Action bank: A high-level representation of activity in video

By Sreemanananth Sadanand, Jason J. Corso. 2012

809 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

Delving Deeper into Convolutional Networks for Learning Video Representations (2015, methodology): “While previous work has traditionally relied on hand-crafted and task-speciﬁc representations (Wang et al., 2011; Sadanand & Corso, 2012), there is a growing interest in designing general video representations that could help solve tasks in video understanding such as human action recognition,…”
3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, background): “Several compositional approaches were studied for complex scenarios and achieved substantial progresses[33, 29, 39, 21, 23, 30, 4, 15], and they decomposed an activity into deformable parts and enriched the models with contextual information.”
Cross-View Action Modeling, Learning, and Recognition (2014, methodology): “STIP [8] and Action Bank [16] do not perform well on this dataset, either.”
Learning human activities and object affordances from RGB-D videos (2012, background): “n activity detection from 2D videos. There has been a lot of work on human activity detection from images (Yang et al., 2010; Yao et al., 2011) and from videos (Liu et al., 2009; Laptev et al., 2008; Sadanand and Corso, 2012; Shi et al., 2011; Hoai et al., 2011; Matikainen et al., 2012; Tang et al.,”
Video Representation Learning Using Discriminative Pooling (2018, background): “[51], or mid-level representations on them, such as Fisher Vectors [34].”
Action recognition with trajectory-pooled deep-convolutional descriptors (2015, background): “To overcome this issue, several mid-level and high-level video representations have been proposed such as Action Bank [22], Dynamic-Poselets [37], Motionlets [35], Motion Atoms and Phrases [34], and Actons [42].”
Actions ~ Transformations (2015, background): “Mid-to high-level representation are also used to model complex actions [41, 55, 36, 60, 14, 24].”
A Closer Look at Spatiotemporal Convolutions for Action Recognition (2017, background): “Some proposed video representations include spatiotemporal interest points (STIPs) [21], SIFT-3D [27], HOG3D [18], Motion Boundary Histogram [5], Cuboids [6], and ActionBank [26].”
Jointly Modeling Deep Video and Compositional Text to Bridge Vision and Language in a Unified Framework (2015, methodology): “CCA CCA (Socher and Fei-Fei 2010) has been used to build an image-text space, we use CCA as a baseline to build the video-language space and compare video retrieval/text retrieval with our method.”
Moments in Time Dataset: One Million Videos for Event Understanding (2018, background): “Sadanand and Corso [34] designed ActionBank as a high-level representation for video and action classification, and Pirsiavash and Ramanan [33] leveraged grammar models for temporally segmenting actions from video.”
Temporal Generative Adversarial Nets with Singular Value Clipping (2016, methodology): “In supervised learning of videos, while a common approach is to use dense trajectories [45, 30, 29], recent methods have employed CNN and achieved state-of-the-art results [14, 16, 33, 43, 24, 46, 47].”
VideoLSTM convolves, attends and flows for action recognition (2016, neutral): “We reckon and value the impact of traditional video representations, e.g., [3,4,5,19,20,21,22], and recent mixtures of shallow and deep encodings e.g., [23,24].”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “Another approach is to represent activities as collections of semantic attributes [18], [19], [20], [21].”
Asynchronous Temporal Fields for Action Recognition (2016, background): “Recently there has been a push towards mid-level representations of video [37, 46, 13, 20], that capture beyond local properties.”
Anticipating the future by watching unlabeled video (2015, methodology): “We also tried to train a deep network to forecast ActionBank [36] in the future instead of fc7, which performed worse.”
Learning to Share Latent Tasks for Action Recognition (2013, methodology): “We adopt the same experiment setup in [22] to repeat the experiment for 5 times.”