Papers › TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
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.
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.
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.
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.
87f39a589f593732 · report
969e8250d805a154 · report
3869ab58c2773dbd · report
d3dbd19bd0c74374 · report
674be50d432e8846 · report
307c022dd3d5678e · report
b42d3b0c5a43e6d2 · report
6670faac3ea134bd · report
e7a7d47996cb6fd6 · report
94e8f254ce489a4b · report
aa5a91226269bf75 · report
0ec9fc2025c16f65 · report
eaef07a98678e866 · report
73cecca9f3575f09 · report
6bb5f8f00704ac2f · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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