Detecting activities in untrimmed videos is an important but challenging
task. The performance of existing methods remains unsatisfactory, e.g., they
often meet difficulties in locating the beginning and end of a long complex
action. In this paper, we propose a generic framework that can accurately
detect a wide variety of activities from untrimmed videos. Our first
contribution is a novel proposal scheme that can efficiently generate
candidates with accurate temporal boundaries. The other contribution is a
cascaded classification pipeline that explicitly distinguishes between
relevance and completeness of a candidate instance. On two challenging temporal
activity detection datasets, THUMOS14 and ActivityNet, the proposed framework
significantly outperforms the existing state-of-the-art methods, demonstrating
superior accuracy and strong adaptivity in handling activities with various
temporal structures.

本文提出了一种通用的框架，利用新颖的提案方案和级联分类管道从未修剪的视频中准确检测各种活动，超越了现有最先进方法在 THUMOS14 和 ActivityNet 数据集上的表现。

追求时间准确性的通用活动检测

A Pursuit of Temporal Accuracy in General Activity Detection

Current state-of-the-art human activity recognition is focused on the
classification of temporally trimmed videos in which only one action occurs per
frame. We propose a simple, yet effective, method for the temporal detection of
activities in temporally untrimmed videos with the help of untrimmed
classification. Firstly, our model predicts the top k labels for each untrimmed
video by analysing global video-level features. Secondly, frame-level binary
classification is combined with dynamic programming to generate the temporally
trimmed activity proposals. Finally, each proposal is assigned a label based on
the global label, and scored with the score of the temporal activity proposal
and the global score. Ultimately, we show that untrimmed video classification
models can be used as stepping stone for temporal detection.

提出了一种新的方法，通过全局特征分析，预测未裁剪视频的前 k 个标签，并结合动态规划实现带时序约束的活动检测。该方法可用于未裁剪视频分类模型的时间检测。

未剪辑视频分类用于活动检测：参加 ActivityNet 挑战赛

Untrimmed Video Classification for Activity Detection: submission to  ActivityNet Challenge

We address temporal action localization in untrimmed long videos. This is
important because videos in real applications are usually unconstrained and
contain multiple action instances plus video content of background scenes or
other activities. To address this challenging issue, we exploit the
effectiveness of deep networks in temporal action localization via three
segment-based 3D ConvNets: (1) a proposal network identifies candidate segments
in a long video that may contain actions; (2) a classification network learns
one-vs-all action classification model to serve as initialization for the
localization network; and (3) a localization network fine-tunes on the learned
classification network to localize each action instance. We propose a novel
loss function for the localization network to explicitly consider temporal
overlap and therefore achieve high temporal localization accuracy. Only the
proposal network and the localization network are used during prediction. On
two large-scale benchmarks, our approach achieves significantly superior
performances compared with other state-of-the-art systems: mAP increases from
1.7% to 7.4% on MEXaction2 and increases from 15.0% to 19.0% on THUMOS 2014,
when the overlap threshold for evaluation is set to 0.5.

本研究提出了一种基于三种分段 3D 卷积神经网络的方法，用于解决未经修剪的长视频中的时间动作定位问题，其中提出网络用于识别可能包含动作的候选段，分类网络以一对多动作分类模型进行学习以作为定位网络的初始化，用于定位每个动作实例。