Lecture by Dr. Ratnesh Kumar “Vehicle Re-identification for Smart Cities: A New Baseline Using Triplet Embedding”

Share

Dr. Ratnesh Kumar, Deep Learning Architect, Nvidia Corporation, San Jose, CA

Event Organized By:

Circuits and Systems Society (CASS) of the IEEE Santa Clara Valley Section

Co-sponsors:

PROGRAM:

6:00 - 6:30 PM Networking & Refreshments
6:30 - 7:45 PM Talk
7:45 - 8:00 PM Q&A/Adjourn

Watch the lecture live on Zoom from your home and anywhere around the world! Register now and you will be sent details one day before the event.

Abstract:

With the proliferation of surveillance cameras enabling smart and safer cities, there is an ever-increasing need to re-identify vehicles across cameras. Typical challenges arising in smart city scenarios include variations of viewpoints, illumination and self occlusions. In this talk we will discuss an exhaustive evaluation of deep embedding losses applied to vehicle re-identification, and demonstrate that using the best practices for learning-embeddings outperform most of the previous approaches in vehicle re-identification.

Bio:

Ratnesh Kumar is currently a Deep Learning Architect at Nvidia USA from January 2017. He has obtained his PhD from STARS team at Inria, France in Dec 2014. His research focus during PhD was on long term video segmentation using optical flow and multiple object tracking. Subsequently he worked as Postdoc at Mitsubishi Electric Research Labs (MERL) Cambridge, Boston, on detection actions in streaming videos. He also holds Bachelors in Engineering from Manipal University, India and Master of Science from University of Florida at Gainesville, USA. At Nvidia since 2017, his focus is on leveraging deep learning on hardware accelerated GPU platforms to solve several problems in video analytics ranging from object detection to re-identification and action detection, with low latency and high data throughput. He is co-author of 9 scientific publications in conferences and journals and has several patents pending. He is also a plenary speaker at IEEE International Conference on Image Processing Applications and Systems (IPAS) 2018. He has also served as organizing member for AI-CITIES 2018 challenge for smart cities.

Venue:

Cypress Semiconductor Corporation, Main Auditorium in Building 6, 198 Champion Ct, San Jose, CA 95134

Convenient VTA light rail access from Mountain View and downtown San Jose.

Live Broadcast:

Lecture will be broadcast live on Zoom. Registrants will be sent the conference details one day before the event.

Admission Fee:

Non-IEEE: $5

Students (non-IEEE): $3

IEEE Members (not members of CASS or SSCS): $3

IEEE CASS and SSCS Members: Free

Open to all to attend.

Online registration is recommended to guarantee seating.



  Date and Time

  Location

  Contact

  Registration



  • Cypress Semiconductor Corporation
  • 198 Champion Ct,
  • San Jose, California
  • United States 95134
  • Building: Main Auditorium in Building 6
  • Click here for Map
  • Co-sponsored by Solid State Circuits Society (SSCS)


  Speakers

Ratnesh Kumar of Nvidia Corporation, San Jose

Topic:

Lecture by Dr. Ratnesh Kumar “Vehicle Re-identification for Smart Cities: A New Baseline Using Triplet Embedding”

With the proliferation of surveillance cameras enabling smart and safer cities, there is an ever-increasing need to re-identify vehicles across cameras. Typical challenges arising in smart city scenarios include variations of viewpoints, illumination and self occlusions. In this talk we will discuss an exhaustive evaluation of deep embedding losses applied to vehicle re-identification, and demonstrate that using the best practices for learning-embeddings outperform most of the previous approaches in vehicle re-identification.

Biography:

Ratnesh Kumar is currently a Deep Learning Architect at Nvidia USA from January 2017. He has obtained his PhD from STARS team at Inria, France in Dec 2014. His research focus during PhD was on long term video segmentation using optical flow and multiple object tracking. Subsequently he worked as Postdoc at Mitsubishi Electric Research Labs (MERL) Cambridge, Boston, on detection actions in streaming videos. He also holds Bachelors in Engineering from Manipal University, India and Master of Science from University of Florida at Gainesville, USA. At Nvidia since 2017, his focus is on leveraging deep learning on hardware accelerated GPU platforms to solve several problems in video analytics ranging from object detection to re-identification and action detection, with low latency and high data throughput. He is co-author of 9 scientific publications in conferences and journals and has several patents pending. He is also a plenary speaker at IEEE International Conference on Image Processing Applications and Systems (IPAS) 2018. He has also served as organizing member for AI-CITIES 2018 challenge for smart cities.





Agenda

With the proliferation of surveillance cameras enabling smart and safer cities, there is an ever-increasing need to re-identify vehicles across cameras. Typical challenges arising in smart city scenarios include variations of viewpoints, illumination and self occlusions. In this talk we will discuss an exhaustive evaluation of deep embedding losses applied to vehicle re-identification, and demonstrate that using the best practices for learning-embeddings outperform most of the previous approaches in vehicle re-identification.