Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
Paper • 2203.07845 • Published
Zexin He
zxhezexin
AI & ML interests
None yet
Recent Activity
upvoted a paper 13 days ago
Efficient Reasoning with Balanced Thinking new activity 3 months ago
KarlP/droid:Non one-to-one mapping between episode ID and TFDS path upvoted a paper 4 months ago
Wan-Move: Motion-controllable Video Generation via Latent Trajectory GuidanceOrganizations
authored 5
papers over 1 year ago
Video Background Music Generation with Controllable Music Transformer
Paper • 2111.08380 • Published • 1
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need
Paper • 2302.02615 • Published
Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion
Paper • 2412.09593 • Published • 18
Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
Paper • 2409.11406 • Published • 27