Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention
Paper • 2410.22306 • Published
Haomeng Zhang
haomengz
AI & ML interests
Computer Vision & Robotics
Recent Activity
upvoted a paper 23 days ago
Tunable Soft Equivariance with Guarantees upvoted a paper 7 months ago
ShapeGen4D: Towards High Quality 4D Shape Generation from Videos upvoted a paper 8 months ago
CLIPSym: Delving into Symmetry Detection with CLIPOrganizations
authored 2
papers 9 months ago