Particularly agree with 2

Good news for video researchers: Kinetics dataset is available on Common Visual Data Foundation: github.com/cvdfoundation/…. No need to worry about the shrinking size of Kinetics. Thanks joao carreira for the great work!

I just registered for ICLR 2021! iclr.cc

#ICCV2021 cam ready: "Social Fabric: Tubelet Compositions for Video Relation Detection" w/ Shuo Chen, Zenglin Shi, Pascal Mettes arxiv.org/abs/2108.08363 TL;DR We classify and detect predicates for pairs of object tubelets a priori, rather than a posteriori. 1/n

#BMVC2021: Diagnosing Errors in Video Relation Detectors w/ Shuo Chen, Pascal Mettes TL;DR deep dive into the #error #diagnosis of current #video #relation detection approaches 1/n isis-data.science.uva.nl/cgmsnoek/pub/c…

perceiving-systems.blog/en/news/novelt…

Very glad to see mostly onsite presentations during the first oral session of ICMR 2023! "Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation" currently being presented. ACM SIGMM Association for Computing Machinery #icmr2023 #multimedia #retrieval #AI #graphs

Thank you very much 😄

Glad to share our team's recent T2V work!