Egocentric activity recognition is one of the most challenging tasks in video
analysis. It requires a fine-grained discrimination of small objects and their
manipulation. While some methods base on strong supervision and attention
mechanisms, they are either annotation consuming or do not take spatio-temporal
patterns into account. In this paper we propose LSTA as a mechanism to focus on
features from spatial relevant parts while attention is being tracked smoothly
across the video sequence. We demonstrate the effectiveness of LSTA on
egocentric activity recognition with an end-to-end trainable two-stream
architecture, achieving state of the art performance on four standard
benchmarks.

本文提出了一种名为 LSTA 的机制，向注意力平滑地跟踪视频序列中的动态空间相关部分的特征，有效提高了两流架构的自我中心活动识别性能，并且在四项标准测评中取得了最佳表现。

LSTA: 面向自我中心行为识别的长短记忆关注

LSTA: Long Short-Term Attention for Egocentric Action Recognition

In this paper we propose an end-to-end trainable deep neural network model
for egocentric activity recognition. Our model is built on the observation that
egocentric activities are highly characterized by the objects and their
locations in the video. Based on this, we develop a spatial attention mechanism
that enables the network to attend to regions containing objects that are
correlated with the activity under consideration. We learn highly specialized
attention maps for each frame using class-specific activations from a CNN
pre-trained for generic image recognition, and use them for spatio-temporal
encoding of the video with a convolutional LSTM. Our model is trained in a
weakly supervised setting using raw video-level activity-class labels.
Nonetheless, on standard egocentric activity benchmarks our model surpasses by
up to +6% points recognition accuracy the currently best performing method that
leverages hand segmentation and object location strong supervision for
training. We visually analyze attention maps generated by the network,
revealing that the network successfully identifies the relevant objects present
in the video frames which may explain the strong recognition performance. We
also discuss an extensive ablation analysis regarding the design choices.

本研究提出一种基于深度神经网络模型的近场活动识别模型，其中使用了通过基于分类的 CNN 网络学习到的高度专业的注意力图，以及融合了空间和时间编码的卷积 LSTM 方法，从而实现了将原始视频级别标签用于弱监督学习。该模型具有较高的准确性。

只需注意力：将物体中心注意力固定在自我中心活动识别中

Attention is All We Need: Nailing Down Object-centric Attention for  Egocentric Activity Recognition

With the increasing availability of wearable devices, research on egocentric
activity recognition has received much attention recently. In this paper, we
build a Multimodal Egocentric Activity dataset which includes egocentric videos
and sensor data of 20 fine-grained and diverse activity categories. We present
a novel strategy to extract temporal trajectory-like features from sensor data.
We propose to apply the Fisher Kernel framework to fuse video and temporal
enhanced sensor features. Experiment results show that with careful design of
feature extraction and fusion algorithm, sensor data can enhance
information-rich video data. We make publicly available the Multimodal
Egocentric Activity dataset to facilitate future research.

本文介绍了一个基于 Wearable 设备的多模态自我中心活动识别数据集，其中提出了一种从传感器数据中提取时空轨迹特征的新颖策略，并应用 Fisher Kernel 框架融合视频和时空增强的传感器特征，实验结果表明，精心设计的特征提取和融合算法可以提高信息丰富的视频数据的质量。