A Data-Driven Approach for Event Prediction

By Jenny Yuen, Antonio Torralba. 2010

105 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Generating Videos with Scene Dynamics (2016, background): “Our work is also related to efforts to predict the future in video [33, 22, 44, 51, 42, 17, 8, 55] as well as concurrent work in future generation [6, 15, 20, 50, 56, 43].”
Unsupervised Learning for Physical Interaction through Video Prediction (2016, methodology): “[30] used a nearest neighbor approach to construct predictions from similar videos in a dataset.”
An Uncertain Future: Forecasting from Static Images Using Variational Autoencoders (2016, methodology): “While this representation is intuitive, the output space is high dimensional and hard to parametrize, an issue which forced [1] to use a Nearest Neighbor algorithm and transfer raw trajectories.”
"What Happens If..." Learning to Predict the Effect of Forces in Images (2016, background): “[41] predict future events that might take place in a query image.”
Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images (2015, background): “Data-driven approaches have been proposed in [37, 25] to predict motion field in a single image.”
Learning to Generate Long-term Future via Hierarchical Prediction (2017, background): “Other existing works focus on predicting high-level semantics, such as trajectories or action labels (Walker et al., 2014; Chao et al., 2017; Yuen & Torralba, 2010; Lee, 2015), driven by immediate applications (e.g., video surveillance).”
Dense Optical Flow Prediction from a Static Image (2015, background): “Some of the initial work in this area focused on predicting the optical flow for the given input image [28].”
Learning Temporal Transformations from Time-Lapse Videos (2016, methodology): “Future prediction: Future prediction has been applied to various tasks such as estimating the future trajectories of cars[11], pedestrians[12], or general objects[13] in images or videos.”
Anticipating the future by watching unlabeled video (2015, background): “Torralba et al. [41] use millions of Internet images to build object and scene recognition systems.”
Temporal Perception and Prediction in Ego-Centric Video (2015, background): “Prediction: Recently, the idea of predicting the future has been introduced for tasks such as estimating the future trajectories of cars [36], pedestrians [19, 39], or general objects [40] in images or videos.”
A Hierarchical Representation for Future Action Prediction (2014, background): “There are also literatures on predicting motion from still images [29].”
Who Let the Dogs Out? Modeling Dog Behavior from Visual Data (2018, background): “[51, 30] predict the motion of objects in a static image using a large collection of videos.”
Anticipating Visual Representations from Unlabeled Video (2015, background): “Pioneering work in computer vision has capitalized on unlabeled videos before to visualize the future [31, 36, 39] and predict motions [28, 40, 43].”
The Pose Knows: Video Forecasting by Generating Pose Futures (2017, background): “Models that either try to directly forecast pixels [27, 33, 42, 47, 54] or pixel motion [9,30,48,50,55] are forced to perform all of these tasks simultaneously.”
Patch to the Future: Unsupervised Visual Prediction (2014, methodology): “However, having a richer output space requires richer represen- 4321 tation (elements of reasoning) and lots of data to learn the priors.”
Predicting Actions from Static Scenes (2014, background): “Yuen and Torralba [17] predict motion for images of static scenes by searching and transferring motion cues from video scenes with similar appearance.”
Human Activity Recognition Using Recurrent Neural Networks (2017, unknown): “The data-driven approaches are capable of handling uncertainties and temporal information [10] but require large datasets for training and learning.”
Decomposing Motion and Content for Natural Video Sequence Prediction (2017, background): “It has led to various tasks depending on the objective of future prediction, such as human activity (Vondrick et al., 2015; Ryoo, 2011; Lan et al., 2014), event (Yuen and Torralba, 2010; Hoai and Torre, 2013) and geometric path (Walker et al., 2014).”