Vicente

Computer Vision Reading Group

This semester we will start a Computer Vision seminar. The overall purpose of this seminar is to bring together people with interests in Computer Vision theory and techniques and to examine some current research papers. This seminar is organized by the students and collaborators of the UVA Vision, Language and Learning (VISLANG) research group. Any student who has some exposure to Computer Vision and Machine Learning should be able to follow the group.

The seminar will focus on topics related to the main research projects in Computer Vision in our group. These include work at the intersection of language and vision, computer vision for images on the web, general works on deep learning and machine learning methods that can be potentially applied to vision and language problems,methods for learning about sense of place, visual recognition of objects in complex environments, buidling systems that can recognize objects and places efficiently. Other topics will depend on the interests of the participants and new members of the reading group.

Schedule - Fall 2020 Meeting on Mondays from 1pm to 3pm - Online
DatePresenter(s)Topic(s)
November 16 All
Current research projects.

November 9 All
Current research projects.

November 2 Fuwen
Memory Aware Synapses: Learning what (not) to forget. Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny, Marcus Rohrbach, Tinne Tuytelaars. ECCV 2018.

October 26 Aman
Hyperbolic Image Embeddings. Valentin Khrulkov, Leyla Mirvakhabova, Evgeniya Ustinova, Ivan Oseledets, Victor Lempitsky. eprint arXiv 1904.02239.

October 19 Ziyan
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby. eprint arXiv 2010.11929.

October 12 Vicente
What is being transferred in transfer learning?. Behnam Neyshabur, Hanie Sedghi, Chiyuan Zhang. eprint arXiv 2008.11687.

October 5 Tianlu
NBDT: Neural-Backed Decision Trees. Alvin Wan, Lisa Dunlap, Daniel Ho, Jihan Yin, Scott Lee, Henry Jin, Suzanne Petryk, Sarah Adel Bargal, Joseph E. Gonzalez. eprint arXiv 2004.00221.

September 28 Aman
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks. Jonathan Frankle, Michael Carbin. ICLR 2019.

Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask. Hattie Zhou, Janice Lan, Rosanne Liu, Jason Yosinski. NeurIPS 2019.

What's Hidden in a Randomly Weighted Neural Network?. Vivek Ramanujan, Mitchell Wortsman, Aniruddha Kembhavi, Ali Farhadi, Mohammad Rastegari. CVPR 2020.

September 14 Tianlu
Beyond Accuracy: Behavioral Testing of NLP models with CheckList. Marco Tulio Ribeiro, Tongshuang Wu, Carlos Guestrin, Sameer Singh. ACL 2020.

September 14 Fuwen & Leticia
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow. Zachary Teed, Jia Deng. ECCV 2020.

September 7 Paola






Leticia



Aman








Towards Recognizing Unseen Categories in Unseen Domains. Massimiliano Mancini, Zeynep Akata, Elisa Ricci, Barbara Caputo. ECCV 2020.

A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning. Xingyu Chen, Xuguang Lan, Fuchun Sun, Nanning Zheng. ECCV 2020.

Learning to Generate Grounded Visual Captions without Localization Supervision. Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib, Peter Vajda, Marcus Rohrbach, Zsolt Kira. ECCV 2020.

Contrastive Learning for Unpaired Image-to-Image Translation. Taesung Park, Alexei A. Efros, Richard Zhang, Jun-Yan Zhu. ECCV 2020.

A Generic Visualization Approach for Convolutional Neural Networks. Ahmed Taha, Xitong Yang, Abhinav Shrivastava, Larry Davis. ECCV 2020.

We Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videos. Alex Andonian, Camilo Fosco, Mathew Monfort, Allen Lee, Rogerio Feris, Carl Vondrick, Aude Oliva. ECCV 2020.

August 31 Fuwen


Ziyan







Tianlu


Multi-modal Transformer for Video Retrieval. Valentin Gabeur, Chen Sun, Karteek Alahari, Cordelia Schmid. ECCV 2020.

Principal Feature Visualisation in Convolutional Neural Networks. Marianne BakkenJohannes Kvam, Johannes Kvam, Alexey A Stepanov, Asbjørn Berge. ECCV 2020.

Fixing Localization Errors to Improve Image Classification. Guolei Sun, Salman Khan, Wen Li, Hisham Cholakkal, Fahad Shahbaz Khan, and Luc Van Gool1. ECCV 2020.

Contextual Diversity for Active Learning. Sharat Agarwal, Himanshu Arora, Saket Anand, Chetan Arora. ECCV 2020.

August 24 Fuwen
Automatically Discovering and Learning New Visual Categories with Ranking Statistics. Kai Han, Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman. ICLR 2020.

Schedule - Spring 2020 Meeting on Mondays from 12pm to 2pm in Rice Hall 504 - moved online due to COVID-19
DatePresenter(s)Topic(s)
August 17 Paola
Context-Aware Zero-Shot Recognition. Ruotian Luo, Ning Zhang, Bohyung Han, Linjie Yang. AAAI 2020.

Online
August 3 Paola
Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification. Sanath Narayan, Akshita Gupta, Fahad Shahbaz Khan, Cees G. M. Snoek, Ling Shao. ECCV 2020.

Online
July 10 Paola
Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions. Jimmy Lei Ba, Kevin Swersky, Sanja Fidler, Ruslan Salakhutdinov. ICCV 2015.

Online
July 1 All
A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning. Dat Huynh, Ehsan Elhamifar. CVPR 2020.

Online
June 22 All
Visual Grounding in Video for Unsupervised Word Translation. Gunnar A. Sigurdsson, Jean-Baptiste Alayrac, Aida Nematzadeh, Lucas Smaira, Mateusz Malinowski, João Carreira, Phil Blunsom, Andrew Zisserman. CVPR 2020.

Online
June 1 Ziyan
Revisiting Modulated Convolutions for Visual Counting and Beyond. Duy-Kien Nguyen, Vedanuj Goswami, Xinlei Chen. arXiv:2004.11883.

Online
May 25 All
Supervised Multimodal Bitransformers for Classifying Images and Text. Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Davide Testuggine. EMNLP 2019.

Online
May 18 All
Shaping Visual Representations with Language for Few-shot Classification. Jesse Mu, Percy Liang, Noah Goodman. ACL 2020.

Online
March All
AutoML-Zero: Evolving Machine Learning Algorithms From Scratch. Esteban Real, Chen Liang, David R. So, Quoc V. Le. ICML 2020.

Online
February, 16 Tianlu


Lindsey

Don’t Judge an Object by Its Context: Learning to Overcome Contextual Bias. Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, Deepti Ghadiyaram. arXiv preprint arXiv:2001.03152, 2020.

Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learning. Lanqing He, Zhongdao Wang, Yali Li, Shengjin Wang. AAAI-2020.

February, 10 Ziyan


Jeffrey

Visual Attention Consistency under Image Transforms for Multi-Label Image Classification. Hao Guo, Kang Zheng, Xiaochuan Fan, Hongkai Yu, Song Wang. CVPR 2019.

Data-Efficient Image Recognition with Contrastive Predictive Coding. Olivier J. Hénaff, Aravind Srinivas, Jeffrey De Fauw, Ali Razavi, Carl Doersch, S. M. Ali Eslami, Aaron van den Oord. arXiv preprint arXiv:1905.09272, 2019.

February, 3 Fuwen
DistInit: Learning Video Representations Without a Single Labeled Video. Rohit Girdhar, Du Tran, Lorenzo Torresani, Deva Ramanan. ICCV 2019.

January, 27 Tianlu


Leticia

Adjusting Decision Boundary for Class Imbalanced Learning. Byungju Kim, Junmo Kim. arXiv preprint arXiv:1912.01857, 2019.

SegSort: Segmentation by Discriminative Sorting of Segments. Jyh-Jing Hwang, Stella X. Yu, Jianbo Shi, Maxwell D. Collins, Tien-Ju Yang, Xiao Zhang, Liang-Chieh Chen. ICCV 2019.

January, 20 Ziyan


Paola

Interpreting CNNs via Decision Trees. Quanshi Zhang, Yu Yang, Haotian Ma, and Ying Nian Wu. CVPR 2019.

Deep High-Resolution Representation Learning for Human Pose Estimation. Ke Sun, Bin Xiao, Dong Liu, Jingdong Wang. CVPR 2019.

January, 13 Fuwen
Putting An End to End-to-End: Gradient-Isolated Learning of Representations. Sindy Löwe, Peter O’Connor, Bastiaan S. Veeling.
NeurIPS 2019.

Schedule - Fall 2019 Meeting on Mondays from 1pm to 2pm in Rice Hall 504
DatePresenter(s)Topic(s)
December, 9 Jeffrey
Momentum Contrast for Unsupervised Visual Representation Learning. Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick. Technical report.

December, 2 Paola
EENA: Efficient Evolution of Neural Architecture. Hui Zhu, Zhulin An, Chuanguang Yang, Kaiqiang Xu, Erhu Zhao, Yongjun Xu. ICCV 2019.

November, 25 Ziyan
Learning to Find Common Objects Across Few Image Collections. Amirreza Shaban, Amir Rahimi, Shray Bansal, Stephen Gould, Byron Boots, Richard Hartley. ICCV 2019.

November, 18 Tianlu
Multi-Label Image Recognition with Graph Convolutional Networks. Zhao-Min Chen, Xiu-Shen Wei, Peng Wang, Yanwen Guo. CVPR 2019.
Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition. Tianshui Chen, Muxin Xu, Xiaolu Hui, Hefeng Wu, Liang Lin. ICCV 2019.

November, 11 Fuwen
Decoupling Representation and Classifier for Long-Tailed Recognition. Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, Yannis Kalantidis. arXiv preprint arXiv:1910.09217. 2019.

November, 4 Debo
Meta-Learning : http://learn2learn.net/. Sébastien M.R. Arnold, Praateek Mahajan, Debajyoti Datta, Ian Bunner.

October, 28 Jeffrey
UNITER: Learning UNiversal Image-TExt Representations. Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, Jingjing Liu. arXiv preprint arXiv:1909.11740. 2019.

October, 21 Paola
Select Via Proxy: Efficient Data Selection For Training Deep Networks. Cody Coleman, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia. arXiv preprint arXiv:1906.11829. 2019.

October, 14 Group
Current project status.

October, 7 Paola
Dataset Distillation Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba, Alexei A. Efros. arXiv preprint arXiv:1811.10959 (2019).

September, 30 Ziyan
WSOD2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection. Zhaoyang Zeng, Bei Liu, Jianlong Fu, Hongyang Chao, Lei Zhang. ICCV 2019.

September, 23 Fuwen
YOLACT: Real-time Instance Segmentation. Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee. arXiv preprint arXiv:1904.02689 (2019).

September, 16 Jeffrey
Bert: Pre-training of deep bidirectional transformers for language understanding. Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova. NAACL 2019.

Schedule - Spring 2017 Meeting Bi-weekly on Wednesdays from 3pm to 4pm in Rice Hall 304
DatePresenter(s)Topic(s)
February, 1st Xuwang

Tianlu
Commonly Uncommon: Semantic Sparsity in Situation Recognition. Mark Yatskar, Vicente Ordonez, Luke Zettlemoyer, Ali Farhadi. arXiv:1612.00901. December 2016.

A Hierarchical Approach for Generating Descriptive Image Paragraphs. Jonathan Krause, Justin Johnson, Ranjay Krishna, Li Fei-Fei. arXiv:1611.06607. November 2016.
February, 15th Siva

Abhimanyu
Sequence to Sequence - Video to Text Subhashini Venugopalan, Marcus Rohrbach, Jeff Donahue, Ray Mooney, Trevor Darrell, Kate Saenko. ICCV 2015

March, 1st Xuwang

Tianlu
Generating Sequences With Recurrent Neural Networks. Alex Graves. arXiv:1308.0850

Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN). Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, Zhiheng Huang, Alan Yuille. ICLR 2015.
March, 15th Everyone ICCV Review Session
March, 29th Siva

Abhimanyu
Zero-Shot Learning-The Good, the Bad and the Ugly. Xian, Yongqin, Bernt Schiele, and Zeynep Akata.. arXiv preprint arXiv:1703.04394 (2017).
April, 26th Siva Pointer networks. Vinyals, Oriol, Meire Fortunato, and Navdeep Jaitly. Advances in Neural Information Processing Systems. 2015.

Department of Computer Science @ The University of Virginia ‒ 85 Engineer's Way, Rice Hall, Charlottesville, VA 22904-4740