Task assignment with unknown duration

By Kris M. Kitani, Brian D. Ziebart, J. Bagnell, Martial Hebert. 2000

951 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Reinforcement Learning

How researchers see this paper

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

In Computer Networks and Communications

In Information Systems

In Reinforcement Learning

Citations in the corpus

Generating Videos with Scene Dynamics (2016, background): “ frame prediction. Our framework can generate videos for longer time scales and learn representations of video using unlabeled data. 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, ”
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”
MERLOT: Multimodal Neural Script Knowledge Models (2021, background): “There has been a large body of work on analyzing ‘what happens next’ in videos [48].”
Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “Previous work considers future localization [113, 120, 174, 230], action anticipation [76, 77, 86, 118, 127, 219], next active object prediction [20, 74], future event prediction [149,167], and future frame prediction [145,146,153,215,218,227].”
Stochastic Prediction of Multi-Agent Interactions from Partial Observations (2019, methodology): “…the agents is assumed to be known (e.g., using fully connected graphs or using a sparse graph derived from spatial proximity), as in the social LSTM (Alahi et al., 2016) and the social GAN (Gupta et al., 2018), or methods based on inverse optimal control (Kitani et al., 2017; Lee et al., 2017).”
C3D: Generic Features for Video Analysis (2014, background): “The computer vision community has been working on video analysis for decades and tackled different problems such as action recognition [2, 31, 40], abnormal event detection [3, 7, 55], and activity understanding [29].”
An Uncertain Future: Forecasting from Static Images Using Variational Autoencoders (2016, background): “Others predict labeled human walking trajectories [14] or object trajectories [15] in restricted domains.”
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos (2015, background): “For example, if the input is a frame depicting a person cocking his arm to throw, the model could predict future actions such as Catch or Hit.”
"What Happens If..." Learning to Predict the Effect of Forces in Images (2016, background): “[16] estimate future movements of humans in a given scene.”
An Algorithmic Perspective on Imitation Learning (2018, background): “Recently, inverse reinforcement learning with partially observable expert demonstrations has gained interest in vision research [Kitani et al., 2012] and robotics [Boularias et al., 2012, Bogert and Doshi, 2014, 2015, Bogert et al., 2016].”
Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images (2015, background): “Future trajectories of people are inferred in [19].”
Learning to Decompose and Disentangle Representations for Video Prediction (2018, background): “Visual prediction is a core problem in computer vision that has been studied in several contexts, including activity prediction and early recognition [20, 30], human pose and trajectory forecasting [1, 18], and future frame prediction [22, 31, 39, 44].”
Dense Optical Flow Prediction from a Static Image (2015, background): “For example, in case of agents such as humans, the output space of prediction can be trajectories themselves [10].”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, methodology): “Maximum entropy inverse reinforcement learning was used by [48], [49], [50] to obtain a distribution over possible human navigation trajectories from visual data, and also used to model the forthcoming interactions with pedestrians for mobile robots [48], [50].”
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.”
Maximum Entropy Deep Inverse Reinforcement Learning (2015, methodology): “Lines 4 and 5 are explained in detail in the algorithms 2 and 3 respectively, and are adapted from (Kitani et al., 2012).”
Inferring the Why in Images (2014, background): “There also has been work in forecasting activities [16, 32] and early event detection [11], but they are interested in predicting the future in videos while we wish to explain the motivations of actions.”
Asynchronous Temporal Fields for Action Recognition (2016, background): “Moving beyond appearance and reasoning about the state of agents in the images requires understanding human intentions [16, 31].”