Human activity prediction: Early recognition of ongoing activities from streaming videos

By Michael S. Ryoo. 2011

600 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022, background): “In the research community, activity forecasting has been often formulated as an extension of action classification, tracking, or feature generation: Given a sequence of image frames, they directly predict a few categorized actions (Ryoo 2011; Hoai and De la Torre 2014; Rhinehart and Kitani 2017), hu”
Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, background): “[51] represented each action as an integral histogram of spatio-temporal features.”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “Predicting future actions before they are actually executed is a critical ingredient for enabling us to effectively interact with other humans on a daily basis (Hoai and De la Torre, 2014; Lan et al., 2014; Ryoo, 2011; Sadegh Aliakbarian et al., 2017; Vu et al., 2014).”
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, background): “However, in many new works, recognizing the actions on the fly before the completion of the action is well studied by a learning formulation based on a structural SVM [13], or a non-parametric moving pose framework [55] and a dynamic integral bag-of-words approach [28].”
Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks (2016, background): “nize partial events, enabling early detection. To reduce the observational latency of human action recognition, a non-parametric moving pose framework [6] and a dynamic integral bag-of-words approach [20] are proposed respectively to detect actions earlier. Our model goes beyond early detection. Bes”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “There are also a few recent works which address the task of early recognition [22], [23].”
Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video (2020, background): “Ryoo [46] introduced the problem of recognizing ongoing actions from streaming video and addressed it proposing an integral histogram of spatio-temporal features.”
Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks (2016, background): “Early detection techniques have been proposed for classifying facial expressions and articulated body motion [12, 32], as well as for predicting future events based on incoming video streams [15, 16].”
Oops! Predicting Unintentional Action in Video (2019, methodology): “In this paper, we base our methods on 3D CNNs. Previous work which studies future action prediction in video is also relevant to predicting unintentionality [48, 44, 72, 22, 11].”
Ongoing human action recognition with motion capture (2014, methodology): “Ryoo [31] has used these bags of words to construct histograms and use them for ongoing activity recognition.”
Fuzzy human motion analysis: A review (2014, methodology): “Early event detection: Apart from that, fuzzy approaches being successful in handl ing the uncertainties in various real-time applications as highlighted in this survey, can b e very well explored to be potentially applied in highly complex HMA applications such as human activity forecasting [2 41] ”
Action-Reaction: Forecasting the Dynamics of Human Interaction (2014, background): “Traditionally dual-agent interactions (e.g.., hugging, pushing) have been represented as a joint phenomenon, where observations from both people are used as features to recognize human interactions from video [22,2,21,8,26].”
r2p2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting (2018, background): “In [17,24,35,36], future activities are predicted via classification-based approaches.”
Progressive Teacher-Student Learning for Early Action Prediction (2019, methodology): “Ryoo [32] intended to recognize ongoing actions by observing some evidences from the features accumulated over time.”
Predicting the Where and What of Actors and Actions through Online Action Localization (2016, methodology): “Inspired from early action recognition and prediction works [26], we also quantify the performance as a function of Video Observation Percentage.”
Classifying actions based on histogram of oriented velocity vectors (2015, methodology): “Motivated by the success of object recognition techniques which ignore local features’ spatial relationships, typically called as bag-of-words, several methods were proposed for human action recognition (Junejo et al. 2010; Li et al. 2010; Ryoo 2011; Wang et al. 2009).”
Part-Activated Deep Reinforcement Learning for Action Prediction (2018, methodology): “We first compared our PA-DRL method with thirteen state-of-the-art action prediction methods, including SVM [31], Bayesian [31], IBOW [31], DBOW [31], SC [2], MSSC [2], Lan et.”