James Rehg

16

Papers

107

Total Citations

Papers (16)

ZeroShape: Regression-based Zero-shot Shape Reconstruction

Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders

The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective

ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models

PointInfinity: Resolution-Invariant Point Diffusion Models

SocialGesture: Delving into Multi-person Gesture Understanding

Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation

Improving Personalized Search with Regularized Low-Rank Parameter Updates

Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation

SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding

RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models

LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations

Towards Black-box Iterative Machine Teaching