VisLang - Vision, Language and Learning Lab at Rice University
Research group at Rice University led by Vicente Ordonez, working at the intersection of computer vision, natural language …
vislang.ai
@inproceedings{smith2023construct, title = {ConStruct-VL: Data-Free Continual Structured VL Concepts Learning.}, author = {Smith, …
MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible …
Universal multimodal embedding models have achieved great success in capturing semantic relevance between queries and …
Learning to Name Objects - VisLang Lab
Learning to Name Objects by Vicente Ordonez, Wei Liu, Jia Deng, Yejin Choi, Alexander C. Berg, Tamara L. Berg.. Communications …
Chat-crowd: A Dialog-based Platform for Visual Layout Composition
본 논문에서 우리는 대화형 상호작용을 통한 시각적 레이아웃 구성을 위한 인터랙티브 환경인 Chat-crowd를 소개한다. Chat-crowd는 두 …
On the Transferability of Visual Features in Generalized Zero-Shot ...
Generalized Zero-Shot Learning (GZSL) nhằm huấn luyện một bộ phân loại có thể khái quát hóa sang các lớp chưa thấy, sử dụng …
Gender Bias in Coreference Resolution: Evaluation and Debiasing …
Wir führen einen neuen Benchmark, WinoBias, für die Koreferenzauflösung mit Fokus auf geschlechtsbezogene Verzerrungen ein. …
One Model, Many Budgets: Elastic Latent Interfaces for Diffusion ...
Diffusion transformers (DiTs) achieve high generative quality but lock FLOPs to image resolution, limiting principled latency-quality …
FlexEControl: Flexible and Efficient Multimodal Control for Text-to ...
Các mô hình khuếch tán text-to-image (T2I) có thể điều khiển tạo ra các ảnh được điều kiện trên cả lời nhắc văn bản lẫn các đầu …
Learning from Synthetic Data for Visual Grounding - VisLang Lab
이 논문은 텍스트 설명을 이미지 영역에 그라운딩하는 비전-언어 모델의 능력을 향상시키기 위한 합성 학습 데이터의 효과를 광범위하게 …
Publications - VisLang Lab at Rice University
Academic publications from the VisLang Lab at Rice University on computer vision, natural language processing, and machine learning.