SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.08451 · ICCV · 2023

Efficient Video Action Detection with Token Dropout and Context Refinement

Yibing Song, Lei Chen, Zhan Tong, Limin Wang, Gangshan Wu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 1 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/2304.08451.json · badge: /api/ran/2304.08451.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
MCG-NJU/EVAD community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
DropPath Ran
ran on a synthesized input
MCG-NJU/EVAD/projects/evad/models/vit_model.py
pointer only (licence: NOASSERTION) · get_code("f1ba368c5af15b64")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, MCG-NJU/EVAD (NOASSERTION). 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.

KTPAttention Ran
ran on a synthesized input
MCG-NJU/EVAD/projects/evad/models/vit_model.py
pointer only (licence: NOASSERTION) · get_code("0c40243389e69366")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, MCG-NJU/EVAD (NOASSERTION). 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.

KTPBlock Not yet run
unverified (harvested, no recorded run)
MCG-NJU/EVAD/projects/evad/models/vit_model.py
pointer only (licence: NOASSERTION) · get_code("3e41f5a8960a91c2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, MCG-NJU/EVAD (NOASSERTION). 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
DropPath
brick of this paper's assembly: model
25 other papers
13 dated earlier, 12 later · 14 only as an assembly brick
2106.08254 (2021-06)
BEIT: BERT Pre-Training of Image Transformers
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
2201.12096 (2022-01)
Mask-based Latent Reconstruction for Reinforcement Learning
and 22 more not named here

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

Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor identification. In this work, we propose an end-toend framework for efficient video action detection (EVAD) based on vanilla ViTs. Our EVAD consists of two specialized designs for video action detection. First, we propose a spatiotemporal token dropout from a keyframe-centric perspective. In a video clip, we maintain all tokens from its keyframe, preserve tokens relevant to actor motions from other frames, and drop out the remaining tokens in this clip. Second, we refine scene context by leveraging remaining tokens for better recognizing actor identities. The region of interest (RoI) in our action detector is expanded into temporal domain. The captured spatiotemporal actor identity representations are refined via scene context in a decoder with the attention mechanism. These two designs make our EVAD efficient while maintaining accuracy, which is validated on three benchmark datasets (i.e., AVA, UCF101-24, JHMDB). Compared to the vanilla ViT backbone, our EVAD reduces the overall GFLOPs by 43% and improves real-time inference speed by 40% with no performance degradation. Moreover, even at similar computational costs, our EVAD can improve the performance by 1.1 mAP with higher resolution inputs. Code is available at https://github.com/MCG-NJU/EVAD.

For agents

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

get_harvested_code_for_paper("2304.08451")
get_code_for_paper("2304.08451")
have("2304.08451")

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

curl https://syntology.ai/api/ran/2304.08451.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.08451.svg)](https://syntology.ai/paper/2304.08451)

Connect an agent — have() is free.