Learning multiscale Transformer models has been evidenced as a viable
approach to augmenting machine translation systems. Prior research has
primarily focused on treating subwords as basic units in developing such
systems. However, the incorporation of fine-grained character-level features
into multiscale Transformer has not yet been explored. In this work, we present
a \textbf{S}low-\textbf{F}ast two-stream learning model, referred to as
Tran\textbf{SF}ormer, which utilizes a ``slow'' branch to deal with subword
sequences and a ``fast'' branch to deal with longer character sequences. This
model is efficient since the fast branch is very lightweight by reducing the
model width, and yet provides useful fine-grained features for the slow branch.
Our TranSFormer shows consistent BLEU improvements (larger than 1 BLEU point)
on several machine translation benchmarks.

本文提出了一种 Slow-Fast 双流学习模型 ——TranSFomer，将细粒度字符级特征与多尺度 Transformer 结合，显著提高了机器翻译 BLEU 指标。

TranSFormer：用于机器翻译的慢速 - 快速 Transformer

TranSFormer: Slow-Fast Transformer for Machine Translation

Group Activity Recognition detects the activity collectively performed by a
group of actors, which requires compositional reasoning of actors and objects.
We approach the task by modeling the video as tokens that represent the
multi-scale semantic concepts in the video. We propose COMPOSER, a Multiscale
Transformer based architecture that performs attention-based reasoning over
tokens at each scale and learns group activity compositionally. In addition,
prior works suffer from scene biases with privacy and ethical concerns. We only
use the keypoint modality which reduces scene biases and prevents acquiring
detailed visual data that may contain private or biased information of users.
We improve the multiscale representations in COMPOSER by clustering the
intermediate scale representations, while maintaining consistent cluster
assignments between scales. Finally, we use techniques such as auxiliary
prediction and data augmentations tailored to the keypoint signals to aid model
training. We demonstrate the model's strength and interpretability on two
widely-used datasets (Volleyball and Collective Activity). COMPOSER achieves up
to +5.4% improvement with just the keypoint modality. Code is available at
this https URL

使用基于多尺度 Transformer 的 COMPOSER 模型，在仅使用关键点模式的情况下提高群体活动识别精度，并通过预测辅助和数据增强等技术进行模型训练。