DEEP LEARNING BASED VISION-TO-LANGUAGE APPLICATIONS: CAPTIONING OF PHOTO STREAMS, VIDEOS, AND ONLINE POSTS
|
|
- Magnus Harrison
- 5 years ago
- Views:
Transcription
1 SEOUL Oct.7, 2016 DEEP LEARNING BASED VISION-TO-LANGUAGE APPLICATIONS: CAPTIONING OF PHOTO STREAMS, VIDEOS, AND ONLINE POSTS Gunhee Kim Computer Science and Engineering Seoul National University October 7, 2016
2 AGENDA Photo stream captioning Video captioning Cesc C. Park and Gunhee Kim. Expressing an Image Stream with a Sequence of Natural Sentences. NIPS
3 GENERAL USERS PHOTO STREAM Suppose that you and your family visit NYC A photo stream is a thread of the user s story Users do not organize the photo streams for later use Can we write a travelogue for a given photo stream? 3 3
4 PREVIOUS WORK IMAGE CAPTIONING Retrieve or generate a descriptive natural language sentence for a given image [Socher et al, TACL2013] [Karpathy et al. CVPR2015 ] [Mao et al, ICLR2015] Many more! [Vinyal et al, CVPR2015] [Gong et al. ECCV2014 ] 4 4
5 LIMITATION OF PREVIOUS WORK Much of previous work mainly discuss the relation between a single image and a single sentence A kid is smiling Absence of correlation, coherence and story for a stream of images Extend both input and output dimension to a sequence of images and a sequence of sentences 5 5
6 PROBLEM STATEMENT Objective: express an image stream to a coherent sequence of sentences A query of image stream A coherent sequence of sentences We took a couple days for family vacation in NYC to get away Empire state building right off the bat. Caeden is checking out the view. Caeden's first MLB game and my first in a while MLB game... He might be a mets fan Shake Shack
7 IMAGE-TEXT PARALLEL TRAINING DATA Use a set of blog posts to learn the relation between a image stream and a sequence of sentences 19K blog posts with 150K images from Blogs are written in a way of storytelling Blog pictures are selected as the most canonical ones out of photo albums Informative sentences associated with pictures about location, sentiments, actors, 7 7
8 OUR SOLUTION CRCN Coherence Recurrent Convolutional Network (1) Convolutional neural networks for image description (2) Bidirectional recurrent neural networks for language model (3) Coherence model for a smooth flow of multi-sentences 8 8
9 OVERVIEW OF ALGORITHM 9 9
10 CRCN ARCHITECTURE The compatibility score btw image and sentence sequence Misaligned Pairs should be few Aligned Pairs should be many 10 10
11 RETRIEVAL SENTENCE SEQUENCES Retrieve best sentence sequences for a query image stream Divide-conquer search strategy! Almost optimal! The local fluency and coherence is required for the global one 11 11
12 USER STUDIES VIA AMT Goal: Find general users preferences between text sequences by different methods for a given photo stream Randomly select 100 test streams of 5 images Our method and one baseline predict text sequences Pairwise preference test via Quantitative results A higher number than 50% validate our approach (CRCN) The coherence becomes more critical as the passage is longer (4th vs 5th columns) 12 12
13 RESULTS FOR NYC DATASET (1) (2) (3) (4) (5) (CRCN) (1) One of the hallway arches inside of the library (2) As we walked through the library I noticed an exhibit called lunch hour nyc it captured my attention as I had also taken a tour of nyc food carts during my trip (3) Here is the top of the Chrysler building everyone's favorite skyscraper in new york. (4) After leaving the nypl we walked along 42nd st. (5) We walked down fifth avenue from rockefeller centre checking out the windows in saks the designer stores and eventually making our way to the impressive new york public library. (RCN) (1) As you walk along in some spots it looks like the buildings are sprouting up out of the high line plants (2) Charlie and his aunt donna relax on the high line after a steamy stroll (3) However navigating the new york subway system can be like trying to find your way through the amazon jungle sans guide (4) We loved nyc! (5) Getting ready for the sunny day...putting sunscreen on
14 AGENDA Photo stream captioning Video captioning 14
15 WON LSMDC 2016! Large Scale Movie Description and Understanding Challenge (LSMDC 2016) in ECCV 2016 and MM Team members: Youngjae Yu, Hyungjin Ko, Jongwook Choi, Gunhee Kim movie description movie multiple-choice movie fill-in-the-blank movie retrieval His vanity license plate reads
16 ATTENTION MECHANISMS IN DEEP LEARNING Machine decides where to attend itself --- sequentially focus or attend on the most relevant part of the input over time. Image captioning [Xu et al. ICML2015] Machine translation [Hermann et al. NIPS2015] K. Xu et al. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. ICML K. M. Hermann et al. Teaching Machines to Read and Comprehend. NIPS
17 ATTENTION MECHANISMS IN DEEP LEARNING Machine decides where to attend itself --- sequentially focus or attend on the most relevant part of the input over time. Action recognition [Sharma et al. Arxiv2015] Golf swinging Trampoline jumping Video captioning [Sharma. Toronto 2016] Generated sentence : A woman is slicing a onion. Groundtruth : A woman is slicing a shrimp. S. Sharma et al. Action Recognition Using Visual Attention. Arxiv U Toronto, S. Sharma. Action recognition and video description using visual attention. MS thesis, 17
18 PROBLEM STATEMENT Although attention models simulate human s attrition, there is no attempt to explicitly use human gaze labels Attention weights are implicitly learned in an end-to-end manner Does human attention improve the model performance? Then how can we inject such supervision to the attention model? Target task: Video captioning 18 18
19 PROBLEM STATEMENT Objective: supervise a caption generation model to attend where human focus on A short movie video stream Movie clip Predicted Human attention A human gaze assisted caption A little boy flies in the air by riding a bicycle
20 RESULTS (CAPTION GENERATION) [1] Subhashini Venugopalan et al. Sequence to Sequence Video to Text. ICCV 2015 [2] Li Yao et al. Describing Videos by Exploiting Temporal Structure. ICCV
21 RESULTS (CAPTION GENERATION) [1] Subhashini Venugopalan et al. Sequence to Sequence Video to Text. ICCV 2015 [2] Li Yao et al. Describing Videos by Exploiting Temporal Structure. ICCV
22 CONCLUSION Joint understanding of multiple data modalities Visual data (images/videos) + Textual data Deep learning models are superior to jointly represent multiple data or tasks In the areas of robotics, VR, security, speech analysis, and more Many possible applications for online services 22 22
23 SEOUL Oct.7, 2016 THANK YOU
Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience.
Outline: Motivation. What s the attention mechanism? Soft attention vs. Hard attention. Attention in Machine translation. Attention in Image captioning. State-of-the-art. 1 Motivation: Attention: Focusing
More informationTranslating Videos to Natural Language Using Deep Recurrent Neural Networks
Translating Videos to Natural Language Using Deep Recurrent Neural Networks Subhashini Venugopalan UT Austin Huijuan Xu UMass. Lowell Jeff Donahue UC Berkeley Marcus Rohrbach UC Berkeley Subhashini Venugopalan
More informationImage Captioning using Reinforcement Learning. Presentation by: Samarth Gupta
Image Captioning using Reinforcement Learning Presentation by: Samarth Gupta 1 Introduction Summary Supervised Models Image captioning as RL problem Actor Critic Architecture Policy Gradient architecture
More informationSequential Predictions Recurrent Neural Networks
CS 2770: Computer Vision Sequential Predictions Recurrent Neural Networks Prof. Adriana Kovashka University of Pittsburgh March 28, 2017 One Motivation: Descriptive Text for Images It was an arresting
More informationRecurrent Neural Networks
CS 2750: Machine Learning Recurrent Neural Networks Prof. Adriana Kovashka University of Pittsburgh March 14, 2017 One Motivation: Descriptive Text for Images It was an arresting face, pointed of chin,
More informationThe University of Tokyo, NVAIL Partner Yoshitaka Ushiku
Recognize, Describe, and Generate: Introduction of Recent Work at MIL The University of Tokyo, NVAIL Partner Yoshitaka Ushiku MIL: Machine Intelligence Laboratory Beyond Human Intelligence Based on Cyber-Physical
More informationAction Recognition. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem
Action Recognition Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem This section: advanced topics Convolutional neural networks in vision Action recognition Vision and Language 3D
More informationAudiovisual to Sign Language Translator
Technical Disclosure Commons Defensive Publications Series July 17, 2018 Audiovisual to Sign Language Translator Manikandan Gopalakrishnan Follow this and additional works at: https://www.tdcommons.org/dpubs_series
More informationVision, Language, Reasoning
CS 2770: Computer Vision Vision, Language, Reasoning Prof. Adriana Kovashka University of Pittsburgh March 5, 2019 Plan for this lecture Image captioning Tool: Recurrent neural networks Captioning for
More informationPractical Bayesian Optimization of Machine Learning Algorithms. Jasper Snoek, Ryan Adams, Hugo LaRochelle NIPS 2012
Practical Bayesian Optimization of Machine Learning Algorithms Jasper Snoek, Ryan Adams, Hugo LaRochelle NIPS 2012 ... (Gaussian Processes) are inadequate for doing speech and vision. I still think they're
More informationInteract-AS. Use handwriting, typing and/or speech input. The most recently spoken phrase is shown in the top box
Interact-AS One of the Many Communications Products from Auditory Sciences Use handwriting, typing and/or speech input The most recently spoken phrase is shown in the top box Use the Control Box to Turn
More informationCSC2541 Project Paper: Mood-based Image to Music Synthesis
CSC2541 Project Paper: Mood-based Image to Music Synthesis Mary Elaine Malit Department of Computer Science University of Toronto elainemalit@cs.toronto.edu Jun Shu Song Department of Computer Science
More informationB657: Final Project Report Holistically-Nested Edge Detection
B657: Final roject Report Holistically-Nested Edge Detection Mingze Xu & Hanfei Mei May 4, 2016 Abstract Holistically-Nested Edge Detection (HED), which is a novel edge detection method based on fully
More informationDeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation
DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation Biyi Fang Michigan State University ACM SenSys 17 Nov 6 th, 2017 Biyi Fang (MSU) Jillian Co (MSU) Mi Zhang
More informationarxiv: v1 [stat.ml] 23 Jan 2017
Learning what to look in chest X-rays with a recurrent visual attention model arxiv:1701.06452v1 [stat.ml] 23 Jan 2017 Petros-Pavlos Ypsilantis Department of Biomedical Engineering King s College London
More informationAutomatic Context-Aware Image Captioning
Technical Disclosure Commons Defensive Publications Series May 23, 2017 Automatic Context-Aware Image Captioning Sandro Feuz Sebastian Millius Follow this and additional works at: http://www.tdcommons.org/dpubs_series
More informationName Period Date. Grade 7, Unit 4 Pre-assessment
Name Period Date Grade 7, Unit 4 Pre-assessment A Letter from New York by Jean Lawler Dear Aunt Julia, I have so much to tell you, I don t know where to begin! Remember last summer when I told you that
More informationAccessible Computing Research for Users who are Deaf and Hard of Hearing (DHH)
Accessible Computing Research for Users who are Deaf and Hard of Hearing (DHH) Matt Huenerfauth Raja Kushalnagar Rochester Institute of Technology DHH Auditory Issues Links Accents/Intonation Listening
More informationPutting Context into. Vision. September 15, Derek Hoiem
Putting Context into Vision Derek Hoiem September 15, 2004 Questions to Answer What is context? How is context used in human vision? How is context currently used in computer vision? Conclusions Context
More informationEfficient Deep Model Selection
Efficient Deep Model Selection Jose Alvarez Researcher Data61, CSIRO, Australia GTC, May 9 th 2017 www.josemalvarez.net conv1 conv2 conv3 conv4 conv5 conv6 conv7 conv8 softmax prediction???????? Num Classes
More informationShu Kong. Department of Computer Science, UC Irvine
Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with
More informationNE LESSON GD Fit Families: Effortless Exercise
NE LESSON GD-000-06 Fit Families: Effortless Exercise LESSON DESCRIPTION In this video and activity lesson, class participants will learn strategies for incorporating physical activity into their daily
More informationRESOURCE CATALOGUE. I Can Sign A Rainbow
RESOURCE CATALOGUE I Can Sign A Rainbow Catalogue # 100 I Can Sign a Rainbow is a 2 disc set (DVD and CD-ROM) designed for pre-schoolers and their families who use New Zealand Sign Language or spoken English.
More informationVideo Saliency Detection via Dynamic Consistent Spatio- Temporal Attention Modelling
AAAI -13 July 16, 2013 Video Saliency Detection via Dynamic Consistent Spatio- Temporal Attention Modelling Sheng-hua ZHONG 1, Yan LIU 1, Feifei REN 1,2, Jinghuan ZHANG 2, Tongwei REN 3 1 Department of
More informationGesture Recognition using Marathi/Hindi Alphabet
Gesture Recognition using Marathi/Hindi Alphabet Rahul Dobale ¹, Rakshit Fulzele², Shruti Girolla 3, Seoutaj Singh 4 Student, Computer Engineering, D.Y. Patil School of Engineering, Pune, India 1 Student,
More informationDeep Learning for Computer Vision
Deep Learning for Computer Vision Lecture 12: Time Sequence Data, Recurrent Neural Networks (RNNs), Long Short-Term Memories (s), and Image Captioning Peter Belhumeur Computer Science Columbia University
More informationCAPL 2 Questionnaire
CAPL 2 Questionnaire What Do You Think About Physical Activity? When we ask you about physical activity, we mean when you are moving around, playing, or exercising. Physical activity is any activity that
More informationGED Preparation Lesson Plan. Module: Science. Lesson Title: Forming a Conclusion. Standards: GED Preparation (Adult General Education)
GED Preparation Lesson Plan Module: Science Lesson Title: Forming a Conclusion Standards: GED Preparation (Adult General Education) Scientific Practices 2014 Assessment Targets Understand and explain textual
More informationLesson 1 Pre-Visit The Athlete's Body
Lesson 1 Pre-Visit The Athlete's Body Objective: Students will be able to: Explain the meaning of fitness. Identify ways that athletes maintain physical fitness. Correctly identify different muscle groups
More informationHierarchical Convolutional Features for Visual Tracking
Hierarchical Convolutional Features for Visual Tracking Chao Ma Jia-Bin Huang Xiaokang Yang Ming-Husan Yang SJTU UIUC SJTU UC Merced ICCV 2015 Background Given the initial state (position and scale), estimate
More informationarxiv: v1 [cs.cv] 12 Dec 2016
Text-guided Attention Model for Image Captioning Jonghwan Mun, Minsu Cho, Bohyung Han Department of Computer Science and Engineering, POSTECH, Korea {choco1916, mscho, bhhan}@postech.ac.kr arxiv:1612.03557v1
More informationDomain Generalization and Adaptation using Low Rank Exemplar Classifiers
Domain Generalization and Adaptation using Low Rank Exemplar Classifiers 报告人 : 李文 苏黎世联邦理工学院计算机视觉实验室 李文 苏黎世联邦理工学院 9/20/2017 1 Outline Problems Domain Adaptation and Domain Generalization Low Rank Exemplar
More informationAnnotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation
Annotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation Ryo Izawa, Naoki Motohashi, and Tomohiro Takagi Department of Computer Science Meiji University 1-1-1 Higashimita,
More informationOpen-Domain Chatting Machine: Emotion and Personality
Open-Domain Chatting Machine: Emotion and Personality Minlie Huang, Associate Professor Dept. of Computer Science, Tsinghua University aihuang@tsinghua.edu.cn http://aihuang.org/p 2017/12/15 1 Open-domain
More informationSource and Description Category of Practice Level of CI User How to Use Additional Information. Intermediate- Advanced. Beginner- Advanced
Source and Description Category of Practice Level of CI User How to Use Additional Information Randall s ESL Lab: http://www.esllab.com/ Provide practice in listening and comprehending dialogue. Comprehension
More informationCS/NEUR125 Brains, Minds, and Machines. Due: Friday, April 14
CS/NEUR125 Brains, Minds, and Machines Assignment 5: Neural mechanisms of object-based attention Due: Friday, April 14 This Assignment is a guided reading of the 2014 paper, Neural Mechanisms of Object-Based
More informationSign Language MT. Sara Morrissey
Sign Language MT Sara Morrissey Introduction Overview Irish Sign Language Problems for SLMT SLMT Data MaTrEx for SLs Future work Introduction (1) Motivation SLs are poorly resourced and lack political,
More informationVector Learning for Cross Domain Representations
Vector Learning for Cross Domain Representations Shagan Sah, Chi Zhang, Thang Nguyen, Dheeraj Kumar Peri, Ameya Shringi, Raymond Ptucha Rochester Institute of Technology, Rochester, NY 14623, USA arxiv:1809.10312v1
More informationShu Kong. Department of Computer Science, UC Irvine
Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge 4. Fine-grained classification with holistic representation
More informationRising Scholars Academy 8 th Grade English I Summer Reading Project The Alchemist By Paulo Coelho
Rising Scholars Academy 8 th Grade English I Summer Reading Project The Alchemist By Paulo Coelho Welcome to 8th grade English I! Summer is a time where you can relax and have fun, but did you know you
More informationAutism, my sibling, and me
ORGANIZATION FOR AUTISM RESEARCH Autism, my sibling, and me Brothers and sisters come in all shapes and sizes. They have a lot in common, and they can be really different from each other. Some kids even
More informationGroup Behavior Analysis and Its Applications
Group Behavior Analysis and Its Applications CVPR 2015 Tutorial Lecturers: Hyun Soo Park (University of Pennsylvania) Wongun Choi (NEC America Laboratory) Schedule 08:30am-08:50am 08:50am-09:50am 09:50am-10:10am
More informationAppendix C. Sample prepirls Passage, Questions, and Scoring Guides. Reading for Literary Experience Charlie s Talent
Appendix C Sample prepirls Passage, Questions, and Scoring Guides Reading for Literary Experience Charlie s Talent Charlie s Talent Summer had just begun. Charlie was planting a garden in front of his
More informationKeyword-driven Image Captioning via Context-dependent Bilateral LSTM
Keyword-driven Image Captioning via Context-dependent Bilateral LSTM Xiaodan Zhang 1,2, Shuqiang Jiang 2, Qixiang Ye 2, Jianbin Jiao 2, Rynson W.H. Lau 1 1 City University of Hong Kong 2 University of
More informationMedical Image Analysis
Medical Image Analysis 1 Co-trained convolutional neural networks for automated detection of prostate cancer in multiparametric MRI, 2017, Medical Image Analysis 2 Graph-based prostate extraction in t2-weighted
More informationAn assistive application identifying emotional state and executing a methodical healing process for depressive individuals.
An assistive application identifying emotional state and executing a methodical healing process for depressive individuals. Bandara G.M.M.B.O bhanukab@gmail.com Godawita B.M.D.T tharu9363@gmail.com Gunathilaka
More informationLearning to Disambiguate by Asking Discriminative Questions Supplementary Material
Learning to Disambiguate by Asking Discriminative Questions Supplementary Material Yining Li 1 Chen Huang 2 Xiaoou Tang 1 Chen Change Loy 1 1 Department of Information Engineering, The Chinese University
More informationLevel 5-6 What Katy Did
Level 5-6 What Katy Did Workbook Teacher s Guide and Answer Key A. Summary 1. Book Summary Teacher s Guide Once there was a girl named Katy. She tried to be good, but she always ended up doing the wrong
More information5/2018. AAC Lending Library. Step-by-Step with Levels. ablenet. Attainment Company. Go Talk One Talking Block. ablenet. Attainment.
5/2018 Device Step-by-Step with Levels Go Talk One Talking Block Go Talk 4, 9, 20 AAC Lending Library User Profile Description Manufacturer EmergentSupplementary Designed for pre-recording a series of
More informationHigh-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks
High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks Krzysztof J. Geras Joint work with Kyunghyun Cho, Linda Moy, Gene Kim, Stacey Wolfson and Artie Shen. GTC 2017
More informationA HMM-based Pre-training Approach for Sequential Data
A HMM-based Pre-training Approach for Sequential Data Luca Pasa 1, Alberto Testolin 2, Alessandro Sperduti 1 1- Department of Mathematics 2- Department of Developmental Psychology and Socialisation University
More informationLOOK, LISTEN, AND DECODE: MULTIMODAL SPEECH RECOGNITION WITH IMAGES. Felix Sun, David Harwath, and James Glass
LOOK, LISTEN, AND DECODE: MULTIMODAL SPEECH RECOGNITION WITH IMAGES Felix Sun, David Harwath, and James Glass MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA {felixsun,
More informationRepurposing Corpus Materials For Interpreter Education. Nancy Frishberg, Ph.D. MSB Associates San Mateo, California USA
Repurposing Corpus Materials For Interpreter Education Nancy Frishberg, Ph.D. MSB Associates San Mateo, California USA nancyf@fishbird.com I was raised in a household with lots of media 78 rpm Phonograph
More informationVisualizing the Affective Structure of a Text Document
Visualizing the Affective Structure of a Text Document Hugo Liu, Ted Selker, Henry Lieberman MIT Media Laboratory {hugo, selker, lieber} @ media.mit.edu http://web.media.mit.edu/~hugo Overview Motivation
More informationarxiv: v1 [cs.cv] 7 Dec 2018
An Attempt towards Interpretable Audio-Visual Video Captioning Yapeng Tian 1, Chenxiao Guan 1, Justin Goodman 2, Marc Moore 3, and Chenliang Xu 1 arxiv:1812.02872v1 [cs.cv] 7 Dec 2018 1 Department of Computer
More informationDeepDiary: Automatically Captioning Lifelogging Image Streams
DeepDiary: Automatically Captioning Lifelogging Image Streams Chenyou Fan David J. Crandall School of Informatics and Computing Indiana University Bloomington, Indiana USA {fan6,djcran}@indiana.edu Abstract.
More informationConvolutional Neural Networks for Text Classification
Convolutional Neural Networks for Text Classification Sebastian Sierra MindLab Research Group July 1, 2016 ebastian Sierra (MindLab Research Group) NLP Summer Class July 1, 2016 1 / 32 Outline 1 What is
More informationBlast Searcher Formative Evaluation. March 02, Adam Klinger and Josh Gutwill
Blast Searcher Formative Evaluation March 02, 2006 Keywords: Genentech Biology Life Sciences Adam Klinger and Josh Gutwill Traits of Life \ - 1 - BLAST Searcher Formative Evaluation March 2, 2006 Adam
More informationIntelligent Machines That Act Rationally. Hang Li Bytedance AI Lab
Intelligent Machines That Act Rationally Hang Li Bytedance AI Lab Four Definitions of Artificial Intelligence Building intelligent machines (i.e., intelligent computers) Thinking humanly Acting humanly
More informationRumor Detection on Twitter with Tree-structured Recursive Neural Networks
1 Rumor Detection on Twitter with Tree-structured Recursive Neural Networks Jing Ma 1, Wei Gao 2, Kam-Fai Wong 1,3 1 The Chinese University of Hong Kong 2 Victoria University of Wellington, New Zealand
More informationEmotion Recognition using a Cauchy Naive Bayes Classifier
Emotion Recognition using a Cauchy Naive Bayes Classifier Abstract Recognizing human facial expression and emotion by computer is an interesting and challenging problem. In this paper we propose a method
More informationWhy did the network make this prediction?
Why did the network make this prediction? Ankur Taly (Google Inc.) Joint work with Mukund Sundararajan and Qiqi Yan Some Deep Learning Successes Source: https://www.cbsinsights.com Deep Neural Networks
More informationBuilding Evaluation Scales for NLP using Item Response Theory
Building Evaluation Scales for NLP using Item Response Theory John Lalor CICS, UMass Amherst Joint work with Hao Wu (BC) and Hong Yu (UMMS) Motivation Evaluation metrics for NLP have been mostly unchanged
More informationA Year of Tips for Communication Success
A Year of Tips for Communication Success 2143 Township Road 112 Millersburg, OH 44654 1-877-397-0178 info@saltillo.com www.saltillo.com Create Communication Success: Teach communication through modeling
More informationMyDispense OTC exercise Guide
MyDispense OTC exercise Guide Version 5.0 Page 1 of 23 Page 2 of 23 Table of Contents What is MyDispense?... 4 Who is this guide for?... 4 How should I use this guide?... 4 OTC exercises explained... 4
More informationHoughton Mifflin Harcourt Discovering French Today! Level correlated to the
Houghton Mifflin Harcourt Discovering French Today! Level 2 2013 correlated to the NCSSFL ACTFL Can-Do Statements (2015), Novice Mid, Novice High, Intermediate Low Novice Mid Interpersonal Communication
More information1. INTRODUCTION. Vision based Multi-feature HGR Algorithms for HCI using ISL Page 1
1. INTRODUCTION Sign language interpretation is one of the HCI applications where hand gesture plays important role for communication. This chapter discusses sign language interpretation system with present
More informationThe Mythos of Model Interpretability
The Mythos of Model Interpretability Zachary C. Lipton https://arxiv.org/abs/1606.03490 Outline What is interpretability? What are its desiderata? What model properties confer interpretability? Caveats,
More informationConvolutional and LSTM Neural Networks
Convolutional and LSTM Neural Networks Vanessa Jurtz January 12, 2016 Contents Neural networks and GPUs Lasagne Peptide binding to MHC class II molecules Convolutional Neural Networks (CNN) Recurrent and
More informationLesson 14: Association Between Categorical Variables
Lesson 14: Association Between Categorical Variables Classwork Example 1 Suppose a random group of people are surveyed about their use of smartphones. The results of the survey are summarized in the tables
More informationIntelligent Machines That Act Rationally. Hang Li Toutiao AI Lab
Intelligent Machines That Act Rationally Hang Li Toutiao AI Lab Four Definitions of Artificial Intelligence Building intelligent machines (i.e., intelligent computers) Thinking humanly Acting humanly Thinking
More informationLevel 14 Book f. Level 14 Word Count 321 Text Type Information report High Frequency children, father, Word/s Introduced people
People and Dolphins Level 14 Book f The Apple Tree Macey s Mess This Little Girl Roger the Bat Goes to Town Written by Sarah Edwards Ringo Goes Missing Level 14 Word Count 321 Text Type Information report
More informationImproving the Interpretability of DEMUD on Image Data Sets
Improving the Interpretability of DEMUD on Image Data Sets Jake Lee, Jet Propulsion Laboratory, California Institute of Technology & Columbia University, CS 19 Intern under Kiri Wagstaff Summer 2018 Government
More informationHelping Families Achieve the Best Outcome for their Child with a Cochlear Implant
Helping Families Achieve the Best Outcome for their Child with a Cochlear Implant Donna L. Sorkin, M.A., Vice President, Consumer Affairs Melissa Wilson, Au.D., CCC-AAA, Clinical Applications Specialist
More informationParents Talk About Teaching Kids to Read
Parents Talk About Teaching Kids to Read [This page prints out on 5 sheets] Learn what other parents say about teaching their kids to read. Click on the links below to go to the quote. After you read the
More informationGlobal&Journal&of&Community&Psychology&Practice&
Global&Journal&of&Community&Psychology&Practice& Volume 2, Issue 2 December 2011 Tearless Logic Model Ashlee D. Lien, Justin P. Greenleaf, Michael K. Lemke, Sharon M. Hakim, Nathan P. Swink, Rosemary Wright,
More informationCS343: Artificial Intelligence
CS343: Artificial Intelligence Introduction: Part 2 Prof. Scott Niekum University of Texas at Austin [Based on slides created by Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All materials
More informationMaking Sure People with Communication Disabilities Get the Message
Emergency Planning and Response for People with Disabilities Making Sure People with Communication Disabilities Get the Message A Checklist for Emergency Public Information Officers This document is part
More informationObject Detectors Emerge in Deep Scene CNNs
Object Detectors Emerge in Deep Scene CNNs Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Presented By: Collin McCarthy Goal: Understand how objects are represented in CNNs Are
More informationAttentional Masking for Pre-trained Deep Networks
Attentional Masking for Pre-trained Deep Networks IROS 2017 Marcus Wallenberg and Per-Erik Forssén Computer Vision Laboratory Department of Electrical Engineering Linköping University 2014 2017 Per-Erik
More informationHuman Information Processing and Cultural Diversity. Jaana Holvikivi, DSc. School of ICT
Human Information Processing and Cultural Diversity Jaana Holvikivi, DSc. School of ICT Outline Introduction Understanding the human mind Cognitive capacity Cultural schemas Jaana Holvikivi 2 The human
More information- Where... you last night? - What time? - At about... - I was... Why? - Because there was a at. - There was? Too bad I wasn t there.
Do You Know..? Activity 1 1. Where was Einstein when he discovered the theory of relativity? 2. Where were Neil Armstrong and Edwin Aldrin on July 10th, 1969? 3. Where was J.F.K. when he was assassinated?
More informationActive Deformable Part Models Inference
Active Deformable Part Models Inference Menglong Zhu Nikolay Atanasov George J. Pappas Kostas Daniilidis GRASP Laboratory, University of Pennsylvania 3330 Walnut Street, Philadelphia, PA 19104, USA Abstract.
More information3. Which word is an antonym
Name: Date: 1 Read the text and then answer the questions. Stephanie s best friend, Lindsey, was having a birthday in a few weeks. The problem was that Stephanie had no idea what to get her. She didn t
More informationInterpreting Deep Neural Networks and their Predictions
Fraunhofer Image Processing Heinrich Hertz Institute Interpreting Deep Neural Networks and their Predictions Wojciech Samek ML Group, Fraunhofer HHI (joint work with S. Lapuschkin, A. Binder, G. Montavon,
More informationCOMP9444 Neural Networks and Deep Learning 5. Convolutional Networks
COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks Textbook, Sections 6.2.2, 6.3, 7.9, 7.11-7.13, 9.1-9.5 COMP9444 17s2 Convolutional Networks 1 Outline Geometry of Hidden Unit Activations
More informationElementary 2 Unit Go to online version of the activity. Go back to this menu.
Elementary 2 Unit 4 1 2 3 4 5 6 7 8 Go to online version of the activity. Go back to this menu. Do You Know..? Activity 1 1. Where was Einstein when he discovered the theory of relativity? 2. Where were
More informationSeptember 2016 Newsletter
September 2016 Newsletter Your Family Name Shuffling your kids back to school these days takes more than a new wardrobe and a shiny apple. What about the dizzying array of immunizations? Hearing and vision
More informationCome for the day, or choose to stay!
Volunteer Program 2018 Thank you for your interest in the Kids Saving the Rainforest volunteer program! We are a wildlife sanctuary, rescue and rehabilitation center located in beautiful Quepos, Costa
More informationThe 29th Fuzzy System Symposium (Osaka, September 9-, 3) Color Feature Maps (BY, RG) Color Saliency Map Input Image (I) Linear Filtering and Gaussian
The 29th Fuzzy System Symposium (Osaka, September 9-, 3) A Fuzzy Inference Method Based on Saliency Map for Prediction Mao Wang, Yoichiro Maeda 2, Yasutake Takahashi Graduate School of Engineering, University
More informationReal Time Sign Language Processing System
Real Time Sign Language Processing System Dibyabiva Seth (&), Anindita Ghosh, Ariruna Dasgupta, and Asoke Nath Department of Computer Science, St. Xavier s College (Autonomous), Kolkata, India meetdseth@gmail.com,
More informationCharacter Motivation Essential Question: How do readers analyze character motivation, including how it advances the plot and theme in a story?
Character Motivation Essential Question: How do readers analyze character motivation, including how it advances the plot and theme in a story? WORDS IN BLUE ARE NOTES FOR YOU! Movie Time!!! https://www.youtube.com/watch?v=y6sbbm5quo0
More informationAppendix I Teaching outcomes of the degree programme (art. 1.3)
Appendix I Teaching outcomes of the degree programme (art. 1.3) The Master graduate in Computing Science is fully acquainted with the basic terms and techniques used in Computing Science, and is familiar
More informationarxiv: v2 [cs.cv] 3 Apr 2018
Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning Jingwen Wang Wenhao Jiang Lin Ma Wei Liu Yong Xu South China University of Technology Tencent AI Lab {jaywongjaywong, cswhjiang,
More informationGIANT: Geo-Informative Attributes for Location Recognition and Exploration
GIANT: Geo-Informative Attributes for Location Recognition and Exploration Quan Fang, Jitao Sang, Changsheng Xu Institute of Automation, Chinese Academy of Sciences October 23, 2013 Where is this? La Sagrada
More informationSocial Skills and Autism: Using Books in Creative Ways to Reach and Teach in Early Education
Social Skills and Autism: Using Books in Creative Ways to Reach and Teach in Early Education Mary Jane Weiss, Ph.D., and Cheri J. Meiners, M.Ed. State of intervention.. Social deficits remain the most
More informationStreamlined Dense Video Captioning
1 3 Topic: caesar salad recipe : a caesar salad is ready and is served in a bowl ee 2 : croutons are in a bowl and chopped ingredients are separated ee 3 : the man mix all the ingredients in a bowl to
More informationMulti-attention Guided Activation Propagation in CNNs
Multi-attention Guided Activation Propagation in CNNs Xiangteng He and Yuxin Peng (B) Institute of Computer Science and Technology, Peking University, Beijing, China pengyuxin@pku.edu.cn Abstract. CNNs
More informationIncreasing Social Awareness in Adults with Autism Spectrum Disorders
Increasing Social Awareness in Adults with Autism Spectrum Disorders Heather Conroy, LCSW Western Region ASERT University of Pittsburgh Medical Center UPMC Center for Autism and Developmental Disorders
More informationUsing Deep Convolutional Networks for Gesture Recognition in American Sign Language
Using Deep Convolutional Networks for Gesture Recognition in American Sign Language Abstract In the realm of multimodal communication, sign language is, and continues to be, one of the most understudied
More information