pith. sign in

Marcus Rohrbach

Identifiers

  • name variant Marcus Rohrbach 0.60 · backfill

Papers (56)

  1. Obliviate: Erasing Concepts from Autoregressive Image Generation Models cs.CV · 2026 · author #7
  2. Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning cs.LG · 2026 · author #4
  3. Geometric Erasure by Contrastive Velocity Matching in Rectified Flows cs.LG · 2026 · author #4
  4. Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models cs.CR · 2026 · author #5
  5. Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents cs.AI · 2026 · author #6
  6. SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring cs.CV · 2026 · author #2
  7. ReCap: Lightweight Referential Grounding for Coherent Story Visualization cs.CV · 2026 · author #4
  8. HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models cs.CV · 2026 · author #6
  9. VeriTaS: The First Dynamic Benchmark for Multimodal Automated Fact-Checking cs.IR · 2026 · author #3
  10. Variational Visual Question Answering for Uncertainty-Aware Selective Prediction cs.CV · 2025 · author #4
  11. Erased but Not Forgotten: How Backdoors Compromise Concept Erasure cs.CR · 2025 · author #3
  12. Towards VQA Models That Can Read cs.CL · 2019 · author #8
  13. On Tiny Episodic Memories in Continual Learning cs.LG · 2019 · author #2
  14. Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering cs.LG · 2019 · author #4
  15. Cycle-Consistency for Robust Visual Question Answering cs.CV · 2019 · author #3
  16. DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition cs.CV · 2019 · author #5
  17. Exploring the Challenges towards Lifelong Fact Learning cs.CV · 2018 · author #4
  18. Grounded Video Description cs.CV · 2018 · author #5
  19. Adversarial Inference for Multi-Sentence Video Description cs.CV · 2018 · author #2
  20. Efficient Lifelong Learning with A-GEM cs.LG · 2018 · author #3
  21. Graph-Based Global Reasoning Networks cs.CV · 2018 · author #2
  22. Visual Coreference Resolution in Visual Dialog using Neural Module Networks cs.CV · 2018 · author #5
  23. Pythia v0.1: the Winning Entry to the VQA Challenge 2018 cs.CV · 2018 · author #4
  24. Selfless Sequential Learning stat.ML · 2018 · author #2
  25. Multimodal Explanations: Justifying Decisions and Pointing to the Evidence cs.AI · 2018 · author #7
  26. CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication cs.CV · 2017 · author #4
  27. Memory Aware Synapses: Learning what (not) to forget cs.CV · 2017 · author #4
  28. Attentive Explanations: Justifying Decisions and Pointing to the Evidence (Extended Abstract) cs.CV · 2017 · author #7
  29. Learning to Reason: End-to-End Module Networks for Visual Question Answering cs.CV · 2017 · author #3
  30. Generating Descriptions with Grounded and Co-Referenced People cs.CV · 2017 · author #2
  31. Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training cs.CV · 2017 · author #2
  32. Attentive Explanations: Justifying Decisions and Pointing to the Evidence cs.CV · 2016 · author #6
  33. Modeling Relationships in Referential Expressions with Compositional Modular Networks cs.CV · 2016 · author #2
  34. Utilizing Large Scale Vision and Text Datasets for Image Segmentation from Referring Expressions cs.CV · 2016 · author #2
  35. Captioning Images with Diverse Objects cs.CV · 2016 · author #3
  36. Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding cs.CV · 2016 · author #6
  37. Movie Description cs.CV · 2016 · author #3
  38. Ask Your Neurons: A Deep Learning Approach to Visual Question Answering cs.CV · 2016 · author #2
  39. Attributes as Semantic Units between Natural Language and Visual Recognition cs.CV · 2016 · author #1
  40. Generating Visual Explanations cs.CV · 2016 · author #3
  41. Segmentation from Natural Language Expressions cs.CV · 2016 · author #2
  42. Learning to Compose Neural Networks for Question Answering cs.CL · 2016 · author #2
  43. Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data cs.CV · 2015 · author #3
  44. Natural Language Object Retrieval cs.CV · 2015 · author #3
  45. Grounding of Textual Phrases in Images by Reconstruction cs.CV · 2015 · author #2
  46. Neural Module Networks cs.CV · 2015 · author #2
  47. Spatial Semantic Regularisation for Large Scale Object Detection cs.CV · 2015 · author #2
  48. The Long-Short Story of Movie Description cs.CV · 2015 · author #2
  49. A Multi-scale Multiple Instance Video Description Network cs.CV · 2015 · author #4
  50. Ask Your Neurons: A Neural-based Approach to Answering Questions about Images cs.CV · 2015 · author #2
  51. Sequence to Sequence -- Video to Text cs.CV · 2015 · author #2
  52. Recognizing Fine-Grained and Composite Activities using Hand-Centric Features and Script Data cs.CV · 2015 · author #1
  53. A Dataset for Movie Description cs.CV · 2015 · author #2
  54. Translating Videos to Natural Language Using Deep Recurrent Neural Networks cs.CV · 2014 · author #4
  55. Long-term Recurrent Convolutional Networks for Visual Recognition and Description cs.CV · 2014 · author #3
  56. Coherent Multi-Sentence Video Description with Variable Level of Detail cs.CV · 2014 · author #2

Mentions

  • 2606.28643 #7 · arxiv_oai · confidence 0.70 Marcus Rohrbach
  • 2606.16214 #4 · arxiv_oai · confidence 0.70 Marcus Rohrbach
  • 1511.05284 #3 · backfill · confidence 0.70 Marcus Rohrbach
  • 1511.04164 #3 · backfill · confidence 0.70 Marcus Rohrbach
  • 1511.03745 #2 · backfill · confidence 0.70 Marcus Rohrbach
  • 1511.02799 #2 · backfill · confidence 0.70 Marcus Rohrbach
  • 1510.02949 #2 · backfill · confidence 0.70 Marcus Rohrbach
  • 1506.01698 #2 · backfill · confidence 0.70 Marcus Rohrbach
  • 1505.05914 #4 · backfill · confidence 0.70 Marcus Rohrbach
  • 1505.01121 #2 · backfill · confidence 0.70 Marcus Rohrbach
  • 1505.00487 #2 · backfill · confidence 0.70 Marcus Rohrbach
  • 1502.06648 #1 · backfill · confidence 0.70 Marcus Rohrbach
  • 1501.02530 #2 · backfill · confidence 0.70 Marcus Rohrbach
  • 1412.4729 #4 · backfill · confidence 0.70 Marcus Rohrbach
  • 2504.21072 #3 · arxiv_oai · confidence 0.70 Marcus Rohrbach
  • 2606.00140 #4 · arxiv_oai · confidence 0.70 Marcus Rohrbach
  • 1411.4389 #3 · backfill · confidence 0.70 Marcus Rohrbach
  • 1403.6173 #2 · backfill · confidence 0.70 Marcus Rohrbach
  • 2605.19227 #5 · arxiv_oai · confidence 0.70 Marcus Rohrbach

Frequent Coauthors