Learning realistic human actions from movies

By Ivan Laptev, Marcin Marszalek, Cordelia Schmid, Benjamin Rozenfeld. 2008

3,817 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

End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, methodology): “Most existing methods [23, 34, 38, 39] rely on supervised learning and, therefore, require large-scale, diverse and representative action datasets for training.”
Joint Discovery of Object States and Manipulation Actions (2017, background): “Most of the prior work on action recognition has focused on designing features to describe time intervals of a video using motion and appearance [30, 39, 43, 44].”
Unsupervised Learning from Narrated Instruction Videos (2015, background): “Particularly related to ours is the work [4] which explores the known order of events to localize and learn actions in training data.”
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (2017, methodology): “In our model comparisons, we did not consider more classic approaches such as bag-of-visual-words representations [6, 19, 21, 30].”
Two-Stream Convolutional Networks for Action Recognition in Videos (2014, methodology): “Recognition of human actions in videos is a challenging task which has received a significant amount of attention in the research community [11, 14, 17, 26].”
The Kinetics Human Action Video Dataset (2017, background): “This is in the spirit of bag of words image modeling approaches [16, 17, 24], but while convenient in practice, it has the issue of entirely ignoring temporal structure (e.g. models can’t potentially distinguish opening from closing a door).”
Dense-Captioning Events in Videos (2017, background): “With the introduction of large scale activity datasets [22, 19, 12, 4], it has become possible to categorize videos into a discrete set of action categories [27, 10, 9, 40, 35].”
A Joint Sequence Fusion Model for Video Question Answering and Retrieval (2018, background): “Video classification [14,15,16,17,18] can be a candidate solution, but tagging only a few labels to a video may be insufficient to fully relate multiple latent events in the video to a language description.”
HMDB: A large video database for human motion recognition (2011, methodology): “The sets were built to ensure that clips from the same video were not used for both training and testing and that the relative proportions of meta tags such as camera position, video quality, motion, etc. were evenly distributed across the training and testing sets.”
A dataset for Movie Description (2015, methodology): “Second, we propose to use semantic parsing of the sentence to extract training labels for recently proposed translation approach [56] for video description.”
Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding (2016, background): “Standard approaches in the past have used videos downloaded from the Internet [3,4,5,6,7,8] gathered from movies [9,10,11] or recorded in controlled environments [12,13,14,15,16,17].”
YouTube-8M: A Large-Scale Video Classification Benchmark (2016, methodology): “Inspired by the success of various classic bag of words representations for video classiﬁcation [23, 36], we next consider a Deep Bag-of-Frames (DBoF) approach.”
Weakly Supervised Action Labeling in Videos under Ordering Constraints (2014, methodology): “This type of weak supervisory signal has been used before in classification [22] and temporal localization [7] tasks.”
Beyond short snippets: Deep networks for video classification (2015, methodology): “These features are then encoded in order to produce a global video-level descriptor through bag of words (BoW) [17] or Fisher vector based encodings [23].”
SlowFast Networks for Video Recognition (2018, methodology): “These methods, including histograms of flow [33], motion boundary histograms [6], and trajectories [53], had shown competitive performance for action recognition before the prevalence of deep learning.”
Differential Recurrent Neural Networks for Action Recognition (2015, background): “Many spatio-temporal descriptors, such as 3D-SIFT [26] and HoGHoF [17], have been proposed to localize and encode the salient spatio-temporal points.”
Cross-View Action Modeling, Learning, and Recognition (2014, methodology): “We exploit commonly used HOG [1] and HOF [9] features to represent the appearance and motion of a given part, respectively.”
Learning human activities and object affordances from RGB-D videos (2012, methodology): “There has been a lot of work on human activity detection from images (Yang et al., 2010; Yao et al., 2011) and from videos (Laptev et al., 2008; Liu et al., 2009; Hoai et al., 2011; Shi et al., 2011; Matikainen et al., 2012; Pirsiavash and Ramanan, 2012; Rohrbach et al., 2012; Sadanand and Corso,…”