Papers › MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing

MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing

13 Jun 2022CVPR 2022 1arXiv:2206.06292archive 2025-07-28

Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei

Convolutional Neural Networks (CNNs) have been regarded as the go-to models for visual recognition. More recently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more popular. Nevertheless, it is not trivial when utilizing these newly-minted networks for video recognition due to the large variations and complexities in video data. In this paper, we present MLP-3D networks, a novel MLP-like 3D architecture for video recognition. Specifically, the architecture consists of MLP-3D blocks, where each block contains one MLP applied across tokens (i.e., token-mixing MLP) and one MLP applied independently to each token (i.e., channel MLP). By deriving the novel grouped time mixing (GTM) operations, we equip the basic token-mixing MLP with the ability of temporal modeling. GTM divides the input tokens into several temporal groups and linearly maps the tokens in each group with the shared projection matrix. Furthermore, we devise several variants of GTM with different grouping strategies, and compose each variant in different blocks of MLP-3D network by greedy architecture search. Without the dependence on convolutions or attention mechanisms, our MLP-3D networks achieves 68.5\%/81.4\% top-1 accuracy on Something-Something V2 and Kinetics-400 datasets, respectively. Despite with fewer computations, the results are comparable to state-of-the-art widely-used 3D CNNs and video transformers. Source code is available at https://github.com/ZhaofanQiu/MLP-3D.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D ArchitectureAction ClassificationAction RecognitionVideo Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 MLP-3D Acc@1 81.4 #84 of 207 Archive leaderboard report
Action Recognition Something-Something V1 MLP-3D Top 1 Accuracy 56.5 #22 of 74 Archive leaderboard report
Action Recognition Something-Something V2 MLP-3D Top-1 Accuracy 68.5 #51 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