Papers › DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning

DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning

25 May 2021arXiv:2105.12085archive 2025-07-28

Wenhao Wu, Yuxiang Zhao, Yanwu Xu, Xiao Tan, Dongliang He, Zhikang Zou, Jin Ye, YingYing Li, Mingde Yao, ZiChao Dong, Yifeng Shi

Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to yield the final video-level prediction. Thus, their video-level prediction does not consider spatio-temporal features of how video evolves along the temporal dimension. In this paper, we introduce a novel Dynamic Segment Aggregation (DSA) module to capture relationship among snippets. To be more specific, we attempt to generate a dynamic kernel for a convolutional operation to aggregate long-range temporal information among adjacent snippets adaptively. The DSA module is an efficient plug-and-play module and can be combined with the off-the-shelf clip-based models (i.e., TSM, I3D) to perform powerful long-range modeling with minimal overhead. The final video architecture, coined as DSANet. We conduct extensive experiments on several video recognition benchmarks (i.e., Mini-Kinetics-200, Kinetics-400, Something-Something V1 and ActivityNet) to show its superiority. Our proposed DSA module is shown to benefit various video recognition models significantly. For example, equipped with DSA modules, the top-1 accuracy of I3D ResNet-50 is improved from 74.9% to 78.2% on Kinetics-400. Codes are available at https://github.com/whwu95/DSANet.

PaperPDFCodeCode 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 13 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 10 ran (10 with no instrument failure; 0 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.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

whwu95/DSANet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 10 ran (0 instrument-failed) · 3 unverified 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

13 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

10ran
3unverified

Licence: 0 of the 13 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 whwu95/DSANet. “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.

whwu95/DSANet official repository 13 samples, 10 ran (0 instrument-failed) · 3 unverified
auto_fp16 codes/core/fp16/decorators.py ran MIT (permissive) · 2a69c55d04d13a71 · report fixture: signature apply_to:NoneType/0/?, out_fp32:bool/0/bool · returned function · level recorded 2026-09-25
cast_tensor_type codes/core/fp16/utils.py ran MIT (permissive) · 7b91d5069635a376 · report fixture: signature inputs:dict/0/?, src_type:dtype/0/?, dst_type:dtype/0/? · returned dict · level recorded 2026-09-25
confusion_matrix in 20 papers codes/core/evaluation/accuracy.py ran MIT (permissive) · f739d3fb27d6f608 · report fixture: signature y_pred:ndarray/1/int, y_real:ndarray/1/int · returned ndarray · level recorded 2026-09-25
force_fp32 codes/core/fp16/decorators.py ran MIT (permissive) · b99f8dd443d13369 · report fixture: signature apply_to:NoneType/0/?, out_fp16:bool/0/bool · returned function · level recorded 2026-09-25
get_input_device codes/core/parallel/_functions.py ran fingerprinted MIT (permissive) · 72b89f53f5854825 · report fixture: signature input:Tensor/2/float · returned int · level recorded 2026-09-25
master_only in 15 papers codes/core/dist_utils.py ran MIT (permissive) · 6a0d65723b2675dc · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-25
mean_class_accuracy codes/core/evaluation/accuracy.py ran MIT (permissive) · 0ebabe504dafca4b · report fixture: signature scores:ndarray/2/float, labels:ndarray/1/int · returned float64 · level recorded 2026-09-25
patch_forward_method codes/core/fp16/hooks.py ran MIT (permissive) · e059fcc920f08632 · report fixture: signature func:callable/0/?, src_type:dtype/0/?, dst_type:dtype/0/?, convert_output:bool/0/bool · returned function · level recorded 2026-09-25
patch_norm_fp32 codes/core/fp16/hooks.py ran MIT (permissive) · f0c7f23268d50c1b · report fixture: signature module:callable/0/? · returned TestModel · level recorded 2026-09-25
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
codes/core/evaluation/accuracy.py ran fingerprinted MIT (permissive) · 622de14b270a7195 · report fixture: signature x:ndarray/2/float, dim:int/0/int · returned ndarray · level recorded 2026-09-25
build in 31 papers codes/models/builder.py unverified MIT (permissive) · 67976edf323e2f17 · report
collate in 50 papers codes/core/parallel/collate.py unverified MIT (permissive) · 1082ce7b7af2c3f7 · report
scatter in 33 papers codes/core/parallel/_functions.py unverified MIT (permissive) · aa73f0787179b863 · report

Tasks

Action RecognitionLong-range modelingRepresentation LearningVideo Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition ActivityNet DSANet (w/ 3D ResNet50) mAP 90.5 #6 of 16 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