---
title: "Spatio-Temporal Multi-Order Interaction for Video Recognition"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05633v1"
permalink: "https://feed.astralor.com/items/itm_64e5b0f1ba5c24c86faf8874"
published: "2026-11-03T21:20:04.000Z"
score: 57
channel: "tech"
tags: ["多模态","Spatio-Temporal Multi-Order Interaction","Video Recognition Many","Many","CNNs","Starting","MogaNet","First"]
---

# Spatio-Temporal Multi-Order Interaction for Video Recognition

## 速览

Many temporal approaches for video recognition rely on explicit cross-channel aggregation projections, which have quadratic complexity in the number of channels, introducing significant computational overhead. In additi…

## 关键点

- Many temporal approaches for video recognition rely on explicit cross-channel aggregation projections, which have quadratic complexity in the number of channels, introducing significant computational overhead.
- In addition, the spatio-temporal representation used for video recognition is biased either toward local order interactions (for CNNs) or toward global order interactions (for transformers).
- Starting from the multi-order spatial representation of MogaNet, our method introduces two complementary contributions to tackle these problems.

## 全文

Many temporal approaches for video recognition rely on explicit cross-channel aggregation projections, which have quadratic complexity in the number of channels, introducing significant computational overhead. In addition, the spatio-temporal representation used for video recognition is biased either toward local order interactions (for CNNs) or toward global order interactions (for transformers). Starting from the multi-order spatial representation of MogaNet, our method introduces two complementary contributions to tackle these problems. First, for the temporal modelling, we introduce parallel multi-order processing with depthwise-only convolutions and implicit gating-based aggregation, which is linear in the number of channels, inducing a considerable computational reduction. Second, we propose a dual interaction between spatial and temporal dimensions, which allows a better spatio-temporal representation without increasing the computational cost. By combining these two contributions, our proposed VideoMogaNet achieves performance on par with or better than state-of-the-art action recognition approaches across multiple video benchmarks (UCF101, HMDB51, Kinetics-400, Diving48), while considerably reducing the cost of the temporal branch.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_64e5b0f1ba5c24c86faf8874