CSE 590V: Computer vision seminar

Fall 2015


Hand with Reflecting Sphere by M. C. Escher.
Recolored by xenomorph1138

Course description

CSE 590V is a seminar/reading group focused on recent work in computer vision. We will cover papers from recent and upcoming conferences related to computer vision (CVPR, ICCV, ECCV, SIGGRAPH, NIPS). The seminar is open to everyone. We especially encourage first year graduate students who may be considering research in computer vision or related areas to participate.


Logistics

Time: Fridays 11am-12pm

Location: CSE 403

Organizers: Fereshteh Sadeghi (fsadeghi @ cs washington edu) and Supasorn Suwajanakorn (supasorn @ cs washington edu)


Presentations

Each week we will cover a recent topic in computer vision by reading and discussing one or more relevant papers. A person will lead the discussion by presenting the chosen paper(s) for the week. We encourage all attendees to read the paper(s) beforehand and to actively participate in the discussion.

Each registered student will attend all classes and prepare a presentation (duration to be determined) on a selected paper(s). We will assign topics/papers during the first week based on preferences.

Each presenter will meet with the organizers before the class date to discuss the upcoming presentation, show prepared slides, and resolve any questions.


Schedule

Date Presenters Papers Slides
October 9 Ezgi Mercan and Hamid Izadinia

  • Unsupervised Object Discovery and Localization in the Wild: Part-Based Matching With Bottom-Up Region Proposals
    Minsu Cho, Suha Kwak, Cordelia Schmid, Jean Ponce, CVPR 2015 (PDF)
  • Structured Indoor Modeling
    Satoshi Ikehata, Hang Yan, Yasutaka Furukawa, ICCV 2015 (PDF)

indoor scene modeling slides
October 16 Antoine Bosselut and Sachin Mehta

  • Show and Tell: A Neural Image Caption Generator
    Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan, CVPR 2015 (PDF)
  • Category-Specific Object Reconstruction from a Single Image
    Abhishek Kar, Shubham Tulsiani, Joao Carreira, Jitendra Malik, CVPR 2015 (PDF)

October 23 Gaoang Wang and Daniel Gordon

  • Single Image 3D Without a Single 3D Image
    David Fouhey, Muhammad Wajahat Hussain, Abhinav Gupta, Martial Hebert, ICCV 2015 (PDF)
  • Recurrent Network Models for Human Dynamics
    Katerina Fragkiadaki, Sergey Levine, Panna Felsen, Jitendra Mali, ICCV 2015 (PDF)

October 30 Maxwell Forbes and Xuan Luo and Shenqi Tang

  • Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
    Yukun Zhu, Ryan Kiros, Rich Zemel, Ruslan salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler, ICCV 2015 (PDF)
  • Fully Convolutional Networks for Semantic Segmentation
    Jonathan Long, Evan Shelhamer, Trevor Darrell, CVPR 2015 (PDF)

November 6 CVPR submission deadline No seminar --
November 13 Alon Milchgrub and Chung-Yi Weng

  • High-Quality Hair Modeling from A Single Portrait Photo
    Menglei Chai, Linjie Luo, Kalyan Sunkavalli, Nathan Carr, Sunil Hadap and Kun Zhou, SIGGRAPH Asia 2015 (PDF)
  • FlowWeb: Joint Image Set Alignment by Weaving Consistent, Pixel-wise Correspondences
    Tinghui Zhou, Yong Jae Lee, Stella X. Yu, Alyosha A. Efros, CVPR 2015 (PDF)

November 20 Fereshteh Sadeghi and Hyunsu Cho

  • Unsupervised Visual Representation Learning by Context Prediction
    Carl Doersch, Abhinav Gupta, Alexei A. Efros, ICCV 2015 (PDF)
  • A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching
    Quynh Nguyen, Antoine Gautier, Matthias Hein, CVPR 2015 (PDF)

November 27 Thanksgiving No seminar --
December 4 (Shu Liang and Ya-shin Chen) and Aleksander Holynski TBA TBA
December 11 Keunhong Park and Aaron Walsman TBA TBA

Paper List

Geometric Scene Understanding (Reconstruction/Recognition/Segmentation)

  • Structured Indoor Modeling (PDF)
    Satoshi Ikehata, Hang Yan, Yasutaka Furukawa
    ICCV 2015
  • Learning to Generate Chairs With Convolutional Neural Networks (PDF)
    Alexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox
    CVPR 2015
  • Single Image 3D Without a Single 3D Image (PDF)
    David Fouhey, Muhammad Wajahat Hussain, Abhinav Gupta, Martial Hebert
    ICCV 2015
  • Accurate Depth Map Estimation From a Lenslet Light Field Camera (PDF)
    Hae-Gon Jeon, Jaesik Park, Gyeongmin Choe, Jinsun Park, Yunsu Bok, Yu-Wing Tai, In So Kweon
    CVPR 2015
  • 3D Scanning Deformable Objects With a Single RGBD Sensor (PDF)
    Mingsong Dou, Jonathan Taylor, Henry Fuchs, Andrew Fitzgibbon, Shahram Izadi
    CVPR 2015
  • Pose Induction for Novel Object Categories (PDF)
    Shubham Tulsiani, Joao Carreira, Jitendra Malik
    ICCV 2015

Vision and Language

  • Generative Adversarial Text to Image Synthesis (PDF,website)
    Scott Reed, Zeynep Akata , Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele and Honglak Lee
    ICML 2016
  • VQA: Visual Question Answering (PDF,website)
    Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, Larry Zitnick, Devi Parikh
    ICCV 2015
  • Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books (PDF,website)
    Yukun Zhu, Ryan Kiros, Rich Zemel, Ruslan salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler
    ICCV 2015
  • CIDEr: Consensus-Based Image Description Evaluation (PDF,website)
    Ramakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh
    CVPR 2015
  • Show and Tell: A Neural Image Caption Generator (PDF)
    Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan
    CVPR 2015

Scene Understanding/Semantics

  • Understanding and Predicting Memorability at a Large-scale (PDF,website)
    Aditya Khosla, Akhil Raju, Antonio Torralba, Aude Oliva
    ICCV 2015
  • What makes an object memorable? (PDF,website)
    Rachit Dubey, Joshua Peterson, Aditya Khosla, Ming-Hsuan Yang, and Bernard Ghanem
    ICCV 2015
  • Learning informative edge maps for indoor scene layout prediction
    Arun Mallya, Svetlana Lazebnik
    ICCV 2015

Automatic Object Discovery

  • Boosting Object Proposals: From Pascal to COCO (PDF)
    Jordi Pont-Tuset, Luc Van Gool
    ICCV 2015
  • Unsupervised Object Discovery and Tracking in Video Collections (PDF)
    Suha Kwak, Minsu Cho, Jean Ponce, Cordelia Schmid, Ivan Laptev
    ICCV 2015
  • Unsupervised Object Discovery and Localization in the Wild: Part-Based Matching With Bottom-Up Region Proposals (PDF)
    Minsu Cho, Suha Kwak, Cordelia Schmid, Jean Ponce
    CVPR 2015

Object Detection/Recognition

  • Fast R-CNN (PDF,website)
    Ross Girshick
    ICCV 2015
  • Semantic Guidance of Visual Attention for Localizing Objects in Scenes
    Juan Caicedo, Svetlana Lazebnik
    ICCV 2015
  • Webly Supervised Learning of Convolutional Networks (PDF)
    Xinlei Chen, Abhinav Gupta
    ICCV 2015
  • Love Thy Neighbors: Image Annotation by Exploiting Social Metadata (PDF)
    Lamberto Ballan, Justin Johnson, Fei-Fei Li
    ICCV 2015

Face

  • Face Flow (PDF)
    Patrick Snape, Anastasios Roussos, Yannis Panagakis, Stefanos Zafeiriou
    ICCV 2015
  • Web-Scale Training for Face Identification (PDF)
    Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, Lior Wolf
    CVPR 2015
  • Detailed Spatio-Temporal Reconstruction of Eyelids (PDF)
    Amit Bermano, Thabo Beeler, Yeara Kozlov, Derek Bradely, Bernd Bickel, Markus Gross
    Siggraph 2015
  • Dynamic 3D Avatar Creation from Hand-held Video Input (PDF)
    Alexandru-Eugen Ichim, Sofien Bouaziz, Mark Pauly
    Siggraph 2015
  • High-Quality Hair Modeling from A Single Portrait Photo(PDF)
    Menglei Chai, Linjie Luo, Kalyan Sunkavalli, Nathan Carr†,Sunil Hadap, Kun Zhou
    Siggraph Asia 2015
  • A Mouth Full of Words: Visually Consistent Acoustic Redubbing (PDF)
    Sarah Taylor, Barry-John Theobald, Iain Matthews
    ICASSP 2015
  • Learning To Look Up: Realtime Monocular Gaze Correction Using Machine Learning(PDF)
    Daniil Kononenko, Victor Lempitsky
    CVPR 2015
  • Skin Microstructure Deformation with Displacement Map Convolution(PDF)
    Koki Nagano, Graham Fyffe, Oleg Alexander, Jernej Barbic, Hao Li, Abhijeet Ghosh, Paul Debevec
    Siggraph 2015
  • Time-offset interaction with a holocaust survivor(PDF)
    Ron Artstein, David Traum, Oleg Alexander, Anton Leuski, Andrew Jones, Kallirroi Georgila, Paul Debevec, William Swartout, Heather Maio, Stephen Smith
    IUI 2014
  • Driving High-Resolution Facial Scans with Video Performance Capture(PDF)
    Graham Fyffe, Andrew Jones, Oleg Alexander, Ryosuke Ichikari, Paul Debevec
    IUI 2014
  • Near-instant capture of high-resolution facial geometry and reflectance(PDF)
    Paul Graham, Graham Fyffe, Borom Tonwattanapong, Abhijeet Ghosh, Paul Debevec
    Siggraph 2015

Human Pose Estimation

  • Dyna(Web)
    Gerard Pons-Moll, Javier Romero, Naureen Mahmood, Michael J. Black
    Siggraph 2015
  • Flowing ConvNets for Human Pose Estimation in Videos (PDF)
    Tomas Pfister, James Charles, Andrew Zisserman
    ICCV 2015
  • Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation (PDF)
    Sijin Li, Weichen Zhang, Antoni Chan
    ICCV 2015

Action Recognition/Temporal Prediction

  • Dynamic Image Networks for Action Recognition (PDF)
    Hakan Bilen, Basura Fernando, Efstratios Gavves, Andrea Vedaldi and Stephen Gould
    CVPR 2016
  • Contextual Action Recognition with R*CNN (PDF)
    Georgia Gkioxari, Ross Girshick, Jitendra Malik
    ICCV 2015
  • Dense Optical Flow Prediction from a Static Image (PDF)
    Jacob Walker, Abhinav Gupta, Martial Hebert
    ICCV 2015
  • Temporal Perception and Prediction in Ego-Centric Video
    Yipin Zhou, Tamara Berg
    ICCV 2015
  • Learning Temporal Embeddings for Complex Video Analysis
    Vignesh Ramanathan, Kevin Tang, Greg Mori, Fei-Fei Li
    ICCV 2015
  • Storyline Representation of Egocentric Videos with an Applications to Story-based Search
    Bo Xiong, Leonid Sigal, Gunhee Kim
    ICCV 2015
  • Space-Time Tree Ensemble for Action Recognition
    Shugao Ma, Leonid Sigal, Stan Sclaroff
    CVPR 2015

Computational Photography

  • Occlusion-aware depth estimation using light-field cameras (PDF)
    Ting-Chun Wang, Alexei Efros, Ravi Ramamoorthi
    ICCV 2015
  • Visual Vibrometry: Estimating Material Properties From Small Motion in Video (PDF,website)
    Abe Davis, Katherine L. Bouman, Justin G. Chen, Michael Rubinstein, Fredo Durand, William T. Freeman
    ICCV 2015
  • Fast Bilateral-Space Stereo for Synthetic Defocus (PDF)
    Jonathan T. Barron, Andrew Adams, YiChang Shih, Carlos Hernandez
    ICCV 2015

Low Level/Descriptors

  • Learning image representations equivariant to ego-motion (PDF)
    Dinesh Jayaraman, Kristen Grauman
    ICCV 2015
  • FlowWeb: Joint Image Set Alignment by Weaving Consistent, Pixel-wise Correspondences (PDF,website)
    Tinghui Zhou, Yong Jae Lee, Stella Yu, and Alexei A. Efros
    CVPR 2015
  • Unsupervised Visual Representation Learning by Context Prediction (PDF)
    Carl Doersch, Abhinav Gupta, Alexei Efros
    ICCV 2015
  • PatchMatch-based Automatic Lattice Detection for Near-Regular Textures
    Siying Liu, Tian-Tsong Ng, Minh Do, Kalyan Sunkavalli, Eli Shechtman, Nathan Carr
    ICCV 2015
  • EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow
    Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui, Cordelia Schmid
    ICCV 2015
  • Understanding Image Representations by Measuring Their Equivariance and Equivalence (PDF)
    Karel Lenc, Andrea Vedaldi
    CVPR 2015

Applications

  • Learning Affordance for Direct Perception in Autonomous Driving (PDF,website)
    Chenyi Chen, Ari Seff, Alain Kornhauser, Jianxiong Xiao
    ICCV 2015
  • Where to Buy It: Matching Street Clothing Photos in Online Shops (PDF)
    Mohammadhadi Kiapour, Xufeng Han, Svetlana Lazebnik, Alex Berg, Tamara Berg
    ICCV 2015
  • Joint Photo Stream and Blog Post Summarization and Exploration (PDF)
    Gunhee Kim, Seungwhan Moon, Leonid Sigal
    CVPR 2015
  • Social Saliency Prediction (PDF)
    Hyun Soo Park, Jianbo Shi
    CVPR 2015
  • Panoptic Studio: A Massively Multiview System for Social Motion Capture (PDF)
    Hanbyul Joo, Hao Liu, Lei Tan, Lin Gui, Shohei Nobuhara, Yaser Sheikh
    ICCV 2015

CVPR15 Best paper award winners

  • DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-Time (PDF)
    Richard A. Newcombe, Dieter Fox, Steven M. Seitz
    CVPR 2015
  • Category-Specific Object Reconstruction from a Single Image (PDF)
    Abhishek Kar, Shubham Tulsiani, Joao Carreira, Jitendra Malik
    CVPR 2015

CVPR15 Best paper honorable mention

  • Efficient Globally Optimal Consensus Maximisation with Tree Search (PDF)
    Tat-Jun Chin, Pulak Purkait, Anders Eriksson, David Suter
    CVPR 2015
  • Fully Convolutional Networks for Semantic Segmentation (PDF)
    Jonathan Long, Evan Shelhamer, Trevor Darrell
    CVPR 2015
  • Picture: A Probabilistic Programming Language for Scene Perception (PDF)
    Tejas D Kulkarni, Pushmeet Kohli, Joshua B Tenenbaum, Vikash Mansinghka
    CVPR 2015