classification Introduction User Study Scanpath Image Classification Interpretability Conclusion Given only the scanpath-image of a user’s eye movements on the news article, predict if the user perceived the article to be relevant for answering the trigger question. Image: https://dev.to/frosnerd/handwritten-digit-recognition-using-convolutional-neural-networks-11g0 Scanpath - Image CNN Image Classifier Perceived Relevance Prediction
  • 17. Scanpath-Image Classification: Neural Network Architecture Introduction User Study Scanpath Image Classification Interpretability Conclusion Final hyperparameters: epochs: 6, batch-size: 16, momentum: 0.9 Shallow(er) models: VGG16, VGG19 Really Deep Models: ResNet50 DenseNet121, DenseNet201 InceptionResNetV2 Optimizer: Stochastic Gradient Descent (SGD) with momentum Pre-trained CNN model (ImageNet Weights) Fully Connected Layer (256 nodes, ReLU, with/without L1L2) Dropout (prob = 0.2) Output Layer (1 node, Sigmoid)
  • 18. Scanpath-Image Classification: Results Introduction User Study Scanpath Image Classification Interpretability Conclusion For this specific task: • Models do not overfit • Shallow models classify better than deep models Shallow Deep Table 1 from paper
  • 19. CNN PREDICTION INTERPRETABILITY Introduction User Study Scanpath Image Classification Interpretability Conclusion
  • 20. Attempt to Interpret CNN Predictions Introduction User Study Scanpath Image Classification Interpretability Conclusion Gradient-Weighted Class Activation Mapping (Grad-CAM) Original Image CAM for “Cat” classCAM for “Dog” class 2017 IEEE International Conference on Computer Vision
  • 21. Attempt to Interpret CNN Predictions Introduction User Study Scanpath Image Classification Interpretability Conclusion SCANPATH CLASS ACTIVATION MAP (CAM) AVERAGE CAM Across all scanpath-images in this relevance class Perceived Irrelevant Perceived Relevant
  • 22. CONCLUSION Introduction User Study Scanpath Image Classification Interpretability Conclusion
  • 23. Conclusion Limitations: • very simple information search task • short texts of similar type • relatively uniform group of participants (college-age students) Future Directions: • complex scenarios, e.g., freely searching on the open web • diverse participants, e.g., young vs. older adults • Eye-movement scanpath-image classification: • no aggregate measures: all eye-tracking data is used • spatio-temporal aspects of eye-movements are preserved • knowledge of screen content not needed • additional insights (e.g. reading / scanning) not needed • Proof of concept: • promising results, even with small dataset, without overfitting • CNNs trained for a different task can detect patterns in eye-movements which are concordant with prior literature Introduction User Study Scanpath Image Classification Interpretability Conclusion
  • 24. Acknowledgements Student Travel Grant Experimental Design Contribution, Data Collection Prof. Bradley Hatfield Dr. Rodolphe Gentili Dr. Joe Dien Hyuk Oh Kyle James Jaquess Li-Chuan Lo Department of Kinesiology, University of Maryland, College Park For inspiration: Blog post on using mouse trajectories for fraud detection Gleb Esman Splunk Inc. THANK YOU @NilavraBnilavra@ieee.org ixlab.ischool.utexas.edu Full paper: https://dl.acm.org/doi/10.1145/3343413.3377960 https://arxiv.org/abs/2001.05152