Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Efficient Human-Contact Representation for Human-Scene Interaction
Nghia Vu, Tuong Do, Binh X. Nguyen +2
Human-scene interaction is an active research topic with several industrial applications in virtual reality, gaming, robotics, and surveillance. Despite significant progress in net…
cs.CV2026
AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers
Nghia Vu, Tuong Do, Khang Nguyen +8
Affordance learning is a complex challenge in many applications, where existing approaches primarily focus on the geometric structures, visual knowledge, and affordance labels of o…
cs.CV2025
Lightweight Temporal Transformer Decomposition for Federated Autonomous Driving
Tuong Do, Binh X. Nguyen, Quang D. Tran +3
Traditional vision-based autonomous driving systems often face difficulties in navigating complex environments when relying solely on single-image inputs. To overcome this limitati…