Asim Kadav

I am co-founder of eigen that provides scalable video reasoning AI. Our entry market is retail. eigen is currently funded by NEC-X and NECLA.

eigen has built the world's first real-time action recognition and video understanding system. Our patented methods learn object interactions in video streams to perform extremely efficient higher-order scene understanding. With extensive applications in retail, healthcare, and other domains, eigenprovides real-time and timely alerts for various events and automate various store operations.

My team has built eigenconsole that runs on the cloud (AWS) and can scale upto thousands of streams into it for cloud-based AI processing. Our efficient AI video algorithms only use $1/camera/day for streaming and inference and these costs can be reduced further. eigen has a web frontend and we recently added support for iOS/Android playback. eigen has signed several pilots in SF Bay Area and is running live serving 150+ streams.

As a Senior Researcher at NEC Labs,. my students and I have built extremely efficient image classification, video classification, video retrieval and pose tracking methods. I am also the Founder of Eigen based on my research on efficient video understanding.

Email: firstname@nec-labs.com

Recent Publications | All | Students

  • Hopper: Multi-hop Transformer for Spatiotemporal Reasoning. In ICLR 2021. PDF. Honglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf.
  • S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation. Yizhe Zhu, Martin Renqiang Min, Asim Kadav, Hans Peter Graf.
    In CVPR 2020.
  • Tripping Through Time: Efficient Localization of Activities in Videos. (Spotlight) Meera Hahn, Asim Kadav, James M. Rehg, Hans Peter Graf.
    In CVPR Workship on Language and Vision, 2019. Also, appears in BMVC'20. PDF.
  • Visual Entailment: A Novel Task for Fine-Grained Image Understanding. Ning Xie, Farley Lai, Derek Doran, Asim Kadav.
    In NeurIPS Workshop on Visually-Grounded Interaction and Language, 2018 (ViGIL’18). PDF.Dataset.
  • Teaching Syntax using Adverserial Distraction. Juho Kim, Christopher Malon, and Asim Kadav. In FEVER-EMNLP, 2018. PDF.
  • Attend and Interact: Higher-Order Object Interactions for Video Understanding. Chih-Yao Ma, Asim Kadav, Iain Melvin, Zsolt Kira, Ghassan AlRegib, and Hans Peter Graf. In CVPR, 2018. PDF. Video NEC Video. Live Demo.
  • DeepConfig: Automating Data Center Network Topologies Management with Machine Learning. Christopher Streiffer, Huan Chen, Theophilus Benson, Asim Kadav. SIGCOMM Net AI Workshop, 2018. PDF.
  • ASAP: Asynchronous Approximate Data-Parallel Computation.
    Asim Kadav and Erik Kruus. arXiv Preprint. Dec 2016. PDF. Code.

Service: