</> Code with Papers by Syntology

Methods › General › Attention Mechanisms › TAM

Temporal Adaptive Module

TAM

32 papers tagged archive 2025-07-28

Introduced by Zhao-Yang Liu et al. in TAM: Temporal Adaptive Module for Video Recognition

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

TAM is designed to capture complex temporal relationships both efficiently and flexibly, It adopts an adaptive kernel instead of self-attention to capture global contextual information, with lower time complexity than GLTR.

TAM has two branches, a local branch and a global branch. Given the input feature map X∈ℝ^(C×T×H×W), global spatial average pooling GAP is first applied to the feature map to ensure TAM has a low computational cost. Then the local branch in TAM employs several 1D convolutions with ReLU nonlinearity across the temporal domain to produce location-sensitive importance maps for enhancing frame-wise features. The local branch can be written as s = σ(Conv1D(δ(Conv1D(GAP(X))))) X¹ = s X Unlike the local branch, the global branch is location invariant and focuses on generating a channel-wise adaptive kernel based on global temporal information in each channel. For the c-th channel, the kernel can be written as

Θ_c = Softmax(FC₂(δ(FC₁(GAP(X)_c))))

where Θ_c ∈ℝᴷ and K is the adaptive kernel size. Finally, TAM convolves the adaptive kernel Θ with Xₒᵤₜ¹: Y = Θ⊗X¹

With the help of the local branch and global branch, TAM can capture the complex temporal structures in video and enhance per-frame features at low computational cost. Due to its flexibility and lightweight design, TAM can be added to any existing 2D CNNs.

PaperSource

Papers archive 2025-07-28

30 shown of 32, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 60 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
ARC3
Action Recognition3
Semantic Segmentation3
Contrastive Learning2
Domain Adaptation2
Language Modelling2
Object2
Segmentation2
Unsupervised Domain Adaptation2
Anatomy1
Anomaly Detection1
Autonomous Driving1
Classification1
Clustering1
Collaborative Filtering1
Combinatorial Optimization1
Cultural Vocal Bursts Intensity Prediction1
Decoder1
Depth Completion1
Descriptive1

Usage over time archive 2025-07-28

Papers per year tagged with TAM: 2020 to 2025, peak 7 7 0 2020: 5 papers 2020 2021: 6 papers 2021 2022: 5 papers 2022 2023: 7 papers 2023 2024: 6 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (32 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Attention Mechanisms

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