# Spatio-Temporal Multi-Order Interaction for Video Recognition

**Authors:** Kevin D. Nguetche, Lilian Hollard, Eric Granger, Marco Pedersoli  
**Lab:** International Laboratory on Learning Systems · **Published:** 3 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.05633) · [PDF](https://arxiv.org/pdf/2611.05633) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.05633.html)

## Abstract

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.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.