Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image

AdderNet: Do We Really Need Multiplications in Deep Learning?

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera

Deep Learning Recommendation Model for Personalization and Recommendation Systems

node2vec: Scalable Feature Learning for Networks