Parsing video events with goal inference and intent prediction

By Mingtao Pei, Yunde Jia, Song-Chun Zhu. 2011

164 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, methodology): “In this work, we develop an expressive configurable human activity model to address the above mentioned issues, absorbing the powers of two promising techniques of broad interests: deep learning [13, 7, 11, 8, 34, 18, 32] and reconfigurable part-based models [41, 1, 22, 16].”
Joint Video and Text Parsing for Understanding Events and Answering Queries (2013, methodology): “It has been employed in computer vision to model objects [6], scenes [7], [8] and events [9], [10].”
Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images (2015, background): “Action Recognition: Early prediction of activities has been discussed in [29, 27, 16, 23].”
Anticipating the future by watching unlabeled video (2015, background): “Although going from these abstract representations to exact pixel values is not easy ...”
Predicting Deeper into the Future of Semantic Segmentation (2017, background): “by explicitly forecasting trajectories of people and other objects in future video frames [1, 12, 15, 21, 23, 29].”
Modeling 4D Human-Object Interactions for Event and Object Recognition (2013, methodology): “In addition to recognizing the entire event, modeling and recognizing these atomic events are also important, especially in the real applications, like predicting agent’s goal and intention in actions [12].”
Learning Perceptual Causality from Video (2013, methodology): “2013], coupled with the Temporal And-Or Graph [Pei et al. 2011].”
Learning a Generative Model for Multi‐Step Human‐Object Interactions from Videos (2019, methodology): “Although this literature is broad, it is largely based on fully supervised classiﬁcation of video clips [LMSR08,EBMM03,RA09] and only a few methods exist to synthesize interactions [SPYZ11,PJZ11] or to structure the causal dependencies of human actions [FZ16].”
Anticipating Visual Representations from Unlabeled Video (2015, background): “Pei et al. [26] and Xie et al. [42] infer people’s intention in performing actions which is a good clue for predicting future actions.”
Temporal Perception and Prediction in Ego-Centric Video (2015, methodology): “More generally, some methods have looked at ideas related to human intent and goal inference for prediction using Stochastic Context Sensitive Grammars [28] or social models of behavior [39].”
Patch to the Future: Unsupervised Visual Prediction (2014, methodology): “For longer term predictions, models such as Markov Decision Process (MDP) [18, 35], Markov Logic Networks [29], ATCRF [19], CRF [8], and AND-OR graphs [12, 25] are used.”
Learning Maximum Margin Temporal Warping for Action Recognition (2013, methodology): “One approach to handle the the temporal structure is based on statistical generative models, such as HMM [12], dynamic Bayes nets [29], stochastic grammar [17] and CRFs [15].”
Prediction of Human Activity by Discovering Temporal Sequence Patterns (2014, background): “an effective representation for prediction, human activities can be characterized by a complex temporal composition of constituent simple actions and interacting objects.”
A combined pose, object, and feature model for action understanding (2012, background): “[23] develop a model for understanding activity through relations between people and objects.”
A Deep Structured Model with Radius–Margin Bound for 3D Human Activity Recognition (2015, methodology): “Our model is inspired by the effectiveness of two widely successful techniques: deep learning [21, 14, 20, 16, 48, 26, 45] and the latent structured models [56, 11, 1, 32, 24].”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “scenes by function and activity [26], where the attraction fields are longer range in a scene than the functionality maps [27, 107] and affordance maps [108, 109, 110] studied in recent literature; (iv) understanding multifaceted relationships among a group of people and their functional roles [111,”