Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol
نویسندگان
چکیده
منابع مشابه
Online Action Detection in Untrimmed, Streaming Videos - Modeling and Evaluation
The goal of Online Action Detection (OAD) is to detect action in a timely manner and to recognize its action category. Early works focused on early action detection, which is effectively formulated as a classification problem instead of online detection in streaming videos, because these works used partially seen short video clip that begins at the start of action. Recently, researchers started...
متن کاملA Decentralized Online Sortition Protocol
We propose a new online sortition protocol which is decentralized. We argue that our protocol has safety, fairness, randomness, non-reputation and openness properties. Sortition is a process that makes random decision and it is used in competitions and lotteries to determine who is the winner. In the real world, sortition is simply done using a lottery machine and all the participa...
متن کاملAction Temporal Localization in Untrimmed Videos via Multi-stage CNNs
We address action temporal 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 action temporal localization via multi-stage segment-based 3D ConvNe...
متن کاملOnline Action Detection
In the computer vision problem of online action detection, the goal is to detect the start of an action in a video stream as soon as it happens. For instance, if a child is chasing a ball, an autonomous car should recognize what is going on and respond immediately. This is a very challenging problem. First, only partial actions are observed. Second, there is a large variability in negative data...
متن کاملTemporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks
This work proposes a simple pipeline to classify and temporally localize activities in untrimmed videos. Our system uses features from a 3D Convolutional Neural Network (C3D) as input to train a a recurrent neural network (RNN) that learns to classify video clips of 16 frames. After clip prediction, we post-process the output of the RNN to assign a single activity label to each video, and deter...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2020
ISSN: 2169-3536
DOI: 10.1109/access.2019.2961789