影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
60.37/100
前 4.7%
全站排名 #3,054
发表论文21 篇
平均评分
年均产出7.0 篇/年
Cordelia Schmid
研究方向
robot manipulation and navigation · vision language navigation · 3D semantic understanding and reasoning · video understanding · learning with weak annotations
15
VoCap: video object captioning and segmentation from any prompt
ICLR 2026Rejected
通讯9
CAViAR: Critic-Augmented Video Agentic Reasoning
ICLR 2026Rejected
通讯5
What Are You Doing? A Closer Look at Controllable Human Video Generation
ICLR 2026Withdrawn
通讯5
ComposeAnything: Composite Object Priors for Text-to-Image Diffusion Models
ICLR 2026Withdrawn
三作5
RECODE: Reasoning Through Code Generation for Visual Question Answering
ICLR 2026Rejected
17
What Drives Compositional Generalization in Visual Generative Models?
ICLR 2026Rejected
6
VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation
ICLR 2026Withdrawn
三作5
MaskCaptioner: Learning to jointly segment and caption object trajectories in videos
ICLR 2026Withdrawn
三作16
Dense Video Object Captioning from Disjoint Supervision
ICLR 2025Spotlight
通讯26
Prediction-Powered Causal Inferences
NeurIPS 2025Poster
16
Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
NeurIPS 2025Poster
通讯13
mOSCAR: A Large-scale Multilingual and Multimodal Document-Level Corpus
ICLR 2025Rejected
17
Neptune: The Long Orbit to Benchmarking Long Video Understanding
ICLR 2025Rejected
5
Incrementally Adapting Generative Vision-Language Models with Task Codebook
ICLR 2025Rejected
通讯7
Grounded Video Caption Generation
ICLR 2025Withdrawn
二作