16-785: Integrated Intelligence in Robotics: Vision, Language, and Planning. Spring 2018 Lecture 14. Image to Text

Size: px
Start display at page:

Download "16-785: Integrated Intelligence in Robotics: Vision, Language, and Planning. Spring 2018 Lecture 14. Image to Text"

Transcription

1 16-785: Integrated Intelligence in Robotics: Vision, Language, and Planning Spring 2018 Lecture 14. Image to Text

2 Input Output Classification tasks 4/1/18 CMU : Integrated Intelligence in Robotics 2

3 Input Output Classification tasks Structured input to structured output tasks o Machine translation or other NLP tasks o Image captioning 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 3

4 Language modeling using RNN Compute the probability of a sentence s = (w 1, w 2,, w T ) p(w 1, w 2,, w T ) = Π t=1 T p(w t w 1,,w t-1 ) RNN Conditional probability 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 4

5 Recap: Forward propagation in RNN Recurrent connections between hidden units; output every time step a (t ) = b +Wh (t 1) +Ux (t ), h t = tanh(a (t ) ), o (t ) = c +Vh (t ), ŷ (t ) = softmax(o (t ) ) [Fig 10.3] Softmax to get normalized probabilities CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 5

6 Language modeling using RNN Compute the probability of a sentence s = (w 1, w 2,, w T ) p(w 1, w 2,, w T ) = Π t=1 T p(w t w 1,,w t-1 ) RNN p(w t+1 =w w 1,,w t ) =g θw (h t, w t ) Conditional probability Probability of the next word being w 4/2/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 6

7 Conditional language model p(w t+1 =w w 1,,w t ) =g θw (h t, w t ) h t = φ θ (h t-1, w t, c) Context 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 7

8 Recap: Encoder-Decoder Sequence-to-Sequence Architecture Map variable-length input sequence to variable-length output sequence Machine translation [Cho et al., 2014] [Sutskever et al., 2014] CMU : Integrated Intelligence in Robotics 8

9 Encoder-Decoder Sequence-to-Sequence Architecture Encoder (reader or input) RNN processes input sequence x=(x (1),, x (nx) )and emits context C CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 9

10 Encoder-Decoder Sequence-to-Sequence Architecture Encoder (reader or input) RNN processes input sequence x=(x (1),, x (nx) )and emits context C Decoder (writer or output) RNN is conditioned on the context C to generate output sequence y=(y (1),, y (ny) ) CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 10

11 Encoder-Decoder [Grid]-to-[Sequence] Architecture Encoder (reader or input) [CNN] processes input image x and emits context C Decoder (writer or output) RNN is conditioned on the context C to generate output sequence y=(y(1),, y(ny)) CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 11

12 Encoder-Decoder [Grid]-to-[Sequence] Architecture Encoder (reader or input) [CNN] processes image The context model isinput too simple to x and emits context C temporal, or guarantee that spatial, spatio-temporal structures of input are preserved. Decoder (writer or output) RNN is conditioned on the context C to generate output sequence y=(y(1),, y(ny)) CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 12

13 Attention mechanisms allow the system to sequentially focus on different subsets of the input (Cho et al., 2015). 4/1/18 CMU : Integrated Intelligence in Robotics 13

14 Attention mechanism A structured representation of input e.g., a set of fixed-size vectors known as context set C = { c 1, c 2,, c M } Attention model: another neural network to map hidden state to context vector 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 14

15 e i t = f Att c t = ϕ Attention model Hidden state z { } j=1 z t 1,c i, α j t 1 M { c } i, t αi i=1 { } i=1 i=1 Soft attention: softmax over context vectors in context set Hard attention: one best match M M = MC sampling [Xu et al., 2015] Attention weight α M α i c i e: score of context c i at time t α t i = exp(e t ) i M e j t j=1 Natural for gradient back-propagation 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 15

16 e i t = f Att c t = ϕ Attention model { } j=1 z t 1,c i, α j t 1 M { c } i, t αi i=1 { } i=1 i=1 Soft attention: softmax over context vectors in context set Hard attention: one best match MC sampling Hidden state z M M = Attention weight α M α i c i e: score of context c i at time t e.g., weighted sum α t i = exp(e t ) i M e j t j=1 Natural for gradient back-propagation 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 16

17 Conditional RNN language model c t = ϕ M { c } i, t αi i=1 { } i=1 Computing context vector every time step instead of using a fixed-length context vector h t = φ θ (h t-1, x t, c t ) M = M i=1 α i c i 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 17

18 Image captioning Representation of input image: Activation of the last fully-connected hidden layer as context vector in simple encoderdecoder model Activation of the last convolutional layer to use attention mechanism 4/1/18 CMU : Integrated Intelligence in Robotics 18

19 [Karpathy & Fei-Fei 2015] Generate dense descriptions of images using multimodal embedding 1/31/18

20 Representing images Bounding box detection using: R-CNN + pretrain on ImageNet + finetuning on 200 classes of ImageNet Detection Challenge [Girshick CVPR 14] 1/31/ activations of fully connected layer right before classification

21 Representing images Top 19 bounding boxes + entire input image = 20 1 image à 20 h-dimensional vectors v = W m [CNN θc (I b )] + b m 1/31/18

22 Recap: Bidirectional RNNs Backward in time Forward in time [Fig ] CMU : Integrated Intelligence in Robotics 22

23 Representing sentences Bidirectional RNN Left to right & right to left context Each input word à 1-of-k vector Encode into h-d vector (the same embedding space as images) 1/31/18

24 Alignment Training set: k: image index l: sentence index Multimodal h-d embedding Image à v 1, v 20 Sentence n words à s 1,,s n Similarity between image region & word based on dot product v kt s t S k,l = max i gk v T i s t (Eq. 8) 1/31/18 t g l

25 Multimodal RNN for text generation Image CNN at t 0 START & END: special tokens Each word encoded into a vector Predict next word as probability distribution over dictionary + END 1/31/18

26 Qualitative result 20 occurrences of man in black shirt 60 occurrences of is playing guitar 1/31/18

27 Additional sample results 1/31/18

28 Show & Tell [Vinyals et al., 2015] C Simple encoder-decoder model using fixed-length context vector 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 28

29 Show & Tell [Vinyals et al., 2015] CNN: Inception V1-3 Batch Normlization 4/1/18 CMU : Integrated Intelligence in Robotics 29

30 Show & Tell [Vinyals et al., 2015] 4/1/18 CMU : Integrated Intelligence in Robotics 30

31 Show, Attend, & Tell [Xu et al., 2015] 4/1/18 CMU : Integrated Intelligence in Robotics 31

32 Show, Attend, & Tell [Xu et al., 2015] 4/1/18 CMU : Integrated Intelligence in Robotics 32

33 Show, Attend, & Tell [Xu et al., 2015] 4/1/18 CMU : Integrated Intelligence in Robotics 33

34 Image captioning with attributes (LSTM-A) [Yao et al., 2017] CNN-RNN encoder-decoder model Predefined set of high-level attributes Multiple instance learning with interattribute correlations 4/1/18 CMU : Integrated Intelligence in Robotics 34

35 Image captioning with attributes (LSTM-A) [Yao et al., 2017] 4/1/18 CMU : Integrated Intelligence in Robotics 35

36 Image captioning with attributes (LSTM-A) [Yao et al., 2017] 4/1/18 CMU : Integrated Intelligence in Robotics 36

37 How much data do we need to achieve decent performance in image captioning? 4/1/18 CMU : Integrated Intelligence in Robotics 37

38 [Young et al., TACL 2014] 30K images + 150K captions P. Young, A. Lai, M. Hodosh, and J. Hockenmaier. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. TACL /31/18

39 MS COCO K images x 5 captions 1/31/18

40 Testing on images outside datasets [Google s Show & Tell] Courtesy: Andy Tsai 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 40

41 Testing on images outside datasets [Show, Attend, & Tell] Courtesy: Junjiao Tian 4/1/18 CMU : Integrated Intelligence in Robotics 41

42 There s a lot of room to improve 4/1/18 CMU : Integrated Intelligence in Robotics (jeanoh@cmu.edu) 42

43 Wednesday papers: Next Project presentation Afshaan Word2vec (Krishna) Skip-thought vector (Satyen) Project midterm report 4/1/18 CMU : Integrated Intelligence in Robotics 43

Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks

Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Zelun Luo Department of Computer Science Stanford University zelunluo@stanford.edu Te-Lin Wu Department of

More information

LSTM for Language Translation and Image Captioning. Tel Aviv University Deep Learning Seminar Oran Gafni & Noa Yedidia

LSTM for Language Translation and Image Captioning. Tel Aviv University Deep Learning Seminar Oran Gafni & Noa Yedidia 1 LSTM for Language Translation and Image Captioning Tel Aviv University Deep Learning Seminar Oran Gafni & Noa Yedidia 2 Part I LSTM for Language Translation Motivation Background (RNNs, LSTMs) Model

More information

Image Captioning with Object Detection and Localization

Image Captioning with Object Detection and Localization Image Captioning with Object Detection and Localization Zhongliang Yang, Yu-Jin Zhang, Sadaqat ur Rehman, Yongfeng Huang, Department of Electronic Engineering, Tsinghua University, Beijing 100084, China

More information

Novel Image Captioning

Novel Image Captioning 000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050

More information

Pointer Network. Oriol Vinyals. 박천음 강원대학교 Intelligent Software Lab.

Pointer Network. Oriol Vinyals. 박천음 강원대학교 Intelligent Software Lab. Pointer Network Oriol Vinyals 박천음 강원대학교 Intelligent Software Lab. Intelligent Software Lab. Pointer Network 1 Pointer Network 2 Intelligent Software Lab. 2 Sequence-to-Sequence Model Train 학습학습학습학습학습 Test

More information

CS839: Probabilistic Graphical Models. Lecture 22: The Attention Mechanism. Theo Rekatsinas

CS839: Probabilistic Graphical Models. Lecture 22: The Attention Mechanism. Theo Rekatsinas CS839: Probabilistic Graphical Models Lecture 22: The Attention Mechanism Theo Rekatsinas 1 Why Attention? Consider machine translation: We need to pay attention to the word we are currently translating.

More information

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention Show, Attend and Tell: Neural Image Caption Generation with Visual Attention Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard Zemel, Yoshua Bengio Presented

More information

Image-Sentence Multimodal Embedding with Instructive Objectives

Image-Sentence Multimodal Embedding with Instructive Objectives Image-Sentence Multimodal Embedding with Instructive Objectives Jianhao Wang Shunyu Yao IIIS, Tsinghua University {jh-wang15, yao-sy15}@mails.tsinghua.edu.cn Abstract To encode images and sentences into

More information

ABC-CNN: Attention Based CNN for Visual Question Answering

ABC-CNN: Attention Based CNN for Visual Question Answering ABC-CNN: Attention Based CNN for Visual Question Answering CIS 601 PRESENTED BY: MAYUR RUMALWALA GUIDED BY: DR. SUNNIE CHUNG AGENDA Ø Introduction Ø Understanding CNN Ø Framework of ABC-CNN Ø Datasets

More information

SEMANTIC COMPUTING. Lecture 9: Deep Learning: Recurrent Neural Networks (RNNs) TU Dresden, 21 December 2018

SEMANTIC COMPUTING. Lecture 9: Deep Learning: Recurrent Neural Networks (RNNs) TU Dresden, 21 December 2018 SEMANTIC COMPUTING Lecture 9: Deep Learning: Recurrent Neural Networks (RNNs) Dagmar Gromann International Center For Computational Logic TU Dresden, 21 December 2018 Overview Handling Overfitting Recurrent

More information

Semantic image search using queries

Semantic image search using queries Semantic image search using queries Shabaz Basheer Patel, Anand Sampat Department of Electrical Engineering Stanford University CA 94305 shabaz@stanford.edu,asampat@stanford.edu Abstract Previous work,

More information

Modeling Sequences Conditioned on Context with RNNs

Modeling Sequences Conditioned on Context with RNNs Modeling Sequences Conditioned on Context with RNNs Sargur Srihari srihari@buffalo.edu This is part of lecture slides on Deep Learning: http://www.cedar.buffalo.edu/~srihari/cse676 1 10. Topics in Sequence

More information

CAP 6412 Advanced Computer Vision

CAP 6412 Advanced Computer Vision CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong Feb 04, 2016 Today Administrivia Attention Modeling in Image Captioning, by Karan Neural networks & Backpropagation

More information

Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks

Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Boya Peng Department of Computer Science Stanford University boya@stanford.edu Zelun Luo Department of Computer

More information

Layerwise Interweaving Convolutional LSTM

Layerwise Interweaving Convolutional LSTM Layerwise Interweaving Convolutional LSTM Tiehang Duan and Sargur N. Srihari Department of Computer Science and Engineering The State University of New York at Buffalo Buffalo, NY 14260, United States

More information

27: Hybrid Graphical Models and Neural Networks

27: Hybrid Graphical Models and Neural Networks 10-708: Probabilistic Graphical Models 10-708 Spring 2016 27: Hybrid Graphical Models and Neural Networks Lecturer: Matt Gormley Scribes: Jakob Bauer Otilia Stretcu Rohan Varma 1 Motivation We first look

More information

LSTM and its variants for visual recognition. Xiaodan Liang Sun Yat-sen University

LSTM and its variants for visual recognition. Xiaodan Liang Sun Yat-sen University LSTM and its variants for visual recognition Xiaodan Liang xdliang328@gmail.com Sun Yat-sen University Outline Context Modelling with CNN LSTM and its Variants LSTM Architecture Variants Application in

More information

Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction

Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction by Noh, Hyeonwoo, Paul Hongsuck Seo, and Bohyung Han.[1] Presented : Badri Patro 1 1 Computer Vision Reading

More information

Image-to-Text Transduction with Spatial Self-Attention

Image-to-Text Transduction with Spatial Self-Attention Image-to-Text Transduction with Spatial Self-Attention Sebastian Springenberg, Egor Lakomkin, Cornelius Weber and Stefan Wermter University of Hamburg - Dept. of Informatics, Knowledge Technology Vogt-Ko

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Announcements Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Seminar registration period starts on Friday We will offer a lab course in the summer semester Deep Robot Learning Topic:

More information

Multi-Glance Attention Models For Image Classification

Multi-Glance Attention Models For Image Classification Multi-Glance Attention Models For Image Classification Chinmay Duvedi Stanford University Stanford, CA cduvedi@stanford.edu Pararth Shah Stanford University Stanford, CA pararth@stanford.edu Abstract We

More information

Sequence Modeling: Recurrent and Recursive Nets. By Pyry Takala 14 Oct 2015

Sequence Modeling: Recurrent and Recursive Nets. By Pyry Takala 14 Oct 2015 Sequence Modeling: Recurrent and Recursive Nets By Pyry Takala 14 Oct 2015 Agenda Why Recurrent neural networks? Anatomy and basic training of an RNN (10.2, 10.2.1) Properties of RNNs (10.2.2, 8.2.6) Using

More information

Project Final Report

Project Final Report Project Final Report Ye Tian Stanford University yetian@stanford.edu Tianlun Li Stanford University tianlunl@stanford.edu Abstract We plan to do image-to-sentence generation. This application bridges vision

More information

Residual Networks And Attention Models. cs273b Recitation 11/11/2016. Anna Shcherbina

Residual Networks And Attention Models. cs273b Recitation 11/11/2016. Anna Shcherbina Residual Networks And Attention Models cs273b Recitation 11/11/2016 Anna Shcherbina Introduction to ResNets Introduced in 2015 by Microsoft Research Deep Residual Learning for Image Recognition (He, Zhang,

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period starts

More information

DCU-UvA Multimodal MT System Report

DCU-UvA Multimodal MT System Report DCU-UvA Multimodal MT System Report Iacer Calixto ADAPT Centre School of Computing Dublin City University Dublin, Ireland iacer.calixto@adaptcentre.ie Desmond Elliott ILLC University of Amsterdam Science

More information

Image Captioning and Generation From Text

Image Captioning and Generation From Text Image Captioning and Generation From Text Presented by: Tony Zhang, Jonathan Kenny, and Jeremy Bernstein Mentor: Stephan Zheng CS159 Advanced Topics in Machine Learning: Structured Prediction California

More information

Recurrent Neural Nets II

Recurrent Neural Nets II Recurrent Neural Nets II Steven Spielberg Pon Kumar, Tingke (Kevin) Shen Machine Learning Reading Group, Fall 2016 9 November, 2016 Outline 1 Introduction 2 Problem Formulations with RNNs 3 LSTM for Optimization

More information

Table of Contents. What Really is a Hidden Unit? Visualizing Feed-Forward NNs. Visualizing Convolutional NNs. Visualizing Recurrent NNs

Table of Contents. What Really is a Hidden Unit? Visualizing Feed-Forward NNs. Visualizing Convolutional NNs. Visualizing Recurrent NNs Table of Contents What Really is a Hidden Unit? Visualizing Feed-Forward NNs Visualizing Convolutional NNs Visualizing Recurrent NNs Visualizing Attention Visualizing High Dimensional Data What do visualizations

More information

Deep Learning in Visual Recognition. Thanks Da Zhang for the slides

Deep Learning in Visual Recognition. Thanks Da Zhang for the slides Deep Learning in Visual Recognition Thanks Da Zhang for the slides Deep Learning is Everywhere 2 Roadmap Introduction Convolutional Neural Network Application Image Classification Object Detection Object

More information

Generative Adversarial Text to Image Synthesis

Generative Adversarial Text to Image Synthesis Generative Adversarial Text to Image Synthesis Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, Honglak Lee Presented by: Jingyao Zhan Contents Introduction Related Work Method

More information

JOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS. Puyang Xu, Ruhi Sarikaya. Microsoft Corporation

JOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS. Puyang Xu, Ruhi Sarikaya. Microsoft Corporation JOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS Puyang Xu, Ruhi Sarikaya Microsoft Corporation ABSTRACT We describe a joint model for intent detection and slot filling based

More information

Recurrent Neural Networks

Recurrent Neural Networks Recurrent Neural Networks Javier Béjar Deep Learning 2018/2019 Fall Master in Artificial Intelligence (FIB-UPC) Introduction Sequential data Many problems are described by sequences Time series Video/audio

More information

Machine Learning for Natural Language Processing. Alice Oh January 17, 2018

Machine Learning for Natural Language Processing. Alice Oh January 17, 2018 Machine Learning for Natural Language Processing Alice Oh January 17, 2018 Overview Distributed representation Temporal neural networks RNN LSTM GRU Sequence-to-sequence models Machine translation Response

More information

Machine Learning 13. week

Machine Learning 13. week Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of

More information

Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Video

Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Video Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Video Weilin Huang, Christopher P. Bridge, J. Alison Noble, and Andrew Zisserman Department of Engineering Science,

More information

Image Classification pipeline. Lecture 2-1

Image Classification pipeline. Lecture 2-1 Lecture 2: Image Classification pipeline Lecture 2-1 Administrative: Piazza For questions about midterm, poster session, projects, etc, use Piazza! SCPD students: Use your @stanford.edu address to register

More information

A Quick Guide on Training a neural network using Keras.

A Quick Guide on Training a neural network using Keras. A Quick Guide on Training a neural network using Keras. TensorFlow and Keras Keras Open source High level, less flexible Easy to learn Perfect for quick implementations Starts by François Chollet from

More information

SEMANTIC COMPUTING. Lecture 8: Introduction to Deep Learning. TU Dresden, 7 December Dagmar Gromann International Center For Computational Logic

SEMANTIC COMPUTING. Lecture 8: Introduction to Deep Learning. TU Dresden, 7 December Dagmar Gromann International Center For Computational Logic SEMANTIC COMPUTING Lecture 8: Introduction to Deep Learning Dagmar Gromann International Center For Computational Logic TU Dresden, 7 December 2018 Overview Introduction Deep Learning General Neural Networks

More information

Internet of things that video

Internet of things that video Video recognition from a sentence Cees Snoek Intelligent Sensory Information Systems Lab University of Amsterdam The Netherlands Internet of things that video 45 billion cameras by 2022 [LDV Capital] 2

More information

Spatial Localization and Detection. Lecture 8-1

Spatial Localization and Detection. Lecture 8-1 Lecture 8: Spatial Localization and Detection Lecture 8-1 Administrative - Project Proposals were due on Saturday Homework 2 due Friday 2/5 Homework 1 grades out this week Midterm will be in-class on Wednesday

More information

Image Caption with Global-Local Attention

Image Caption with Global-Local Attention Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) Image Caption with Global-Local Attention Linghui Li, 1,2 Sheng Tang, 1, Lixi Deng, 1,2 Yongdong Zhang, 1 Qi Tian 3

More information

Image Classification pipeline. Lecture 2-1

Image Classification pipeline. Lecture 2-1 Lecture 2: Image Classification pipeline Lecture 2-1 Administrative: Piazza For questions about midterm, poster session, projects, etc, use Piazza! SCPD students: Use your @stanford.edu address to register

More information

arxiv: v1 [cs.cv] 21 Dec 2016

arxiv: v1 [cs.cv] 21 Dec 2016 arxiv:1612.07360v1 [cs.cv] 21 Dec 2016 Top-down Visual Saliency Guided by Captions Vasili Ramanishka Boston University Abir Das Boston University Jianming Zhang Adobe Research Kate Saenko Boston University

More information

Temporal-difference Learning with Sampling Baseline for Image Captioning

Temporal-difference Learning with Sampling Baseline for Image Captioning Temporal-difference Learning with Sampling Baseline for Image Captioning Hui Chen, Guiguang Ding, Sicheng Zhao, Jungong Han School of Software, Tsinghua University, Beijing 100084, China School of Computing

More information

Encoding RNNs, 48 End of sentence (EOS) token, 207 Exploding gradient, 131 Exponential function, 42 Exponential Linear Unit (ELU), 44

Encoding RNNs, 48 End of sentence (EOS) token, 207 Exploding gradient, 131 Exponential function, 42 Exponential Linear Unit (ELU), 44 A Activation potential, 40 Annotated corpus add padding, 162 check versions, 158 create checkpoints, 164, 166 create input, 160 create train and validation datasets, 163 dropout, 163 DRUG-AE.rel file,

More information

Recurrent Neural Networks and Transfer Learning for Action Recognition

Recurrent Neural Networks and Transfer Learning for Action Recognition Recurrent Neural Networks and Transfer Learning for Action Recognition Andrew Giel Stanford University agiel@stanford.edu Ryan Diaz Stanford University ryandiaz@stanford.edu Abstract We have taken on the

More information

arxiv: v1 [cs.cv] 17 Nov 2016

arxiv: v1 [cs.cv] 17 Nov 2016 Instance-aware Image and Sentence Matching with Selective Multimodal LSTM arxiv:1611.05588v1 [cs.cv] 17 Nov 2016 An old man with his bag and dog is sitting on the bench beside the road and grass Yan Huang

More information

Image Captioning with Attention

Image Captioning with Attention ing with Attention Blaine Rister (blaine@stanford.edu), Dieterich Lawson (jdlawson@stanford.edu) 1. Introduction In the past few years, neural networks have fueled dramatic advances in image classication.

More information

Machine Learning: Chenhao Tan University of Colorado Boulder LECTURE 15

Machine Learning: Chenhao Tan University of Colorado Boulder LECTURE 15 Machine Learning: Chenhao Tan University of Colorado Boulder LECTURE 15 Slides adapted from Jordan Boyd-Graber Machine Learning: Chenhao Tan Boulder 1 of 21 Logistics HW3 available on Github, due on October

More information

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU, Machine Learning 10-701, Fall 2015 Deep Learning Eric Xing (and Pengtao Xie) Lecture 8, October 6, 2015 Eric Xing @ CMU, 2015 1 A perennial challenge in computer vision: feature engineering SIFT Spin image

More information

Generating Images from Captions with Attention. Elman Mansimov Emilio Parisotto Jimmy Lei Ba Ruslan Salakhutdinov

Generating Images from Captions with Attention. Elman Mansimov Emilio Parisotto Jimmy Lei Ba Ruslan Salakhutdinov Generating Images from Captions with Attention Elman Mansimov Emilio Parisotto Jimmy Lei Ba Ruslan Salakhutdinov Reasoning, Attention, Memory workshop, NIPS 2015 Motivation To simplify the image modelling

More information

Lecture 7: Semantic Segmentation

Lecture 7: Semantic Segmentation Semantic Segmentation CSED703R: Deep Learning for Visual Recognition (207F) Segmenting images based on its semantic notion Lecture 7: Semantic Segmentation Bohyung Han Computer Vision Lab. bhhanpostech.ac.kr

More information

RUC-Tencent at ImageCLEF 2015: Concept Detection, Localization and Sentence Generation

RUC-Tencent at ImageCLEF 2015: Concept Detection, Localization and Sentence Generation RUC-Tencent at ImageCLEF 2015: Concept Detection, Localization and Sentence Generation Xirong Li 1, Qin Jin 1, Shuai Liao 1, Junwei Liang 1, Xixi He 1, Yujia Huo 1, Weiyu Lan 1, Bin Xiao 2, Yanxiong Lu

More information

Semantic Segmentation. Zhongang Qi

Semantic Segmentation. Zhongang Qi Semantic Segmentation Zhongang Qi qiz@oregonstate.edu Semantic Segmentation "Two men riding on a bike in front of a building on the road. And there is a car." Idea: recognizing, understanding what's in

More information

Topics in AI (CPSC 532L): Multimodal Learning with Vision, Language and Sound. Lecture 12: Deep Reinforcement Learning

Topics in AI (CPSC 532L): Multimodal Learning with Vision, Language and Sound. Lecture 12: Deep Reinforcement Learning Topics in AI (CPSC 532L): Multimodal Learning with Vision, Language and Sound Lecture 12: Deep Reinforcement Learning Types of Learning Supervised training Learning from the teacher Training data includes

More information

Structured Attention Networks

Structured Attention Networks Structured Attention Networks Yoon Kim Carl Denton Luong Hoang Alexander M. Rush HarvardNLP 1 Deep Neural Networks for Text Processing and Generation 2 Attention Networks 3 Structured Attention Networks

More information

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro CMU 15-781 Lecture 18: Deep learning and Vision: Convolutional neural networks Teacher: Gianni A. Di Caro DEEP, SHALLOW, CONNECTED, SPARSE? Fully connected multi-layer feed-forward perceptrons: More powerful

More information

A PARALLEL-FUSION RNN-LSTM ARCHITECTURE FOR IMAGE CAPTION GENERATION

A PARALLEL-FUSION RNN-LSTM ARCHITECTURE FOR IMAGE CAPTION GENERATION A PARALLEL-FUSION RNN-LSTM ARCHITECTURE FOR IMAGE CAPTION GENERATION Minsi Wang, Li Song, Xiaokang Yang, Chuanfei Luo Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University

More information

Autoencoder. Representation learning (related to dictionary learning) Both the input and the output are x

Autoencoder. Representation learning (related to dictionary learning) Both the input and the output are x Deep Learning 4 Autoencoder, Attention (spatial transformer), Multi-modal learning, Neural Turing Machine, Memory Networks, Generative Adversarial Net Jian Li IIIS, Tsinghua Autoencoder Autoencoder Unsupervised

More information

Convolutional Sequence to Sequence Learning. Denis Yarats with Jonas Gehring, Michael Auli, David Grangier, Yann Dauphin Facebook AI Research

Convolutional Sequence to Sequence Learning. Denis Yarats with Jonas Gehring, Michael Auli, David Grangier, Yann Dauphin Facebook AI Research Convolutional Sequence to Sequence Learning Denis Yarats with Jonas Gehring, Michael Auli, David Grangier, Yann Dauphin Facebook AI Research Sequence generation Need to model a conditional distribution

More information

arxiv: v2 [cs.cv] 23 Mar 2017

arxiv: v2 [cs.cv] 23 Mar 2017 Recurrent Memory Addressing for describing videos Arnav Kumar Jain Abhinav Agarwalla Kumar Krishna Agrawal Pabitra Mitra Indian Institute of Technology Kharagpur {arnavkj95, abhinavagarawalla, kumarkrishna,

More information

arxiv: v1 [cs.cv] 17 Nov 2016

arxiv: v1 [cs.cv] 17 Nov 2016 Multimodal Memory Modelling for Video Captioning arxiv:1611.05592v1 [cs.cv] 17 Nov 2016 Junbo Wang 1 Wei Wang 1 Yan Huang 1 Liang Wang 1,2 Tieniu Tan 1,2 1 Center for Research on Intelligent Perception

More information

Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features

Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features Xu SUN ( 孙栩 ) Peking University xusun@pku.edu.cn Motivation Neural networks -> Good Performance CNN, RNN, LSTM

More information

Word2vec and beyond. presented by Eleni Triantafillou. March 1, 2016

Word2vec and beyond. presented by Eleni Triantafillou. March 1, 2016 Word2vec and beyond presented by Eleni Triantafillou March 1, 2016 The Big Picture There is a long history of word representations Techniques from information retrieval: Latent Semantic Analysis (LSA)

More information

Lecture 21 : A Hybrid: Deep Learning and Graphical Models

Lecture 21 : A Hybrid: Deep Learning and Graphical Models 10-708: Probabilistic Graphical Models, Spring 2018 Lecture 21 : A Hybrid: Deep Learning and Graphical Models Lecturer: Kayhan Batmanghelich Scribes: Paul Liang, Anirudha Rayasam 1 Introduction and Motivation

More information

Deep Learning for Computer Vision II

Deep Learning for Computer Vision II IIIT Hyderabad Deep Learning for Computer Vision II C. V. Jawahar Paradigm Shift Feature Extraction (SIFT, HoG, ) Part Models / Encoding Classifier Sparrow Feature Learning Classifier Sparrow L 1 L 2 L

More information

Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network

Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network Feng Mao [0000 0001 6171 3168], Xiang Wu [0000 0003 2698 2156], Hui Xue, and Rong Zhang Alibaba Group, Hangzhou, China

More information

Convolutional Networks for Text

Convolutional Networks for Text CS11-747 Neural Networks for NLP Convolutional Networks for Text Graham Neubig Site https://phontron.com/class/nn4nlp2017/ An Example Prediction Problem: Sentence Classification I hate this movie very

More information

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Xiaodong Yang, Pavlo Molchanov, Jan Kautz INTELLIGENT VIDEO ANALYTICS Surveillance event detection Human-computer interaction

More information

RNNs as Directed Graphical Models

RNNs as Directed Graphical Models RNNs as Directed Graphical Models Sargur Srihari srihari@buffalo.edu This is part of lecture slides on Deep Learning: http://www.cedar.buffalo.edu/~srihari/cse676 1 10. Topics in Sequence Modeling Overview

More information

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta Encoder-Decoder Networks for Semantic Segmentation Sachin Mehta Outline > Overview of Semantic Segmentation > Encoder-Decoder Networks > Results What is Semantic Segmentation? Input: RGB Image Output:

More information

arxiv: v2 [cs.cv] 12 Apr 2017

arxiv: v2 [cs.cv] 12 Apr 2017 input image SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning Long Chen 1 Hanwang Zhang 2 Jun Xiao 1 Liqiang Nie 3 Jian Shao 1 Wei Liu 4 Tat-Seng Chua 5 1 Zhejiang

More information

Deep Learning with Tensorflow AlexNet

Deep Learning with Tensorflow   AlexNet Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification

More information

Grounded Compositional Semantics for Finding and Describing Images with Sentences

Grounded Compositional Semantics for Finding and Describing Images with Sentences Grounded Compositional Semantics for Finding and Describing Images with Sentences R. Socher, A. Karpathy, V. Le,D. Manning, A Y. Ng - 2013 Ali Gharaee 1 Alireza Keshavarzi 2 1 Department of Computational

More information

Empirical Evaluation of RNN Architectures on Sentence Classification Task

Empirical Evaluation of RNN Architectures on Sentence Classification Task Empirical Evaluation of RNN Architectures on Sentence Classification Task Lei Shen, Junlin Zhang Chanjet Information Technology lorashen@126.com, zhangjlh@chanjet.com Abstract. Recurrent Neural Networks

More information

UTS submission to Google YouTube-8M Challenge 2017

UTS submission to Google YouTube-8M Challenge 2017 UTS submission to Google YouTube-8M Challenge 2017 Linchao Zhu Yanbin Liu Yi Yang University of Technology Sydney {zhulinchao7, csyanbin, yee.i.yang}@gmail.com Abstract In this paper, we present our solution

More information

A Torch Library for Action Recognition and Detection Using CNNs and LSTMs

A Torch Library for Action Recognition and Detection Using CNNs and LSTMs A Torch Library for Action Recognition and Detection Using CNNs and LSTMs Gary Thung and Helen Jiang Stanford University {gthung, helennn}@stanford.edu Abstract It is very common now to see deep neural

More information

End-To-End Spam Classification With Neural Networks

End-To-End Spam Classification With Neural Networks End-To-End Spam Classification With Neural Networks Christopher Lennan, Bastian Naber, Jan Reher, Leon Weber 1 Introduction A few years ago, the majority of the internet s network traffic was due to spam

More information

arxiv: v2 [cs.cv] 7 Aug 2017

arxiv: v2 [cs.cv] 7 Aug 2017 Dense Captioning with Joint Inference and Visual Context Linjie Yang Kevin Tang Jianchao Yang Li-Jia Li Snap Inc. {linjie.yang, kevin.tang, jianchao.yang}@snap.com lijiali@cs.stanford.edu arxiv:1611.06949v2

More information

Dense Captioning with Joint Inference and Visual Context

Dense Captioning with Joint Inference and Visual Context Dense Captioning with Joint Inference and Visual Context Linjie Yang Kevin Tang Jianchao Yang Li-Jia Li Snap Inc. Google Inc. {linjie.yang, kevin.tang, jianchao.yang}@snap.com lijiali@cs.stanford.edu Abstract

More information

Multimodal Learning. Victoria Dean. MIT 6.S191 Intro to Deep Learning IAP 2017

Multimodal Learning. Victoria Dean. MIT 6.S191 Intro to Deep Learning IAP 2017 Multimodal Learning Victoria Dean Talk outline What is multimodal learning and what are the challenges? Flickr example: joint learning of images and tags Image captioning: generating sentences from images

More information

Deep Learning and Its Applications

Deep Learning and Its Applications Convolutional Neural Network and Its Application in Image Recognition Oct 28, 2016 Outline 1 A Motivating Example 2 The Convolutional Neural Network (CNN) Model 3 Training the CNN Model 4 Issues and Recent

More information

Mask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma

Mask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN Background Related Work Architecture Experiment Mask R-CNN Background Related Work Architecture Experiment Background From left

More information

Introduction to Neural Networks

Introduction to Neural Networks Introduction to Neural Networks Jakob Verbeek 2017-2018 Biological motivation Neuron is basic computational unit of the brain about 10^11 neurons in human brain Simplified neuron model as linear threshold

More information

CSC 578 Neural Networks and Deep Learning

CSC 578 Neural Networks and Deep Learning CSC 578 Neural Networks and Deep Learning Fall 2018/19 7. Recurrent Neural Networks (Some figures adapted from NNDL book) 1 Recurrent Neural Networks 1. Recurrent Neural Networks (RNNs) 2. RNN Training

More information

Top-down Visual Saliency Guided by Captions

Top-down Visual Saliency Guided by Captions Top-down Visual Saliency Guided by Captions Vasili Ramanishka Boston University vram@bu.edu Abir Das Boston University dasabir@bu.edu Jianming Zhang Adobe Research jianmzha@adobe.com Kate Saenko Boston

More information

Recurrent Fusion Network for Image Captioning

Recurrent Fusion Network for Image Captioning Recurrent Fusion Network for Image Captioning Wenhao Jiang 1, Lin Ma 1, Yu-Gang Jiang 2, Wei Liu 1, Tong Zhang 1 1 Tencen AI Lab, 2 Fudan University {cswhjiang, forest.linma}@gmail.com, ygj@fudan.edu.cn,

More information

Mask R-CNN. Kaiming He, Georgia, Gkioxari, Piotr Dollar, Ross Girshick Presenters: Xiaokang Wang, Mengyao Shi Feb. 13, 2018

Mask R-CNN. Kaiming He, Georgia, Gkioxari, Piotr Dollar, Ross Girshick Presenters: Xiaokang Wang, Mengyao Shi Feb. 13, 2018 Mask R-CNN Kaiming He, Georgia, Gkioxari, Piotr Dollar, Ross Girshick Presenters: Xiaokang Wang, Mengyao Shi Feb. 13, 2018 1 Common computer vision tasks Image Classification: one label is generated for

More information

Deep Learning Applications

Deep Learning Applications October 20, 2017 Overview Supervised Learning Feedforward neural network Convolution neural network Recurrent neural network Recursive neural network (Recursive neural tensor network) Unsupervised Learning

More information

Aggregating Frame-level Features for Large-Scale Video Classification

Aggregating Frame-level Features for Large-Scale Video Classification Aggregating Frame-level Features for Large-Scale Video Classification Shaoxiang Chen 1, Xi Wang 1, Yongyi Tang 2, Xinpeng Chen 3, Zuxuan Wu 1, Yu-Gang Jiang 1 1 Fudan University 2 Sun Yat-Sen University

More information

Spotlight: A Smart Video Highlight Generator Stanford University CS231N Final Project Report

Spotlight: A Smart Video Highlight Generator Stanford University CS231N Final Project Report Spotlight: A Smart Video Highlight Generator Stanford University CS231N Final Project Report Jun-Ting (Tim) Hsieh junting@stanford.edu Chengshu (Eric) Li chengshu@stanford.edu Kuo-Hao Zeng khzeng@cs.stanford.edu

More information

arxiv: v1 [cs.cv] 4 Sep 2018

arxiv: v1 [cs.cv] 4 Sep 2018 Text2Scene: Generating Abstract Scenes from Textual Descriptions Fuwen Tan 1, Song Feng 2, Vicente Ordonez 1 1 University of Virginia, 2 IBM Thomas J. Watson Research Center. fuwen.tan@virginia.edu, sfeng@us.ibm.com,

More information

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Charles R. Qi* Hao Su* Kaichun Mo Leonidas J. Guibas

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Charles R. Qi* Hao Su* Kaichun Mo Leonidas J. Guibas PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Charles R. Qi* Hao Su* Kaichun Mo Leonidas J. Guibas Big Data + Deep Representation Learning Robot Perception Augmented Reality

More information

Context-aware multimodal Recurrent Neural Network for automatic image captioning

Context-aware multimodal Recurrent Neural Network for automatic image captioning Radboud University AI Master Thesis Context-aware multimodal Recurrent Neural Network for automatic image captioning Author: Flip van Rijn (s4050614) Supervisor: Dr. F. Grootjen External supervisor Dedicon:

More information

Deep learning for dense per-pixel prediction. Chunhua Shen The University of Adelaide, Australia

Deep learning for dense per-pixel prediction. Chunhua Shen The University of Adelaide, Australia Deep learning for dense per-pixel prediction Chunhua Shen The University of Adelaide, Australia Image understanding Classification error Convolution Neural Networks 0.3 0.2 0.1 Image Classification [Krizhevsky

More information

GraphNet: Recommendation system based on language and network structure

GraphNet: Recommendation system based on language and network structure GraphNet: Recommendation system based on language and network structure Rex Ying Stanford University rexying@stanford.edu Yuanfang Li Stanford University yli03@stanford.edu Xin Li Stanford University xinli16@stanford.edu

More information

Rich feature hierarchies for accurate object detection and semantic segmentation

Rich feature hierarchies for accurate object detection and semantic segmentation Rich feature hierarchies for accurate object detection and semantic segmentation BY; ROSS GIRSHICK, JEFF DONAHUE, TREVOR DARRELL AND JITENDRA MALIK PRESENTER; MUHAMMAD OSAMA Object detection vs. classification

More information

WITH the development of remote sensing technology,

WITH the development of remote sensing technology, 1 Exploring Models and Data for Remote Sensing Image Caption Generation Xiaoqiang Lu, Senior Member, IEEE, Binqiang Wang, Xiangtao Zheng, and Xuelong Li, Fellow, IEEE arxiv:1712.07835v1 [cs.cv] 21 Dec

More information

LSTM: An Image Classification Model Based on Fashion-MNIST Dataset

LSTM: An Image Classification Model Based on Fashion-MNIST Dataset LSTM: An Image Classification Model Based on Fashion-MNIST Dataset Kexin Zhang, Research School of Computer Science, Australian National University Kexin Zhang, U6342657@anu.edu.au Abstract. The application

More information