AI RESEARCH
LiquidTAD: An Efficient Method for Temporal Action Detection via Liquid Neural Dynamics
arXiv CS.CV
•
ArXi:2604.18274v1 Announce Type: new Temporal Action Detection (TAD) in untrimmed videos is currently dominated by Transformer-based architectures. While high-performing, their quadratic computational complexity and substantial parameter redundancy limit deployment in resource-constrained environments. In this paper, we propose LiquidTAD, a novel parameter-efficient framework that replaces cumbersome self-attention layers with parallelized ActionLiquid blocks.