Papers › Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

16 Jun 2022arXiv:2206.08155archive 2025-07-28

Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev, Cordelia Schmid

Video question answering (VideoQA) is a complex task that requires diverse multi-modal data for training. Manual annotation of question and answers for videos, however, is tedious and prohibits scalability. To tackle this problem, recent methods consider zero-shot settings with no manual annotation of visual question-answer. In particular, a promising approach adapts frozen autoregressive language models pretrained on Web-scale text-only data to multi-modal inputs. In contrast, we here build on frozen bidirectional language models (BiLM) and show that such an approach provides a stronger and cheaper alternative for zero-shot VideoQA. In particular, (i) we combine visual inputs with the frozen BiLM using light trainable modules, (ii) we train such modules using Web-scraped multi-modal data, and finally (iii) we perform zero-shot VideoQA inference through masked language modeling, where the masked text is the answer to a given question. Our proposed approach, FrozenBiLM, outperforms the state of the art in zero-shot VideoQA by a significant margin on a variety of datasets, including LSMDC-FiB, iVQA, MSRVTT-QA, MSVD-QA, ActivityNet-QA, TGIF-FrameQA, How2QA and TVQA. It also demonstrates competitive performance in the few-shot and fully-supervised setting. Our code and models are publicly available at https://github.com/antoyang/FrozenBiLM.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2206.08155")

Code

Syntology Ran 14 of 34 code samples harvested from 3 repositories linked to this paper; 20 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 12 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 0 ran; community (archive-listed): 26 samples from 2 repositories, 14 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

antoyang/FrozenBiLM officialmentioned in papermentioned on GitHubpytorch report
klauscc/dam mentioned on GitHubpytorch report
sts-vlcc/sts-vlcc mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

34 samples harvested; 14 ran; 1 honoured the contract we drafted; 20 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
12ran
20unverified

Licence: 1 of the 34 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

DebertaV2Attention antoyang/FrozenBiLM/model/deberta.py official repository unverified Apache-2.0 (permissive) · ed339d8069718237 · report
DebertaV2Encoder antoyang/FrozenBiLM/model/deberta.py official repository unverified Apache-2.0 (permissive) · deded63a5e7d8699 · report
DebertaV2Layer antoyang/FrozenBiLM/model/deberta.py official repository unverified Apache-2.0 (permissive) · 32cb0a816174decd · report
DebertaV2Model antoyang/FrozenBiLM/model/deberta.py official repository unverified Apache-2.0 (permissive) · f576b70e9c2bc9c4 · report
DisentangledSelfAttention antoyang/FrozenBiLM/model/deberta.py official repository unverified Apache-2.0 (permissive) · b2ac2b6c1c0b64dc · report
build_relative_position antoyang/FrozenBiLM/model/deberta.py official repository unverified Apache-2.0 (permissive) · b1852809457a4b1f · report
make_log_bucket_position antoyang/FrozenBiLM/model/deberta.py official repository unverified Apache-2.0 (permissive) · 29371b9c270911e1 · report
Adapter sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 020a7d784fec3e8b · report
ConvLayer sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran · metamorphic tier: deterministic Apache-2.0 (permissive) · be2fdff3546c4ee9 · report
DebertaV2Embeddings sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran · metamorphic tier: deterministic Apache-2.0 (permissive) · fb069d6e466f4cf8 · report
DebertaV2Intermediate sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 713015c84afd123d · report
DebertaV2LMPredictionHead sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 4f4202be5c178fde · report
DebertaV2OnlyMLMHead sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 491522c8a24566a6 · report
DebertaV2Output sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d3b79844fb5a1268 · report
DebertaV2PreTrainedModel sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 48742f01e32d514b · report
DebertaV2SelfOutput sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a14cfd37805f8d1a · report
StableDropout sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 104d374e92036a6f · report
XDropout sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran Apache-2.0 (permissive) · 1f587485f1c0247d · report
XSoftmax sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran Apache-2.0 (permissive) · d4b3d76edcfa3131 · report
build_relative_position sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran · honoured contract fingerprinted Apache-2.0 (permissive) · 0464dc8467b456dc · report
make_log_bucket_position sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) ran · violated contract fingerprinted Apache-2.0 (permissive) · 567c8b010f8e20d2 · report
BaseModelOutput sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · 06f89381bbcaa62a · report
BaseModelOutput klauscc/dam/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · 5c632e836a01b0f1 · report
DebertaV2Attention sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · 19240ea1e9c179bc · report
DebertaV2Embeddings klauscc/dam/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · d402090dd56a6f46 · report
DebertaV2Encoder sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · 0905316df8bf0d3e · report
DebertaV2Encoder klauscc/dam/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · cc3b22c7c43000bf · report
DebertaV2ForMaskedLM sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · 24dd2616a44d83c7 · report
DebertaV2Layer sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · b76e671720991509 · report
DebertaV2Model sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · 6a90151a5129dc8e · report
DebertaV2Model klauscc/dam/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · 63c2fffe385cf5e9 · report
DisentangledSelfAttention sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · f5ca472802a4cfb0 · report
DropoutContext sts-vlcc/sts-vlcc/model/deberta.py community (archive-listed) unverified Apache-2.0 (permissive) · ae0fc5a9e16f1c5d · report
get_mask identical code first harvested elsewhere unverified licence of this copy not recorded · 05732f1a5126672d · report

Tasks

Fill MaskLanguage ModelingLanguage ModellingMasked Language ModelingQuestion AnsweringTGIF-FrameVideo Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Zero-Shot LearningZero-Shot Video Question AnswerZeroshot Video Question Answer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering ActivityNet-QA FrozenBiLM Accuracy 43.2 #21 of 36 Archive leaderboard report
Video Question Answering ActivityNet-QA FrozenBiLM (0-shot) Accuracy 25.9 #34 of 36 Archive leaderboard report
Video Question Answering How2QA FrozenBiLM Accuracy 86.7 #2 of 8 Archive leaderboard report
Video Question Answering How2QA FrozenBiLM (0-shot) Accuracy 58.4 #7 of 8 Archive leaderboard report
Video Question Answering MSRVTT-QA FrozenBiLM Accuracy 47.0 #7 of 14 Archive leaderboard report
Video Question Answering MSRVTT-QA FrozenBiLM (0-shot) Accuracy 16.7 #14 of 14 Archive leaderboard report
Video Question Answering TVQA FrozenBiLM Accuracy 82 #2 of 6 Archive leaderboard report
Video Question Answering iVQA FrozenBiLM Accuracy 39.6 #2 of 7 Archive leaderboard report
Video Question Answering iVQA FrozenBiLM (0-shot) Accuracy 26.8 #6 of 7 Archive leaderboard report
Visual Question Answering MSRVTT-QA FrozenBiLM Accuracy 0.470 #2 of 4 Archive leaderboard report
Visual Question Answering MSVD-QA FrozenBiLM Accuracy 0.548 #1 of 2 Archive leaderboard report
Zero-Shot Learning LSMDC FrozenBiLM Accuracy 51.5 #1 of 1 Archive leaderboard report
Zero-Shot Learning iVQA FrozenBiLM Accuracy 0.268 #1 of 1 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA FrozenBiLM Accuracy 24.7 #27 of 28 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA FrozenBiLM Confidence Score - #27 of 28 Archive leaderboard report
Zero-Shot Video Question Answer EgoSchema (fullset) FrozenBiLM Accuracy 26.9 #27 of 29 Archive leaderboard report
Zero-Shot Video Question Answer MSVD-QA FrozenBiLM Accuracy 33.8 #28 of 28 Archive leaderboard report
Zero-Shot Video Question Answer TGIF-QA FrozenBiLM Accuracy 41.9 #13 of 14 Archive leaderboard report
Zero-Shot Video Question Answer TVQA FrozenBiLM (with speech) Accuracy 59.7 #1 of 9 Archive leaderboard report
Zero-Shot Video Question Answer TVQA FrozenBILM (no speech) Accuracy 29.7 #9 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections