mlsanityData to 7 Oct 2026

Question Generation for Evaluating Cross-Dataset Shifts in Multi-modal Grounding

arXiv 2201.09639 ↗First posted 24 Jan 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Visual question answering (VQA) is the multi-modal task of answering natural language questions about an input image. Through cross-dataset adaptation methods, it is possible to transfer knowledge from a source dataset with larger train samples to a target dataset where training set is limited. Suppose a VQA model trained on one dataset train set fails in adapting to another, it is hard to identify the underlying cause of domain mismatch as there could exists a multitude of reasons such as image distribution mismatch and question distribution mismatch. At UCLA, we are working on a VQG module that facilitate in automatically generating OOD shifts that aid in systematically evaluating cross-dataset adaptation capabilities of VQA models.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 24 Jan 2022.

Builds on

16 of 37 references.

References · 16

  1. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  2. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  3. 2015VQA: Visual Question Answeringcited by 2,489
  4. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  5. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  6. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
  7. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 852
  8. 2015Visual7W: Grounded Question Answering in Imagescited by 315
  9. 2020Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressionscited by 33
  10. 2020DeFormer: Decomposing Pre-trained Transformers for Faster Question Answeringcited by 29
  11. 2020Evaluating Models' Local Decision Boundaries via Contrast Setscited by 24
  12. 2018Cross-Dataset Adaptation for Visual Question Answeringcited by 17
4 more
  1. 2019Natural Language Interaction with Explainable AI Modelscited by 8
  2. 2019X-ToM: Explaining with Theory-of-Mind for Gaining Justified Human Trustcited by 8
  3. 2022Effective Representation to Capture Collaboration Behaviors between Explainer and Usercited by 4
  4. 2022Discourse Analysis for Evaluating Coherence in Video Paragraph Captionscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1.

3 papers.

  1. 2023Grounded Image Text Matching with Mismatched Relation Reasoningcited by 8
  2. 2022Attention cannot be an Explanationcited by 4
  3. 2022On the Importance of Karaka Framework in Multi-modal Groundingcited by 0