Recognize Human Activities from Partially Observed Videos

By Yu Cao, Daniel Paul Barrett, Andrei Barbu, Siddharth Narayanaswamy, Haonan Yu, Aaron Michaux, Yuewei Lin, Sven J. Dickinson, Jeffrey Mark Siskind, Song Wang. 2013

202 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Computer Vision and Pattern Recognition

Citations in the corpus

Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, methodology): “It has attracted a lot of research attention due to its wide range of applications in security surveillance, human-machine interaction, patient monitoring, etc [1], [2].”
Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video (2020, background): “Cao et al. [47] used sparse coding to recognize actions from partially observed videos.”
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].”
Human Action Recognition and Prediction: A Survey (2018, methodology): “[20,144,220], [117] incorporates an important prior knowledge that informative action information is increasing when new observations are available.”
SSNet: Scale Selection Network for Online 3D Action Prediction (2018, background): “It has attracted a lot of attention due to its wide range of applications in security surveillance, human-machine interaction, patient monitoring, etc [23, 4].”
Social LSTM: Human Trajectory Prediction in Crowded Spaces (2016, unknown): “[55, 8, 71, 67, 44, 58] forecast actions in streaming videos.”
Deep Sequential Context Networks for Action Prediction (2017, methodology): “The proposed approach is significantly different from existing action prediction and early detection approaches [24, 13, 2, 14, 9, 19].”
Approximate MaxEnt Inverse Optimal Control and Its Application for Mental Simulation of Human Interactions (2015, methodology): “We use 10-fold evaluation as in (Cao et al. 2013).”
Real-Time RGB-D Activity Prediction by Soft Regression (2016, methodology): “In addition, most of activity prediction works in literatures focus on predicting human activities from RGB sequences by matching visual appearance and human motion among the activities executed at different progress levels [3, 8, 6, 4, 9].”
What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention (2019, background): “The problem has been widely investigated in the domain of third person vision [2, 4, 6, 9, 19, 23, 24, 39, 46].”
Predicting the Where and What of Actors and Actions through Online Action Localization (2016, methodology): “[2] perform action prediction by applying sparse coding to derive the activity likelihood at small temporal segments, and later combine the likelihoods for all the segments.”
Part-Activated Deep Reinforcement Learning for Action Prediction (2018, methodology): “[2] designed an action prediction model with sparse coding to learn the features and reconstructed the testing partial videos with the bases extracted from the training activities.”
Spatial, Structural and Temporal Feature Learning for Human Interaction Prediction (2016, methodology): “A sparse coding method (SC) is then used to approximate the features of the test video with one matrix basis or a mix- ture of several matrix bases (MSSC).”
Online Action Detection (2016, unknown): “Current work on related problems assumes simplified setups [2, 6, 7, 11, 12, 15].”
A Discriminative Model with Multiple Temporal Scales for Action Prediction (2014, unknown): “Our method captures action dynamics in both local and global temporal scales, while [1,4,14] only use a single temporal scale.”
First-Person Activity Forecasting with Online Inverse Reinforcement Learning (2016, background): “Other works predict actions several seconds into the future [3, 8, 11, 29].”