Anna Rohrbach

papers in the register

1. Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents
   ArXiv.org · 2026
   Embodied cognitionComputer scienceArtificial intelligenceInference
2. Diffusion Classifiers Understand Compositionality, but Conditions Apply.
   NeurIPS · 2025
3. Chrono: A Simple Blueprint for Representing Time in MLLMs
   ICCV · 2025
   BlueprintComputer scienceENCODETask (project management)
4. V² Dial: Unification of Video and Visual Dialog via Multimodal Experts
   CVPR · 2025
   DialComputer scienceDialog boxUnification
5. DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts.
   ICML · 2025
6. Simple Token-Level Confidence Improves Caption Correctness.
   WACV · 2024
7. Shape-Guided Diffusion with Inside-Outside Attention.
   WACV · 2024
8. MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding.
   CVPR · 2023
9. More Control for Free! Image Synthesis with Semantic Diffusion Guidance.
   WACV · 2023
10. Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motion.
    WACV · 2023
11. Using Language to Extend to Unseen Domains.
    ICLR · 2023
12. ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension.
    ACL · 2022
13. How Much Can CLIP Benefit Vision-and-Language Tasks?
    ICLR · 2022
14. TL;DW? Summarizing Instructional Videos with Task Relevance and Cross-Modal Saliency.
    ECCV · 2022
15. Exposing the Limits of Video-Text Models through Contrast Sets.
    NAACL · 2022
16. K-LITE: Learning Transferable Visual Models with External Knowledge.
    NeurIPS · 2022
17. DETReg: Unsupervised Pretraining with Region Priors for Object Detection.
    CVPR · 2022
18. The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning.
    ECCV · 2022
19. On Guiding Visual Attention with Language Specification.
    CVPR · 2022
20. G3: Geolocation via Guidebook Grounding.
    EMNLP · 2022
21. Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly.
    ECCV · 2022
22. Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens.
    NeurIPS · 2022
23. Focus! Relevant and Sufficient Context Selection for News Image Captioning.
    EMNLP · 2022
24. Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation.
    NAACL · 2022
25. Object-Region Video Transformers.
    CVPR · 2022
26. NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media.
    EMNLP · 2021
27. Benchmark for Compositional Text-to-Image Synthesis.
    NeurIPS · 2021
28. CLIP-It! Language-Guided Video Summarization.
    NeurIPS · 2021
29. Compositional Video Synthesis with Action Graphs.
    ICML · 2021
30. Identity-Aware Multi-sentence Video Description.
    ECCV · 2020
31. Advisable Learning for Self-Driving Vehicles by Internalizing Observation-to-Action Rules.
    CVPR · 2020
32. Adversarial Inference for Multi-Sentence Video Description.
    CVPR · 2019
33. Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation.
    ACL · 2019
34. Language-Conditioned Graph Networks for Relational Reasoning.
    ICCV · 2019
35. Adversarial Inference for Multi-Sentence Video Description.
    CVPR · 2019
36. Robust Change Captioning.
    ICCV · 2019
37. Fooling Vision and Language Models Despite Localization and Attention Mechanism.
    CVPR · 2018
38. Object Hallucination in Image Captioning.
    EMNLP · 2018
39. Textual Explanations for Self-Driving Vehicles.
    ECCV · 2018
40. Speaker-Follower Models for Vision-and-Language Navigation.
    NeurIPS · 2018
41. Women Also Snowboard: Overcoming Bias in Captioning Models.
    ECCV · 2018
42. Multimodal Explanations: Justifying Decisions and Pointing to the Evidence.
    CVPR · 2018
43. Video Object Segmentation with Referring Expressions.
    ECCV · 2018
44. Generating Descriptions with Grounded and Co-referenced People.
    CVPR · 2017
45. Gradient-free Policy Architecture Search and Adaptation.
    CoRL · 2017
46. A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering.
    CVPR · 2017
47. Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding.
    EMNLP · 2016
48. Grounding of Textual Phrases in Images by Reconstruction.
    ECCV · 2016
49. Commonsense in Parts: Mining Part-Whole Relations from the Web and Image Tags.
    AAAI · 2016
50. A dataset for Movie Description.
    CVPR · 2015

Profile built from publicly available sources (OpenAlex, arXiv; origin per Art. 14 GDPR). Corrections or removal · aisr@hessian.ai