Parsing Videos of Actions with Segmental Grammars

By Hamed Pirsiavash, Deva Ramanan. 2014

179 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

Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos (2015, background): “Discriminative variants include those based on latent SVMs over key poses and action grammars [17, 33, 19].”
Temporal Convolutional Networks for Action Segmentation and Detection (2016, background): “typically too short to capture long-range temporal patterns; segmental models [25, 16, 24], which typically condition the current action class on the previous segment, thus ignoring long-range latent dependencies; and recurrent models [28, 10], which empirically can have a limited span of attention ”
Unsupervised Semantic Parsing of Video Collections (2015, methodology): “Additionally, several method for localizing instances of actions in rather longer video sequences have been developed [10, 18, 34, 6, 47].”
Temporal Relational Reasoning in Videos (2017, background): “Besides, many previous works model the temporal structures of videos for action recognition and detection using bag of words, motion atoms, or action grammar [5, 16, 26, 6, 27].”
Moments in Time Dataset: One Million Videos for Event Understanding (2018, background): “classification, and Pirsiavash and Ramanan [33] leveraged grammar models for temporally segmenting actions from video.”
End-to-End Learning of Action Detection from Frame Glimpses in Videos (2015, background): “It must learn to effectively utilize these observations, or frame glimpses, to reason on the temporal bounds of actions.”
Connectionist Temporal Modeling for Weakly Supervised Action Labeling (2016, methodology): “Our use of visual similarities in the training is related to unsupervised video parsing [28,29,45], where frames are grouped into segments based on visual or semantic cues.”
Temporal Segment Networks for Action Recognition in Videos (2017, methodology): “temporal structure of video for action recognition [19], [20], [21], [22], [59], [60].”
CliqueCNN: Deep Unsupervised Exemplar Learning (2016, methodology): “Learning similarities is also of particular importance for posture analysis [8] and video parsing [17].”
Asynchronous Temporal Fields for Action Recognition (2016, background): “Capturing the whole information of the video in terms of temporal evolution of the video stream has been the focus of some recent approaches [51, 6, 12, 35, 49, 30].”
D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation (2019, background): “Action recognition has been an important task for video understanding [13, 27, 33, 36].”
Watch-n-patch: Unsupervised understanding of actions and relations (2015, background): “…them, the temporal structure of actions is often discovered by Markov models such as Hidden Markov Model (HMM) [34] and semi- Markov [12] [32], or by linear dynamical systems [3], or by hierarchical grammars [27] [37] [20] [39] [2], or by other spatiotemporal representations [15] [26] [17] [19].”
Weakly supervised learning of actions from transcripts (2016, background): “in the context of hierarchical action detection, where long activities can be subdivided into smaller action units, several works make use of grammars [6, 20, 21, 22].”
Listen to Look: Action Recognition by Previewing Audio (2019, background): “Recent work includes capturing long-term temporal structure via recurrent networks [74, 11] or ranking functions [17], pooling across space and/or time [63, 23], modeling hierarchical or spatiotemporal information in videos [44, 58], building long-term temporal relations [67, 77], or boosting accura”
Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos (2017, background): “This includes recent progress in scene graphs [13, 20, 51, 64], storylines [1, 14, 17, 31, 53], and action understanding [10, 44, 55].”
An end-to-end generative framework for video segmentation and recognition (2015, background): “A closely related approach was proposed in [21] where action units were combined with a set of production rules to build a grammar to model the hierarchical temporal structure of human activities.”
Dense-Captioning Events in Videos (2017, background): “Early work in activity recognition involved using hidden Markov models to learn latent action states [45], followed by discriminative SVM models that used key poses and action grammars [26, 36, 30].”
Action Recognition by Hierarchical Mid-Level Action Elements (2015, background): “Thus, in order to ∗indicates equal contribution achieve a full understanding of the action that takes place in a scene, one must recognize and parse this complex structure of mid-level action elements (MAEs) at different levels of semantic and spatial-temporal resolution.”
SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition (2019, methodology): “Our approach belongs to the genre of work that performs video classification by aggregating temporal information from long videos [13, 32, 33, 36, 45, 46, 47, 48, 49, 51, 62].”