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
38.61/100
前 15.4%
全站排名 #9,935
发表论文4 篇
平均评分
年均产出2.0 篇/年
Hanoona Abdul Rasheed
研究方向
Multi-modal Vision Transformers · Prompt Learning · Adaptation of Vision-language models for downstream tasks · Open Vocabulary Object Detection · Class-agnostic Object Detection · Large Multi-Modal Models (LMM) · Generative AI
16
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
NeurIPS 2025Spotlight
20
Perception Encoder: The best visual embeddings are not at the output of the network
NeurIPS 2025Oral
6
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
ICLR 2025Withdrawn
二作