Search Results for author:
Found 10 papers, 5 papers with code
Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models
Advancements in vision-language models (VLMs) have propelled the field of computer vision, particularly in the zero-shot learning setting.
Depth-guided NeRF Training via Earth Mover's Distance
This work proposes a novel approach to uncertainty in depth priors for NeRF supervision.
VideoAgent: Long-form Video Understanding with Large Language Model as Agent
Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences.
Ranked #1 on
Zero-Shot Video Question Answer
on NExT-QA
Training Small Multimodal Models to Bridge Biomedical Competency Gap: A Case Study in Radiology Imaging
Frontier models such as GPT-4V still have major competency gaps in multimodal capabilities for biomedical applications.
Multi-Human Mesh Recovery with Transformers
Conventional approaches to human mesh recovery predominantly employ a region-based strategy.
Revisiting Active Learning in the Era of Vision Foundation Models
Foundation vision or vision-language models are trained on large unlabeled or noisy data and learn robust representations that can achieve impressive zero- or few-shot performance on diverse tasks.
Template-Free Single-View 3D Human Digitalization with Diffusion-Guided LRM
We present Human-LRM, a diffusion-guided feed-forward model that predicts the implicit field of a human from a single image.
Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
However, this assumption is under-explored due to the poorly understood geometry of the multi-modal contrastive space, where a modality gap exists.
Describing Differences in Image Sets with Natural Language
To aid in this discovery process, we explore the task of automatically describing the differences between two $\textbf{sets}$ of images, which we term Set Difference Captioning.
Diffusion-HPC: Synthetic Data Generation for Human Mesh Recovery in Challenging Domains
Recent text-to-image generative models have exhibited remarkable abilities in generating high-fidelity and photo-realistic images.
