Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison, convolutional designs for videos offer an efficient alternative but lack long-range dependency modeling. Towards achieving the best of both designs, this work proposes Video-FocalNet, an effective and efficient architecture for video recognition that models both local and global contexts. Video-FocalNet is based on a spatio-temporal focal modulation architecture that reverses the interaction and aggregation steps of self-attention for better efficiency. Further, the aggregation step and the interaction step are both implemented using efficient convolution and element-wise multiplication operations that are computationally less expensive than their self-attention counterparts on video representations. We extensively explore the design space of focal modulation-based spatio-temporal context modeling and demonstrate our parallel spatial and temporal encoding design to be the optimal choice. Video-FocalNets perform favorably well against the state-of-the-art transformer-based models for video recognition on five large-scale datasets (Kinetics-400, Kinetics-600, SS-v2, Diving-48, and ActivityNet-1.3) at a lower computational cost. Our code/models are released at https://github.com/TalalWasim/Video-FocalNets.

翻译：近期视频识别模型利用Transformer模型进行长程时空上下文建模。基于自注意力机制的视频Transformer设计虽能建模全局上下文，但计算成本高昂。相比之下，卷积视频设计提供了高效替代方案，却缺乏长程依赖建模能力。为融合两者优势，本文提出Video-FocalNet——一种兼顾局部与全局上下文的高效视频识别架构。该架构基于时空焦点调制机制，通过反转自注意力的交互与聚合步骤提升效率，并采用计算成本低于自注意力的高效卷积与逐元素乘法实现聚合与交互步骤。我们系统探索了基于焦点调制的时空上下文建模设计空间，证明并行时空编码方案为最优选择。在五个大规模数据集（Kinetics-400、Kinetics-600、SS-v2、Diving-48及ActivityNet-1.3）上，Video-FocalNets以更低计算成本取得优于当前最先进Transformer模型的视频识别性能。代码与模型已开源至https://github.com/TalalWasim/Video-FocalNets。