Unsupervised video-based object-centric learning is a promising avenue to
learn structured representations from large, unlabeled video collections, but
previous approaches have only managed to scale to real-world datasets in
restricted domains. Recently, it was shown that the reconstruction of
pre-trained self-supervised features leads to object-centric representations on
unconstrained real-world image datasets. Building on this approach, we propose
a novel way to use such pre-trained features in the form of a temporal feature
similarity loss. This loss encodes temporal correlations between image patches
and is a natural way to introduce a motion bias for object discovery. We
demonstrate that this loss leads to state-of-the-art performance on the
challenging synthetic MOVi datasets. When used in combination with the feature
reconstruction loss, our model is the first object-centric video model that
scales to unconstrained video datasets such as YouTube-VIS.

本文提出了一种基于无监督学习、自主学习特征的物体中心学习方法，以及如何使用时间特征相似性损失来发现运动目标，并在视频数据集上取得了最先进的表现。

通过预测时间特征相似性实现面向实际世界视频的对象中心学习

Object-Centric Learning for Real-World Videos by Predicting Temporal  Feature Similarities

We present a new algorithm for selection of informative frames in video
action recognition. Our approach is designed for aerial videos captured using a
moving camera where human actors occupy a small spatial resolution of video
frames. Our algorithm utilizes the motion bias within aerial videos, which
enables the selection of motion-salient frames. We introduce the concept of
patch mutual information (PMI) score to quantify the motion bias between
adjacent frames, by measuring the similarity of patches. We use this score to
assess the amount of discriminative motion information contained in one frame
relative to another. We present an adaptive frame selection strategy using
shifted leaky ReLu and cumulative distribution function, which ensures that the
sampled frames comprehensively cover all the essential segments with high
motion salience. Our approach can be integrated with any action recognition
model to enhance its accuracy. In practice, our method achieves a relative
improvement of 2.2 - 13.8% in top-1 accuracy on UAV-Human, 6.8% on NEC Drone,
and 9.0% on Diving48 datasets.

本文提出了一种用于视频动作识别的新算法，旨在从航拍视频中选择包含人在内的高运动唯象帧，该算法通过利用航拍视频中的运动偏差，利用了一些简单的重叠分析来识别视频中仅仅包含对应行为的帧。

PMI Sampler: 基于图像块相似度指导的航拍行动识别帧选择

PMI Sampler: Patch similarity guided frame selection for Aerial Action  Recognition

Monocular visual odometry (VO) and simultaneous localization and mapping
(SLAM) have seen tremendous improvements in accuracy, robustness and
efficiency, and have gained increasing popularity over recent years.
Nevertheless, not so many discussions have been carried out to reveal the
influences of three very influential yet easily overlooked aspects: photometric
calibration, motion bias and rolling shutter effect. In this work, we evaluate
these three aspects quantitatively on the state of the art of direct,
feature-based and semi-direct methods, providing the community with useful
practical knowledge both for better applying existing methods and developing
new algorithms of VO and SLAM. Conclusions (some of which are
counter-intuitive) are drawn with both technical and empirical analyses to all
of our experiments. Possible improvements on existing methods are directed or
proposed, such as a sub-pixel accuracy refinement of ORB-SLAM which boosts its
performance.

通过定量评估直接、特征和半直接方法的最新技术，提供了社区有用的实用知识，以便更好地应用现有的方法和开发新的 VO 和 SLAM 算法，并提出了可能的改进现有方法的建议。