Papers › DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition

DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition

19 Mar 2022CVPR 2022 1arXiv:2203.10233archive 2025-07-28

Thanh-Dat Truong, Quoc-Huy Bui, Chi Nhan Duong, Han-Seok Seo, Son Lam Phung, Xin Li, Khoa Luu

Human action recognition has recently become one of the popular research topics in the computer vision community. Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video action recognition with competitive results. However, these methods have suffered some fundamental limitations such as lack of robustness and generalization, e.g., how does the temporal ordering of video frames affect the recognition results? This work presents a novel end-to-end Transformer-based Directed Attention (DirecFormer) framework for robust action recognition. The method takes a simple but novel perspective of Transformer-based approach to understand the right order of sequence actions. Therefore, the contributions of this work are three-fold. Firstly, we introduce the problem of ordered temporal learning issues to the action recognition problem. Secondly, a new Directed Attention mechanism is introduced to understand and provide attentions to human actions in the right order. Thirdly, we introduce the conditional dependency in action sequence modeling that includes orders and classes. The proposed approach consistently achieves the state-of-the-art (SOTA) results compared with the recent action recognition methods, on three standard large-scale benchmarks, i.e. Jester, Kinetics-400 and Something-Something-V2.

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="2203.10233")

Code

Syntology Ran 4 of 8 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

uark-cviu/direcformer officialmentioned in paperpytorchApache-2.0 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

8 samples harvested; 4 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
1ran · our draft was wrong
2ran
4unverified

Licence: 8 of the 8 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 uark-cviu/direcformer. “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.

extract_layer uark-cviu/direcformer/slowfast/models/helpers.py official repository ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · c8a06e6ec83e9e27 · report
get_same_padding uark-cviu/direcformer/slowfast/models/conv2d_same.py official repository ran · honoured contract fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 54e11386110ff042 · report
load_state_dict uark-cviu/direcformer/slowfast/models/helpers.py official repository ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 83ec90904c246b55 · report
pad_same uark-cviu/direcformer/slowfast/models/conv2d_same.py official repository ran Apache-2.0 recorded; this copy not marked cleared · pointer only · a5912e0e800a1929 · report
attention_pool uark-cviu/direcformer/slowfast/models/attention.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · a4723eab8df61dbe · report
drop_path uark-cviu/direcformer/slowfast/models/common.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · bcc1cdae3bb3212c · report
get_padding_value uark-cviu/direcformer/slowfast/models/conv2d_same.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 909f6252536bbcf0 · report
resume_checkpoint uark-cviu/direcformer/slowfast/models/helpers.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 102b75f3481035d1 · report

Tasks

Action ClassificationAction RecognitionAction Recognition In VideosGesture RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 DirecFormer Acc@1 82.75 #73 of 207 Archive leaderboard report
Action Classification Kinetics-400 DirecFormer Acc@5 94.86 #73 of 207 Archive leaderboard report
Action Recognition Jester (Gesture Recognition) DirecFormer Val 98.15 #1 of 3 Archive leaderboard report
Action Recognition Something-Something V2 DirecFormer Top-1 Accuracy 64.94 #91 of 123 Archive leaderboard report
Action Recognition Something-Something V2 DirecFormer Top-5 Accuracy 87.9 #91 of 123 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