SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.10233 · CVPR · 2022

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

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

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2203.10233.json · badge: /api/ran/2203.10233.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
uark-cviu/direcformer canonical (classifier label)
classifier basis not recorded on the link
5 ran · 3 no recorded run
FunctionStatusWhere it lives
drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
uark-cviu/direcformer/slowfast/models/common.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("bcc1cdae3bb3212c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, uark-cviu/direcformer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_layer Ran
ran; our contract draft was wrong, not the code
uark-cviu/direcformer/slowfast/models/helpers.py
pointer only (licence: Apache-2.0) · get_code("c8a06e6ec83e9e27")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, uark-cviu/direcformer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_same_padding Ran
ran, honoured the contract we drafted
uark-cviu/direcformer/slowfast/models/conv2d_same.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from facebookresearch/depthshrinker, is pointer only (licence: NOASSERTION) · get_code("54e11386110ff042")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, uark-cviu/direcformer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_state_dict Ran
ran; our contract draft was wrong, not the code
uark-cviu/direcformer/slowfast/models/helpers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Wenhao-Chi/UNIEGO, is pointer only (licence: NOASSERTION) · get_code("83ec90904c246b55")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, uark-cviu/direcformer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_same Ran
ran; our contract draft was wrong, not the code
uark-cviu/direcformer/slowfast/models/conv2d_same.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Wenhao-Chi/UNIEGO, is pointer only (licence: NOASSERTION) · get_code("a5912e0e800a1929")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, uark-cviu/direcformer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

attention_pool Not yet run
unverified (harvested, no recorded run)
uark-cviu/direcformer/slowfast/models/attention.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rajatmodi62/OccludedActionBenchmark, is pointer only (licence: NONE) · get_code("a4723eab8df61dbe")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, uark-cviu/direcformer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_padding_value Not yet run
unverified (harvested, no recorded run)
uark-cviu/direcformer/slowfast/models/conv2d_same.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Wenhao-Chi/UNIEGO, is pointer only (licence: NOASSERTION) · get_code("909f6252536bbcf0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, uark-cviu/direcformer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

resume_checkpoint Not yet run
unverified (harvested, no recorded run)
uark-cviu/direcformer/slowfast/models/helpers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Wenhao-Chi/UNIEGO, is pointer only (licence: NOASSERTION) · get_code("102b75f3481035d1")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, uark-cviu/direcformer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 8 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 8 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
drop_path 11 other papers
3 dated earlier, 7 later, 1 same year, order not determinable
2106.09703 (2021-06)
MaCLR: Motion-aware Contrastive Learning of Representations for Videos
2110.06915 (2021-10)
Object-Region Video Transformers
2110.07058 (2021-10)
Ego4D: Around the World in 3,000 Hours of Egocentric Video
and 8 more not named here
attention_pool 8 other papers
2 dated earlier, 5 later, 1 same year, order not determinable
2106.09703 (2021-06)
MaCLR: Motion-aware Contrastive Learning of Representations for Videos
2110.06915 (2021-10)
Object-Region Video Transformers
136950068 (2022 (year only))
Efficient Video Transformers with Spatial-Temporal Token Selection
and 5 more not named here
resume_checkpoint 6 other papers
1 dated earlier, 5 later
2110.07641 (2021-10)
Non-deep Networks
2206.03452 (2022-06)
Can CNNs Be More Robust Than Transformers?
2210.04135 (2022-10)
VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment
and 3 more not named here
extract_layer 4 other papers
1 dated earlier, 3 later
2002.08258 (2020-02)
Knapsack Pruning with Inner Distillation
2407.03179 (2024-07)
Motion meets Attention: Video Motion Prompts
2412.10569 (2024-12)
Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
and 1 more not named here
get_same_padding 4 other papers
1 dated earlier, 3 later
2003.13678 (2020-03)
Designing Network Design Spaces
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
2407.03179 (2024-07)
Motion meets Attention: Video Motion Prompts
and 1 more not named here
get_padding_value 3 other papers
3 later
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
2407.03179 (2024-07)
Motion meets Attention: Video Motion Prompts
2606.20559 (2026-06)
UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning
pad_same 3 other papers
3 later
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
2407.03179 (2024-07)
Motion meets Attention: Video Motion Prompts
2606.20559 (2026-06)
UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning
load_state_dict 2 other papers
2 later
2407.03179 (2024-07)
Motion meets Attention: Video Motion Prompts
2606.20559 (2026-06)
UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 (Direc-Former) framework 1 for robust action recognition. The method takes a simple but novel perspective of Transformerbased approach to understand the right order of sequence actions. Therefore, the contributions of this work are threefold. 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 [4,18,72,74], on three standard large-scale benchmarks, i.e. Jester, Kinetics-400 and Something-Something-V2.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.10233")
get_code_for_paper("2203.10233")
have("2203.10233")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.10233.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.10233.svg)](https://syntology.ai/paper/2203.10233)

Connect an agent — have() is free.