Papers › Test of Time: Instilling Video-Language Models with a Sense of Time

Test of Time: Instilling Video-Language Models with a Sense of Time

5 Jan 2023CVPR 2023 1arXiv:2301.02074archive 2025-07-28

Piyush Bagad, Makarand Tapaswi, Cees G. M. Snoek

Modelling and understanding time remains a challenge in contemporary video understanding models. With language emerging as a key driver towards powerful generalization, it is imperative for foundational video-language models to have a sense of time. In this paper, we consider a specific aspect of temporal understanding: consistency of time order as elicited by before/after relations. We establish that seven existing video-language models struggle to understand even such simple temporal relations. We then question whether it is feasible to equip these foundational models with temporal awareness without re-training them from scratch. Towards this, we propose a temporal adaptation recipe on top of one such model, VideoCLIP, based on post-pretraining on a small amount of video-text data. We conduct a zero-shot evaluation of the adapted models on six datasets for three downstream tasks which require varying degrees of time awareness. We observe encouraging performance gains especially when the task needs higher time awareness. Our work serves as a first step towards probing and instilling a sense of time in existing video-language models without the need for data and compute-intense training from scratch.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2301.02074")

Code

Syntology Ran 10 of 10 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 9 ran; found in paper text by Syntology: 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

bpiyush/TestOfTime officialmentioned on GitHubpytorchMIT 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

10 samples harvested; 10 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
9ran

Licence: 0 of the 10 samples are 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

active_event_description_combiner bpiyush/TestOfTime/package/datasets/synthetic.py official repository ran MIT (permissive) · d9fa3afc6393fd8c · report
average_precision bpiyush/TestOfTime/package/evaluators/videoclip_action_retrieval.py official repository ran fingerprinted MIT (permissive) · deacd11293b2686f · report
check_args bpiyush/TestOfTime/postpretrain.py official repository ran MIT (permissive) · f2d84c0542d17a04 · report
compute_metrics bpiyush/TestOfTime/package/metrics/retrieval.py official repository ran MIT (permissive) · b717eef2896560b3 · report
freeze_required_layers bpiyush/TestOfTime/postpretrain.py official repository ran MIT (permissive) · 5c70504364bdc3ac · report
mean_average_precision bpiyush/TestOfTime/package/evaluators/videoclip_action_retrieval.py official repository ran fingerprinted MIT (permissive) · 0196aa2f7fc22400 · report
passive_event_description_combiner bpiyush/TestOfTime/package/datasets/synthetic.py official repository ran MIT (permissive) · 053b2f9dfa05e107 · report
remove_multiple_spaces bpiyush/TestOfTime/package/datasets/synthetic.py official repository ran MIT (permissive) · 9fbb5b9290a438a0 · report
update_config bpiyush/TestOfTime/postpretrain.py official repository ran MIT (permissive) · 149908a60cbc536a · report
interpolate_temporal_pos_embed jayleicn/singularity/models/utils.py found in paper text by Syntology ran · fixture could not drive it MIT (permissive) · f64c56c357505158 · report

Tasks

Video UnderstandingVideo-Text Retrieval

Datasets

Introduced by this paper, per the archive.

Test-of-Time

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video-Text Retrieval Test-of-Time TACT 2-Class Accuracy 64.4 #3 of 4 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.

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