Open-World Video Object Detection and Segmentation Challenge

Workshop and Challenge @ ICCV 2021 Oct. 16th

~~URL:~~ ~~https://fb.zoom.us/j/93681340357?pwd=eU1hNW1Wb SzdScC9HVjRkSFlsdjRWdz09~~

Workshop Schedule

Recordings are available at:

Start: 8:00 AM (EDT)

8:00 - 8:15: Du Tran - Opening remarks
8:15 - 8:45: Jason Corso - Invited speaker talk 1
8:45 - 8:55: Dahun Kim - Invited paper talk 1: Learning Open-World Object Proposals without Learning to Classify.
8:55 - 9:05: Jonathon Luiten - Invited paper talk 2: Opening up Open-World Tracking.
9:05 - 9:15: Yuqing Wang - Invited paper talk 3: End-to-End Video Instance Segmentation with Transformers.
9:15 - 9:30 Break
9:30 - 10:00 Kristen Grauman - invited speaker talk 2
10:00 - 10:25: Weiyao Wang - Competition results & summary
10:25 - 10:45: Yuming Du - Competition winner talks
10:45 - 11:15: Ross Girshick - Invited speaker talk 3
11:15 - 11:25: Drew Jaegle - Invited paper talk 4: Perceiver: General Perception with Iterative Attention.
11:25 - 11:35: Drew Hudson - Invited paper talk 5: GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering.
11-35 - 11:45: Saquib Sarfraz - Invited paper talk 6: Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation.
11:45 - 12:00: Vivek Sharma Closing

Invited Speakers

Jason Corso

Jason J. Corso is currently director of the Stevens Institute for Artificial Intelligence and a professor of Computer Science at Stevens Institute of Technology. He received his Ph.D. in Computer Science at The Johns Hopkins University in 2005. He is a recipient of the NSF CAREER award (2009), ARO Young Investigator award (2010), Google Faculty Research Award (2015) and on the DARPA CSSG. He is also the Co-Founder and CEO of Voxel51, a computer vision tech startup that builds the leading open-source tool for creating flexible workflows in dataset curation and model interpretation, https://fiftyone.ai.

Ross Girshick

Ross Girshick is a research scientist at Facebook AI Research (FAIR), working on computer vision and machine learning. He received a PhD in computer science from the University of Chicago under the supervision of Pedro Felzenszwalb in 2012. Prior to joining FAIR, Ross was a researcher at Microsoft Research, Redmond and a postdoc at the University of California, Berkeley, where he was advised by Jitendra Malik and Trevor Darrell. His interests include instance-level object understanding and visual reasoning challenges that combine natural language processing with computer vision. He received the 2017 PAMI Young Researcher Award and is well-known for developing the R-CNN (Region-based Convolutional Neural Network) approach to object detection. In 2017, Ross also received the Marr Prize at ICCV for "Mask R-CNN".

Kristen Grauman

Kristen Grauman is a Research Scientist in Facebook AI Research (FAIR) and a Professor in the Department of Computer Science at the University of Texas at Austin. Her research in computer vision and machine learning focuses on visual recognition, video, egocentric perception, and embodied AI. She received her Ph.D. at MIT in 2006. She is an IEEE Fellow, AAAI Fellow, Sloan Fellow, and recipient of the Computers and Thought Award. She and her collaborators have been recognized with several best paper awards, including a 2011 Marr Prize and a 2017 Helmholtz Prize. She served as Program Chair of NeurIPS 2018 and CVPR 2015 and is an Associate Editor-in-Chief for the Transactions on Pattern Analysis and Machine Intelligence (PAMI).

Organizers