Papers › TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding

TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding

29 Oct 2023arXiv:2310.19060archive 2025-07-28

Shuhuai Ren, Sishuo Chen, Shicheng Li, Xu sun, Lu Hou

Large-scale video-language pre-training has made remarkable strides in advancing video-language understanding tasks. However, the heavy computational burden of video encoding remains a formidable efficiency bottleneck, particularly for long-form videos. These videos contain massive visual tokens due to their inherent 3D properties and spatiotemporal redundancy, making it challenging to capture complex temporal and spatial relationships. To tackle this issue, we propose an efficient method called TEmporal-Spatial Token Aggregation (TESTA). TESTA condenses video semantics by adaptively aggregating similar frames, as well as similar patches within each frame. TESTA can reduce the number of visual tokens by 75% and thus accelerate video encoding. Building upon TESTA, we introduce a pre-trained video-language model equipped with a divided space-time token aggregation module in each video encoder block. We evaluate our model on five datasets for paragraph-to-video retrieval and long-form VideoQA tasks. Experimental results show that TESTA improves computing efficiency by 1.7 times, and achieves significant performance gains from its scalability in processing longer input frames, e.g., +13.7 R@1 on QuerYD and +6.5 R@1 on Condensed Movie.

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="2310.19060")

Code

Syntology Ran 11 of 15 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 10 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

renshuhuai-andy/testa officialmentioned in papermentioned 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

15 samples harvested; 11 ran; 1 honoured the contract we drafted; 4 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
10ran
4unverified

Licence: 0 of the 15 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 renshuhuai-andy/testa. “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.

bipartite_soft_matching renshuhuai-andy/testa/testa/merge.py official repository ran MIT (permissive) · 87f39a589f593732 · report
do_nothing renshuhuai-andy/testa/testa/merge.py official repository ran · honoured contract fingerprinted MIT (permissive) · 969e8250d805a154 · report
generate_colormap renshuhuai-andy/testa/testa/vis.py official repository ran fingerprinted MIT (permissive) · 3869ab58c2773dbd · report
get_custom_args renshuhuai-andy/testa/models/blip.py official repository ran MIT (permissive) · d3dbd19bd0c74374 · report
kth_bipartite_soft_matching renshuhuai-andy/testa/testa/merge_original.py official repository ran MIT (permissive) · 674be50d432e8846 · report
merge_wavg renshuhuai-andy/testa/testa/merge.py official repository ran MIT (permissive) · 307c022dd3d5678e · report
original_bipartite_soft_matching renshuhuai-andy/testa/testa/merge_original.py official repository ran MIT (permissive) · b42d3b0c5a43e6d2 · report
params_count renshuhuai-andy/testa/model_stats.py official repository ran MIT (permissive) · 6670faac3ea134bd · report
parse_merging_type renshuhuai-andy/testa/testa/utils.py official repository ran MIT (permissive) · e7a7d47996cb6fd6 · report
parse_r renshuhuai-andy/testa/testa/utils.py official repository ran fingerprinted MIT (permissive) · 94e8f254ce489a4b · report
tile renshuhuai-andy/testa/models/testa_vqa.py official repository ran fingerprinted MIT (permissive) · aa5a91226269bf75 · report
all_gather_with_grad renshuhuai-andy/testa/models/testa_retrieval.py official repository unverified MIT (permissive) · 0ec9fc2025c16f65 · report
benchmark renshuhuai-andy/testa/testa/utils.py official repository unverified MIT (permissive) · eaef07a98678e866 · report
concat_all_gather renshuhuai-andy/testa/models/testa_retrieval.py official repository unverified MIT (permissive) · 73cecca9f3575f09 · report
make_visualization renshuhuai-andy/testa/testa/vis.py official repository unverified MIT (permissive) · 6bb5f8f00704ac2f · report

Tasks

FormLanguage ModellingRetrievalVideo Question AnsweringVideo RetrievalVideo-Text Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering ActivityNet-QA TESTA (ViT-B/16) Accuracy 45 #17 of 36 Archive leaderboard report
Video Retrieval ActivityNet TESTA (ViT-B/16) text-to-video R@1 54.8 #12 of 31 Archive leaderboard report
Video Retrieval ActivityNet TESTA (ViT-B/16) text-to-video R@10 89.6 #12 of 31 Archive leaderboard report
Video Retrieval ActivityNet TESTA (ViT-B/16) text-to-video R@5 80.8 #12 of 31 Archive leaderboard report
Video Retrieval Condensed Movies TESTA (ViT-B/16) text-to-video R@1 24.9 #1 of 3 Archive leaderboard report
Video Retrieval Condensed Movies TESTA (ViT-B/16) text-to-video R@10 55.1 #1 of 3 Archive leaderboard report
Video Retrieval Condensed Movies TESTA (ViT-B/16) text-to-video R@5 46.5 #1 of 3 Archive leaderboard report
Video Retrieval DiDeMo TESTA (ViT-B/16) text-to-video R@1 61.2 #8 of 40 Archive leaderboard report
Video Retrieval DiDeMo TESTA (ViT-B/16) text-to-video R@10 91.5 #8 of 40 Archive leaderboard report
Video Retrieval DiDeMo TESTA (ViT-B/16) text-to-video R@5 87.2 #8 of 40 Archive leaderboard report
Video Retrieval QuerYD TESTA (ViT-B/16) text-to-video R@1 83.4 #1 of 5 Archive leaderboard report
Video Retrieval QuerYD TESTA (ViT-B/16) text-to-video R@10 95.3 #1 of 5 Archive leaderboard report
Video Retrieval QuerYD TESTA (ViT-B/16) text-to-video R@5 93.8 #1 of 5 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