The LEAR submission at Thumos 2014

By Dan Oneaţă, Jakob Verbeek, Cordelia Schmid. 2014

144 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, background): “action detection approaches are developed for handling offline mode that conducts detection after observing the whole long sequence [22], [23], [68].”
Unsupervised Semantic Parsing of Video Collections (2015, background): “Even though some recent works attempted action recognition in untrimmed videos [21, 43, 20], they are mostly fully supervised.”
End-to-End Learning of Action Detection from Frame Glimpses in Videos (2015, methodology): “It must learn to effectively utilize these observations, or frame glimpses, to reason on the temporal bounds of actions.”
Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks (2016, methodology): “Most published methods are designed for ofﬂine detection [7], which performs detection after fully observing the sequence.”
Predictive-Corrective Networks for Action Detection (2017, methodology): “Temporal action localization: A common way to extend action recognition models to temporal detection is through the sliding windows paradigm [48, 17, 49, 27, 57].”
Temporal Action Detection with Structured Segment Networks (2017, methodology): “On THUMOS14, we compare with the contest results (Wang et al. 2014a; Oneata et al. 2014; Richard and Gall 2016) and those from recent works, including the methods that use segment-based 3D CNN (Shou et al.”
Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints (2017, methodology): “Well studied methods from classical action recognition are frequently used as framewise feature extractors [21, 27, 39, 24].”
Efficient Action Detection in Untrimmed Videos via Multi-task Learning (2016, methodology): “This work was funded in part by a National Science Foundation CAREER grant, #IIS1150115, and a seed grant from the Center for Information Technology in the Interest of Society (CITRIS).”
ConvNet Architecture Search for Spatiotemporal Feature Learning (2017, background): “Some baselines in [13, 43, 25, 3] are SVM classifiers trained on a pool of features that do not specifically address the detection problem.”
UntrimmedNets for Weakly Supervised Action Recognition and Detection (2017, unknown): “[33]∗ 14.”
SST: Single-Stream Temporal Action Proposals (2017, background): “A number of existing methods approach the problem of temporal action localization [19, 22, 26, 27, 31, 32, 35, 40, 24, 30, 38].”
R-C3D: Region Convolutional 3D Network for Temporal Activity Detection (2017, methodology): “Existing state-of-the-art approaches address this task as detection by classiﬁcation , i.e. classifying temporal segments generated in the form of sliding windows [13, 20, 24, 37] or via an external “pro-posal” generation mechanism [10, 35].”
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation (2018, methodology): “For proposal generation, earlier works [23,29,40] directly use sliding windows as proposals.”