← Back to all news
arXiv AI By Kevin D. Nguetche, Lilian Hollard, Eric Granger, Marco Pedersoli

Spatio-Temporal Multi-Order Interaction for Video Recognition

Read the original on arXiv AI →

The paper introduces VideoMogaNet, a video recognition model that addresses computational inefficiencies in temporal modeling by using parallel multi-order processing with depthwise-only convolutions and implicit gating-based aggregation, achieving linear complexity in channel count. It also proposes a dual interaction between spatial and temporal dimensions to enhance spatio-temporal representation without added cost. VideoMogaNet matches or surpasses state‑of‑the‑art action recognition performance on benchmarks such as UCF101, HMDB51, Kinetics‑400, and Diving48 while significantly reducing temporal branch computation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
Oct 9

SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection

SV-TAD introduces native sparse 2D convolutions to enable convolutional adapters to operate directly on dynamically pruned token sets, addressing the inefficiency of dense reconstruction in token‑selection methods. By integrating this primitive into a temporal action detection framework, the approach cuts VideoMAEv2‑L computation by up to 64% and achieves 2.2× faster inference while preserving state‑of‑the‑art accuracy on THUMOS‑14 and ActivityNet‑1.3. When applied to InternVideoNext‑L, it surpasses prior state‑of‑the‑art performance at roughly half the computational cost and naturally supports auxiliary task tokens for improved fine‑grained assembly detection on ATTACH.

By Ricardo Pizarro, Roberto Valle, Jos\'e M. Buenaposada, Luis M. Bergasa, Luis Baumela
llmsefficiencybenchmarks
More like this →
Hugging Face Trending Papers
Oct 8

SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection

SV‑TAD introduces native sparse 2D convolutions to enable convolutional adapters to operate directly on dynamically pruned token sets, addressing the inefficiency of existing adapters that do not reduce inference‑time computation. By integrating this primitive, SV‑TAD cuts VideoMAEv2‑L computation by up to 64% and achieves 2.2× faster inference while preserving state‑of‑the‑art accuracy on THUMOS‑14 and ActivityNet‑1.3. When applied to InternVideoNext‑L, the approach surpasses prior state‑of‑the‑art performance at roughly half the computational cost and also supports auxiliary task tokens, improving fine‑grained assembly detection on ATTACH.

llmsefficiencybenchmarks
More like this →