影响力指数

56.73/100

前 5.8%

全站排名 #3,745

发表论文11 篇

平均评分5.7

年均产出3.7 篇/年

Anurag Arnab

Research Scientist@Google·法国·OpenReview

研究方向

transformer · video · 3d human pose · deep learning · computer vision · segmentation

VoCap: video object captioning and segmentation from any prompt

ICLR 2026Rejected

What Are You Doing? A Closer Look at Controllable Human Video Generation

ICLR 2026Withdrawn

Dense Video Object Captioning from Disjoint Supervision

ICLR 2025Spotlight

Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers

NeurIPS 2025Poster

Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames

NeurIPS 2025Poster

Progressive Data Dropout: An Embarrassingly Simple Approach to Train Faster

NeurIPS 2025Poster

Towards Optimal Adapter Placement for Efficient Transfer Learning

ICLR 2025Rejected

合作者 (20)

Cordelia Schmid

Paul Hongsuck Seo