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 three large-scale datasets (Kinetics-400, Kinetics-600, and SS-v2) 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模型对长程时空上下文进行建模。视频Transformer设计基于自注意力机制，虽能建模全局上下文，但计算成本较高。相比之下，视频卷积设计虽提供高效替代方案，但缺乏长程依赖建模能力。为兼具二者优势，本文提出Video-FocalNet——一种高效且有效的视频识别架构，能够同时建模局部与全局上下文。Video-FocalNet采用时空焦点调制架构，通过反转自注意力机制中的交互与聚合步骤以提升效率。此外，聚合与交互步骤均通过高效卷积与逐元素乘法运算实现，其在视频表示上的计算开销低于对应自注意力操作。我们广泛探索了基于焦点调制的时空上下文建模设计空间，并证明并行时空编码设计为最优选择。在三个大规模数据集（Kinetics-400、Kinetics-600、SS-v2）上，Video-FocalNets以更低计算成本取得了与基于Transformer的最先进视频识别模型相媲美甚至更优的性能。我们的代码/模型已在https://github.com/TalalWasim/Video-FocalNets开源。