Papers › Towards Long-Form Video Understanding

Towards Long-Form Video Understanding

21 Jun 2021CVPR 2021 1arXiv:2106.11310archive 2025-07-28

Chao-yuan Wu, Philipp Krähenbühl

Our world offers a never-ending stream of visual stimuli, yet today's vision systems only accurately recognize patterns within a few seconds. These systems understand the present, but fail to contextualize it in past or future events. In this paper, we study long-form video understanding. We introduce a framework for modeling long-form videos and develop evaluation protocols on large-scale datasets. We show that existing state-of-the-art short-term models are limited for long-form tasks. A novel object-centric transformer-based video recognition architecture performs significantly better on 7 diverse tasks. It also outperforms comparable state-of-the-art on the AVA dataset.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 1 repository linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 18 ran (15 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-27 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 18 samples that ran has no recorded date.

chaoyuaw/lvu officialmentioned in paperpytorchMITSyntology: 19 samples, 18 ran (3 instrument-failed) · 1 unverified report
md-mohaiminul/ViS4mer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Long Movie Clip Classification with State-Space Video Models (arXiv:2204.01692; that paper's own run record: 11 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

19 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
3ran · our draft was wrong
13ran
1unverified

Licence: 2 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from chaoyuaw/lvu. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

chaoyuaw/lvu official repository 19 samples, 18 ran (3 instrument-failed) · 1 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
src/models/modeling_bert.py ran · our draft was wrong fingerprinted MIT (permissive) · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
MaskedBCEWithLogitsLoss src/models/modeling_roberta.py ran fingerprinted MIT (permissive) · a788ae380900c50e · report fixture: signature preds:Tensor/2/float, labels:Tensor/2/float · returned Tensor · level recorded 2026-09-25
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
src/models/modeling_bert.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 211753ba29188d4e · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gelu_new in 55 papers
census: 3 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
src/models/modeling_bert.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 77601724cad03f95 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_constant_schedule in 21 papers src/models/optimization.py ran MIT (permissive) · 4575f85aa7122560 · report fixture: signature optimizer:SGD/0/?, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-25
get_constant_schedule_with_warmup in 25 papers src/models/optimization.py ran MIT (permissive) · a2003a42a1bf5632 · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-25
get_linear_schedule_with_warmup in 39 papers src/models/optimization.py ran MIT (permissive) · a3c458ae06a14711 · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-26
get_pairs in 260 papers src/models/tokenization_gpt2.py ran · our draft was wrong MIT (permissive) · 4f76173dfe4b0c11 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-26
hf_bucket_url in 13 papers src/models/file_utils.py ran fingerprinted MIT (permissive) · b2be6c932ce41084 · report fixture: signature identifier:str/0/str, postfix:str/0/str, cdn:bool/0/bool · returned str · level recorded 2026-09-25
is_remote_url in 23 papers src/models/file_utils.py ran MIT (permissive) · 4381d1f588a7f42a · report fixture: signature url_or_filename:str/0/str · returned bool · level recorded 2026-09-26
make_image_key in 6 papers src/utils/ava_eval_helper.py ran MIT (permissive) · 15e577f3614f1586 · report fixture: signature video_id:str/0/str, timestamp:float/0/float · returned str · level recorded 2026-09-25
prune_conv1d_layer in 20 papers src/models/modeling_utils.py ran MIT (permissive) · 8cc492d40c50497b · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Conv1D · level recorded 2026-09-25
prune_linear_layer in 40 papers src/models/modeling_utils.py ran · our draft was wrong MIT (permissive) · d30d6c3098df2c42 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Linear · level recorded 2026-09-22
read_exclusions src/utils/ava_eval_helper.py ran MIT (permissive) · 66b0d97a822e992a · report fixture: signature exclusions_file:str/0/str · returned set · level recorded 2026-09-25
soft_label_loss_sigmoid src/models/modeling_roberta.py ran MIT (permissive) · 9547eabe3165408d · report fixture: signature preds:Tensor/2/float, soft_labels:Tensor/2/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-26
soft_label_loss_softmax src/models/modeling_roberta.py ran MIT (permissive) · f8a333d6a2819774 · report fixture: signature preds:Tensor/2/float, soft_labels:Tensor/2/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-25
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
src/models/modeling_utils.py ran MIT (permissive) · 8e873fc150477bd1 · report fixture: returned Tensor · level recorded 2026-09-27
url_to_filename in 73 papers src/models/file_utils.py ran fingerprinted MIT (permissive) · e827d94caab33f59 · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-24
read_csv in 60 papers src/utils/ava_eval_helper.py unverified MIT (permissive) · a49fc9f33754fd90 · report

Tasks

Action RecognitionFormVideo RecognitionVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition AVA v2.2 Object Transformer mAP 31.0 #26 of 38 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