Marcus Rohrbach

Affiliations

TU Darmstadt

papers

3,215

total citations

papers (14)

KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA

CVPR 2021arXiv

231

citations

Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA

CVPR 2020arXiv

226

citations

Adversarial Continual Learning

ECCV 2020arXiv

224

citations

Learning To Recognize Procedural Activities With Distant Supervision

CVPR 2022arXiv

citations

Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly

ECCV 2022arXiv

citations

Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition

ECCV 2022arXiv

citations

CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition

ECCV 2022arXiv

citations

Improving Selective Visual Question Answering by Learning From Your Peers

CVPR 2023arXiv

citations

Efficient Pre-training for Localized Instruction Generation of Procedural Videos

ECCV 2024

citations

V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts

CVPR 2025

citations

Marcus Rohrbach

Affiliations

papers (14)

FLAVA: A Foundational Language and Vision Alignment Model

TextCaps: a Dataset for Image Captioning with Reading Comprehension

12-in-1: Multi-Task Vision and Language Representation Learning

In Defense of Grid Features for Visual Question Answering

KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA

Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA

Adversarial Continual Learning

Learning To Recognize Procedural Activities With Distant Supervision

Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly

Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition

CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition

Improving Selective Visual Question Answering by Learning From Your Peers

Efficient Pre-training for Localized Instruction Generation of Procedural Videos

V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts

papers (14)

FLAVA: A Foundational Language and Vision Alignment Model

TextCaps: a Dataset for Image Captioning with Reading Comprehension

12-in-1: Multi-Task Vision and Language Representation Learning

In Defense of Grid Features for Visual Question Answering

KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA

Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA

Adversarial Continual Learning

Learning To Recognize Procedural Activities With Distant Supervision

Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly

Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition

CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition

Improving Selective Visual Question Answering by Learning From Your Peers

Efficient Pre-training for Localized Instruction Generation of Procedural Videos

V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts