Papers › TAM: Temporal Adaptive Module for Video Recognition

TAM: Temporal Adaptive Module for Video Recognition

14 May 2020ICCV 2021 10arXiv:2005.06803archive 2025-07-28

Zhao-Yang Liu, Li-Min Wang, Wayne Wu, Chen Qian, Tong Lu

Video data is with complex temporal dynamics due to various factors such as camera motion, speed variation, and different activities. To effectively capture this diverse motion pattern, this paper presents a new temporal adaptive module ({\bf TAM}) to generate video-specific temporal kernels based on its own feature map. TAM proposes a unique two-level adaptive modeling scheme by decoupling the dynamic kernel into a location sensitive importance map and a location invariant aggregation weight. The importance map is learned in a local temporal window to capture short-term information, while the aggregation weight is generated from a global view with a focus on long-term structure. TAM is a modular block and could be integrated into 2D CNNs to yield a powerful video architecture (TANet) with a very small extra computational cost. The extensive experiments on Kinetics-400 and Something-Something datasets demonstrate that our TAM outperforms other temporal modeling methods consistently, and achieves the state-of-the-art performance under the similar complexity. The code is available at \url{ https://github.com/liu-zhy/temporal-adaptive-module}.

PaperPDFConference PDFCodeCode 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="2005.06803")

Code

Syntology Ran 0 of 11 code samples harvested from 2 repositories linked to this paper; 11 have no recorded run.

By repository: official repository: 10 samples from 2 repositories, 0 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

liu-zhy/TANet officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
liu-zhy/temporal-adaptive-module officialmentioned in papermentioned on GitHubpytorch 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

11 samples harvested; 0 ran; 0 honoured the contract we drafted; 11 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.

11unverified

Licence: 1 of the 11 samples is 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. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

accuracy liu-zhy/TANet/ops/utils.py official repository unverified Apache-2.0 (permissive) · f0c9a29156911331 · report
bninception liu-zhy/TANet/archs/bn_inception.py official repository unverified Apache-2.0 (permissive) · c89c29bd79c97227 · report
eval_video liu-zhy/temporal-adaptive-module/test_models.py official repository unverified Apache-2.0 (permissive) · 25a2a9af3ae42ab2 · report
get_ip liu-zhy/TANet/ops/dist_utils.py official repository unverified Apache-2.0 (permissive) · 8aa1bb59c94441a2 · report
make_temporal_modeling liu-zhy/TANet/ops/temporal_module.py official repository unverified Apache-2.0 (permissive) · 3463156e190cae52 · report
parse_shift_option_from_log_name liu-zhy/temporal-adaptive-module/test_models.py official repository unverified Apache-2.0 (permissive) · cb4f97c8c0af5da8 · report
return_hmdb51 liu-zhy/TANet/ops/dataset_config.py official repository unverified Apache-2.0 (permissive) · da3f1f7cf67362e2 · report
return_something liu-zhy/TANet/ops/dataset_config.py official repository unverified Apache-2.0 (permissive) · 48f65a4712d42061 · report
return_ucf101 liu-zhy/TANet/ops/dataset_config.py official repository unverified Apache-2.0 (permissive) · 2aa6d9e3ae6cf167 · report
softmax liu-zhy/TANet/ops/utils.py official repository unverified Apache-2.0 (permissive) · 2fc0c71db48a9af8 · report
accuracy identical code first harvested elsewhere unverified licence of this copy not recorded · b02c6e331bc88d68 · report

Tasks

Action RecognitionVideo Recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: TAM

SPEEDTAM

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