CoChat

Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models

Pan, Junting, Lin, Ziyi, Ge, Yuying, Zhu, Xiatian, Zhang, Renrui, Wang, Yi, Qiao, Yu, Li, Hongsheng · 2023 · 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Cited by 27

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.

Abstract

Video Question Answering (VideoQA) has been significantly advanced from the scaling of recent Large Language Models (LLMs). The key idea is to convert the visual information into the language feature space so that the capacity of LLMs can be fully exploited. Existing VideoQA methods typically take two paradigms: (1) learning cross-modal alignment, and (2) using an off-the-shelf captioning model to describe the visual data. However, the first design needs costly training on many extra multi-modal data, whilst the second is further limited by limited domain generalization. To address these limitations, a simple yet effective Retrieving-to-Answer (R2A) framework is proposed. Given an input video, R2A first retrieves a set of semantically similar texts from a generic text corpus using a pre-trained multi-modal model (e.g., CLIP). With both the question and the retrieved texts, a LLM (e.g., DeBERTa) can be directly used to yield a desired answer. Without the need for cross-modal fine-tuning, R2A allows for all the key components (e.g., LLM, retrieval model, and text corpus) to plug-and-play. Extensive experiments on several VideoQA benchmarks show that despite with 1.3B parameters and no fine-tuning, our R2A can outperform the 61× larger Flamingo-80B model [1] even additionally trained on nearly 2.1B multi-modal data.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/iccvw60793.2023.00035

Cites

22 of 22 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 22 references

Research works printed but not linked: 43

  1. 10.1109/CVPR46437.2021.00356 · DOI · Paper page
  2. 10.1109/CVPR52688.2022.01750 · DOI · Paper page
  3. 10.1609/aaai.v35i2.16203 · DOI
  4. 10.1109/IJCNN52387.2021.9533961 · DOI
  5. Guo, Accelerating large-scale inference with anisotropic vector quantization, 3887
  6. Guo, Accelerating large-scale inference with anisotropic vector quantization, 3887
  7. Hu, 2023, Open-domain visual entity recognition: Towards recognizing millions of wikipedia entities, 10.1109/ICCV51070.2023.01108 · DOI
  8. 10.1109/ICCV.2013.457 · DOI
  9. 10.18653/v1/2021.eacl-main.74 · DOI · Paper page
  10. 10.1109/CVPR.2017.149 · DOI · Paper page
  11. 10.1109/cvpr52729.2023.00638 · DOI · Paper page
  12. 10.1609/aaai.v35i14.17556 · DOI
  13. 10.1109/CVPR46437.2021.00725 · DOI · Paper page
  14. Lewis, 2020, Pre-training via paraphrasing, Advances in Neural Information Processing Systems, 33, 18470
  15. 10.1109/CVPR52688.2022.00294 · DOI
  16. 10.1007/978-3-319-10602-1_48 · DOI · Paper page
  17. 10.1109/CVPR46437.2021.00693 · DOI
  18. 10.1109/CVPR.2015.7298748 · DOI · Paper page
  19. 10.1109/CVPR52688.2022.00683 · DOI · Paper page
  20. 10.18653/v1/2023.eacl-main.185 · DOI
  21. 10.18653/v1/2022.findings-emnlp.67 · DOI · Paper page
  22. 10.1007/978-3-031-19781-9_24 · DOI
  23. 10.1109/CVPR46437.2021.01527 · DOI
  24. 10.1109/CVPR.2018.00918 · DOI · Paper page
  25. Radford, Learning transferable visual models from natural language supervision, 139, 8748
  26. 10.1109/cvpr52729.2023.00278 · DOI · Paper page
  27. 10.18653/v1/2021.naacl-main.196 · DOI
  28. 10.1145/3549555.3549585 · DOI · Paper page
  29. 10.1109/CVPR52688.2022.01743 · DOI · Paper page
  30. 10.1109/CVPR46437.2021.01660 · DOI
  31. 10.1109/ICCV.2019.00756 · DOI · Paper page
  32. 10.1145/2812802 · DOI · Paper page
  33. 10.1109/CVPR46437.2021.00965 · DOI · Paper page
  34. 10.1609/aaai.v36i3.20184 · DOI
  35. 10.1145/3123266.3123427 · DOI · Paper page
  36. 10.1145/3123266.3123427 · DOI · Paper page
  37. 10.18653/v1/2021.emnlp-main.544 · DOI · Paper page
  38. 10.1109/ICCV48922.2021.00171 · DOI · Paper page
  39. 10.1609/aaai.v36i3.20215 · DOI · Paper page
  40. 10.1109/CVPR52688.2022.01589 · DOI · Paper page
  41. Zellers, 2021, Merlot: Multimodal neural script knowledge models, Advances in Neural Information Processing Systems, 34
  42. 10.1109/CVPR46437.2021.00971 · DOI
  43. 10.18653/v1/2022.emnlp-main.432 · DOI

Cited by

See all 27

Metadata

Authors
Pan, J., Lin, Z., Ge, Y., Zhu, X., Zhang, R., Wang, Y., Qiao, Y., & Li, H.
Affiliations
  • The Chinese University of Hong Kong,Multimedia Lab
  • University of Hong Kong
  • University of Surrey
  • Shanghai AI Laboratory
Venue
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Publisher
IEEE
Published
2023-10-02
Pages
272-283
Cited by
27
References
22

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models. https://app.cochat.ai/papers/10.1109/iccvw60793.2023.00035
The paper
Pan, J., Lin, Z., Ge, Y., Zhu, X., Zhang, R., Wang, Y., Qiao, Y., & Li, H. (2023). Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models. 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). https://doi.org/10.1109/iccvw60793.2023.00035

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.