My research focus is on video understanding, with the goal to build machine intelligence that understands and anticipates human activities, and ultimately develop autonomous machines that interact with and assist us in unconstrained environments. My research has been recognized by two winning entries at COCO object detection challenge 2016 and iNaturalist challenge 2017, a best paper finalist at CVPR 2019 and media coverage from WIRED, TechCrunch, etc.