Human action recognition by learning bases of action attributes and parts

By Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy Lai Lin, Leonidas J. Guibas, Li Fei-Fei. 2011

683 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

Growing a Brain: Fine-Tuning by Increasing Model Capacity (2017, methodology): “…available baselines and report multi-class Tasks and datasets: We evaluate on standard benchmark datasets for scene classiﬁcation: MIT-67 [44], for ﬁne-grained recognition: Caltech-UCSD Birds (CUB) 200 - 2011 [48] and Oxford 102 Flowers [27], and for action recognition: Stanford-40 actions [54].”
Learning Visual Features from Large Weakly Supervised Data (2015, methodology): “…comprising a range of computer-vision tasks: (1) the MIT Indoor dataset [38], (2) the MIT SUN dataset [55], (3) the Stanford 40 Actions dataset [57], (4) the Oxford Flowers dataset [33], (5) the Sports dataset [17], (6) the ImageNet ILSVRC 2014 dataset [42], and (7) the Pascal VOC 2007 dataset…”
Learning Features by Watching Objects Move (2016, methodology): “We minimally tuned some hyper-parameters (we increased the step size to allow longer training) on VOC 2007 validation, and used the same settings for both VOC 2007 and Stanford 40 Actions.”
Joint Discovery of Object States and Manipulation Actions (2017, background): “Modeling co-occurrences of objects and actions have shown benefits for recognizing actions in [11, 19, 26, 35, 47].”
Learning Deep Features for Discriminative Localization (2015, methodology): “We then use GoogLeNet-GAP to extract features again from the crops inside the bounding box, for training and testing.”
Network Dissection: Quantifying Interpretability of Deep Visual Representations (2017, background): “001 on the training data for action40 action recognition task [34].”
Interpreting Deep Visual Representations via Network Dissection (2017, neutral): “We include the event8 [51], action40 [52], indoor67 [53], sun397 [54], caltech101 [55], and caltech256 [56].”
Online Continual Learning under Extreme Memory Constraints (2020, methodology): “To this end, as a supplement to the experiments shown in the main paper, we test our method on Stanford 40 Actions [4], a dataset for understanding human actions in still images.”
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting (2018, methodology): “We divide both CUB-200 Birds and Stanford-40 Actions datasets into four groups of an equal number of classes.”
Learning human activities and object affordances from RGB-D videos (2012, background): “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,…”
Class-Incremental Learning: Survey and Performance Evaluation on Image Classification (2020, neutral): “Next, we use several ﬁne-grained classiﬁcation datasets: Oxford Flowers [102], MIT Indoor Scenes [103], CUB-200-2011 Birds [104], Stanford Cars [105], FGVC Air-craft [106], and Stanford Actions [107].”
Contextual Action Recognition with R*CNN (2015, methodology): “We run R∗CNN on the Stanford 40 Actions dataset [33].”
Cross-Task Weakly Supervised Learning From Instructional Videos (2019, methodology): “This is similar to attributes [12, 13], which have been used in action recognition in the past [23, 33].”
Ternary Feature Masks: continual learning without any forgetting (2020, methodology): “We evaluate our approaches on a larger lower resolution dataset (tiny ImageNet ILSVRC2012 [38]), on a large-scale dataset (ImageNet [39]) and some ﬁne-grained classiﬁcation datasets: Oxford 102 Flowers [40], CUB-200-2011 Birds [41] and Stanford Actions [42].”
Weakly-Supervised Learning of Visual Relations (2017, background): “This task was studied for the special case of human-object interactions [8, 9, 17, 38, 39, 48, 49, 50], where the triplet is in the form ( person, action, object ) .”
Latent Embeddings for Zero-Shot Classification (2016, background): “They are typically collected through costly human annotation [7, 17, 28] and have shown promising results [1, 3, 6, 20, 22, 33, 34, 40] in various computer vision problems.”
Label-Embedding for Image Classification (2015, neutral): “Attributes have been used for image description [19], [18], [9], caption generation [27], [41], face recognition [29], [51], [10], image retrieval [28], [56], [15], action recognition [32], [69], novelty detection [62] and object classiﬁcation [30], [18], [64], [65], [34], [54], [38].”