AI

IBM Research at CVPR 2020

Share this post:

Like so many events impacted the COVID-19 pandemic, the annual conference on Computer Vision and Pattern Recognition (CVPR 2020), has gone virtual. It’s an interesting time for all of us as we find new ways of working and opportunities to apply our research to help our communities.

IBM CEO Arvind Krishna recently sent a letter to the United States Congress outlining detailed policy proposals to advance racial equality in the U.S. He also shared, in the context of addressing responsible use of technology by law enforcement, that IBM has sunset its general-purpose facial recognition and analysis software products.

Though we do not focus on facial recognition research, IBM Research AI continues in its quest to give AI systems sight. Our computer vision research explores a variety of areas within computer vision and multimedia, with a focus on multimodal perception (jointly modeling vision, sound, and language), video understanding, and “learning more from less” — i.e., developing more accurate models with less data, expertise, and effort. And we have a firm commitment to delivering secure, trusted AI with research focused on explainability, fairness and bias reduction.

2020 VizWiz Grand Challenge Workshop

A team from IBM Research won the 2020 VizWiz Grand Challenge Workshop focused on building AI systems for captioning images taken by visually impaired individuals.

Image captioning to assist the visually impaired is an important effort under IBM’s Science for Social Good work. This task is challenging as it requires solving many intelligent tasks, such as reading and comprehension of the visual scene, in order to come up with sentences that help the visually impaired to achieve a goal.

Congratulations to the IBM researchers involved (listed alphabetically): Pierre Dognin, Igor Melnyk, Youssef Mroueh, Inkit Padhi, Mattia Rigotti, Jarret Ross  and Yair Schiff.

CVPR Sponsorship

IBM Research is also proudly sponsoring CVPR 2020 as Supporter Sponsor, as well as the Women in Computer Vision Workshop. We hope you’ll visit our virtual booth to see and hear about our latest technology demos, publications and career opportunities, including the AI Residency Program. For more, check out our papers and workshops listed below.

Accepted Papers at CVPR (Main Conference)

  1. Video Instance Segmentation Tracking Chung-Ching Lin, Ying Hung, Rogerio Feris, Linglin He
  2. Leveraging 2D Data to Learn Textured 3D Mesh Generation Paul Henderson, Vagia Tsiminaki, Christoph H. Lampert
  3. Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation Zhonghao Wang, Mo Yu, Yunchao Wei, Rogerio Feris, Jinjun Xiong, Wen-mei Hwu, Thomas S. Huang, Honghui Shi
  4. Non-Adversarial Video Synthesis with Learned Priors Abhishek Aich, Akash Gupta, Rameswar Panda, Rakib Hyder, M. Salman Asif, Amit K. Roy-Chowdhur
  5. Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning Sk Miraj Ahmed, Aske R Lejbolle, Rameswar Panda, Amit K. Roy-Chowdhury
  6. Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining Yiqun Mei, Yuchen Fan, Yuqian Zhou, Lichao Huang, Thomas S. Huang, Honghui Shi
  7. Music Gesture for Visual Sound Separation Chuang Gan, Deng Huang, Hang Zhao, Joshua B. Tenenbaum, Antonio Torralba
  8. Dense Regression Network for Video Grounding Runhao Zeng, Haoming Xu, Wenbing Huag, Peihao Chen, Mingkui Tan, Chuang Gan
  9. Bottom-up Higher-Resolution Networks for Multi-Person Pose Estimation Bowen Cheng, Bin Xiao, Jingdong Wang, Honghui Shi, Thomas Huang, Lei Zhang
  10. Towards Verifying Robustness of Neural Networks against Semantic Perturbations Jeet Mohapatra, Lily Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel
  11. Adversarial Robustness: From Self-Supervised Pretraining to Fine-Tuning Tianlong Chen, Sijia Liu , Shiyu Chang, Yu Cheng, Lisa Amini, Zhangyang Wang

Accepted Papers at CVPR (Workshops)

1. Improving the affordability of robustness training for DNNs

Workshop on Adversarial Machine Learning in Computer Vision

Sidharth Gupta, Parijat Dube, Ashish Verma

2. Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation

Workshop on Visual Learning with limited labels: zero-shot, few-shot, any-shot, and cross-domain few-shot learning

Zhonghao Wang, Yunchao Wei, Rogerio Feris, Jinjun Xiong, Wen-Mei Hwu, Thomas H. Huang, Honghui Shi

3. Relationship Matters: Relation Guided Knowledge Transfer for Incremental Learning of Object Detectors

Workshop on Continual Learning in Computer Vision

Kandan Ramakrishnan, Rameswar Panda, Quanfu Fan, John Henning, Aude Oliva, Rogerio Feris

4. StarNet: towards weakly supervised few-shot detection and explainable few-shot classification

Workshop on Visual Learning with limited labels: zero-shot, few-shot, any-shot, and cross-domain few-shot learning

Leonid Karlinsky, Joseph Shtok, Amit Alfassy, Moshe Lichtenstein, Sivan Harary, Eli Schwartz, Sivan Doveh, Prasanna Sattigeri, Rogerio Feris, Alexander Bronstein, Raja Giryes

5. MetAdapt: Meta-Learned Task-Adaptive Architecture for Few-Shot Classification

Workshop on Visual Learning with limited labels: zero-shot, few-shot, any-shot, and cross-domain few-shot learning

Leonid Karlinsky, Joseph Shtok, Amit Alfassy, Moshe Lichtenstein, Sivan Harary, Eli Schwartz, Sivan Doveh, Prasanna Sattigeri, Rogerio Feris, Alexander Bronstein, Raja Giryes

6. TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification

Workshop on Visual Learning with limited labels: zero-shot, few-shot, any-shot, and cross-domain few-shot learning

Moshe Lichtenstein, Prasanna Sattigeri, Rogerio Feris, Raja Giryes, Leonid Karlinsky

7. P2L: Predicting Transfer Learning for Images and Semantic Relations

Deep Vision Workshop

Bhattacharjee, J. Kender, M. Hill, P. Dube, S. Huo, M.R. Glass, B.M. Belgodere, S. Pankanti, N.C. Codella, and P. Watson.

8.  Self-Supervised Object Detection and Retrieval Using Unlabeled Videos

Workshop on Multimodal Learning

Elad Amrani, Rami Ben-Ari, Inbar Shapira, Tal Hakim, Alex Bronstein

Workshops Organized by IBM

  1. Workshop on Visual Understanding by Learning from Web Data Wen Li, Hilde Kuehne, Suman Saha, Qin Wang, Limin Wang, Wei Li, Jesse Berent, Abhinav Gupta, Rahul Sukthankar, Luc Van Gool.
  2. Language & Vision with applications to Video Understanding Qi Wu, Xin Wang, Chenxi Liu, Licheng Yu, Lu Jiang, Yan Huang, Ting Yao, Qin Jin, William Wang, Anton van den Hengel, Andrei Barbu, Siddharth N., Dan Gutfreund, Philip Torr.
  3. 5th International Skin Imaging Collaboration (ISIC) Workshop on Skin Image Analysis Emre Celebi, Noel C. F. Codella, Kristin Dana, Allan Halpern, Philipp Tschandl, Marc Combalia.
  4. DIRA Workshop and Challenge Diagram Image Retrieval and Analysis (DIRA): Representation, Learning, and Similarity Metrics Liping Yang, Subarna Tripathi, Adriana Kovashka, Rogerio Feris, Brendt Wohlberg, Diane Oyen.
  5. Fair, Data-Efficient and Trusted Computer Vision Nalini Ratha, Mayank Vatsa, Richa Singh, Kush Varshney, Michele Merler, Karthik Nandakumar, Sharath Pankanti, Vishal Patel, Kuan-Chuan Peng, Ziyan Wu, Zeynep Akata, Srikrishna Karanam, Adriana Kovashka, Rama Chellappa, Rogerio Feris.
  6. 6th International Workshop on Computer Vision in Sports (CVsports) Thomas Moeslund, Graham Thomas, Adrian Hilton, Jim Little, Michele Merler, Rikke Gade.
  7. Neural Architecture Search and Beyond for Representation Learning Radu Timofte, Ming-Hsuan Yang, Shuhang Gu, Martin Danelljan, Kai Zhang, Zhiwu Huang, Kyoung Mu Lee, Lei Zhang, Eli Shechtman, Seungjun Nah, Luc Van Gool, Boaz Arad, Abdelrahman Abdelhamed, Mahmoud Afifi, Cosmin Ancuti, Codruta Ancuti.
  8. 3rd Workshop on Computer Vision For Fashion, Art and Design Hui Wu, Negar Rostamzadeh, Yuying Ge, Wei Zhang, Leonidas Lefakis, Xiaoxiao Guo, Ruimao Zhang, Chris Pal, Rogerio Feris.
  9. Visual Learning with limited labels: zero-shot, few-shot, any-shot, and cross-domain few-shot learning Rogerio Feris, Leonid Karlinsky, Bishwaranjan Bhattacharjee, Noel Codella, Joseph Shtok, Alex Bronstein.

Tutorials

  1. Neuro-Symbolic Visual Reasoning and Program Synthesis Jiayuan Mao, Kevin Ellis, Chuang Gan, Jiajun Wu, Danny Gutfreund, Josh Tenenbaum
  2. Zeroth Order Optimization: Theory and Applications to Deep Learning Pin-Yu Chen, Sijia Liu

Talks

Sharath Pankanti

Keynote talk at The 1st International Workshop and Prize Challenge on Agriculture-Vision: Challenges & Opportunities for Computer Vision in Agriculture

Kate Saenko
Keynote talk at 2020 VizWiz Grand Challenge Workshop

Chieko Asakawa
Keynote Talk at 2020 VizWiz Grand Challenge Workshop

Lingfei Wu
Keynote talk at DIRA Workshop And Challenge

John R. Smith
Keynote talk at Workshop on Computer Vision in Sports (CVsports) at CVPR 2020
Keynote talk at Visual Learning with Limited Labels Workshop

Pin-Yu Chen
Keynote talk at Adversarial Machine Learning in Computer Vision  

Hui Wu
Keynote talk at The Workshop on Computer Vision For Fashion, Art and Design

Rogerio Feris
Keynote talk at DIRA Workshop And Challenge

Inventing What’s Next.

Stay up to date with the latest announcements, research, and events from IBM Research through our newsletter.

 

Principal RSM and Manager, Computer Vision and Multimedia Department, IBM Research

More AI stories

We’ve moved! The IBM Research blog has a new home

In an effort better integrate the IBM Research blog with the IBM Research web experience, we have migrated to a new landing page: https://research.ibm.com/blog

Continue reading

Pushing the boundaries of human-AI interaction at IUI 2021

At the 2021 virtual edition of the ACM International Conference on Intelligent User Interfaces (IUI), researchers at IBM will present five full papers, two workshop papers, and two demos.

Continue reading

From HPC Consortium’s success to National Strategic Computing Reserve

Founded in March 2020 just as the pandemic’s wave was starting to wash over the world, the Consortium has brought together 43 members with supercomputing resources. Private and public enterprises, academia, government and technology companies, many of whom are typically rivals. “It is simply unprecedented,” said Dario Gil, Senior Vice President and Director of IBM Research, one of the founding organizations. “The outcomes we’ve achieved, the lessons we’ve learned, and the next steps we have to pursue are all the result of the collective efforts of these Consortium’s community.” The next step? Creating the National Strategic Computing Reserve to help the world be better prepared for future global emergencies.

Continue reading