Script Data for Attribute-Based Recognition of Composite Activities

By Marcus Rohrbach, Michaela Regneri, Mykhaylo Andriluka, Sikandar Amin, Manfred Pinkal, Bernt Schiele. 2012

204 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

Actions ~ Transformations (2015, methodology): “For example, Tang et al. [47] proposed an HMM model to model the duration as well as the transitions of states in event video.”
Coherent Multi-sentence Video Description with Variable Level of Detail (2014, methodology): “We use additional videos from the MPII Composite dataset [20] that correspond to dishes of the TACoS subset.”
Towards a Visual Turing Challenge (2014, background): “Other, lingui stically rich datasets either do not tackle images at all [54, 55] or consider only few in very constraine d domain [15], or are more suitable for the learning an embedding/image-sentence retrieval or lan gu ge generation [22, 56, 57, 58].”
TALL: Temporal Activity Localization via Language Query (2017, methodology): “These objects and actions annotations are from the original MPIICompositive dataset [25].”
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): “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].”
Modeling video evolution for action recognition (2015, background): “Temporal ordering models have also been applied in the context of complex activity recognition [6, 26, 32].”
Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video (2016, methodology): “Current methods explore both high-level representations based on objects, attributes, or scenes [3], [4], [8], [22], [23], as well as holistic frame-level CNN descriptors [4]–[7].”
Discovering Attribute Shades of Meaning with the Crowd (2015, background): “However, in some cases it is possible to generate it (semi-)automatically, as in (Wang et al. 2009; Branson et al. 2010; Berg et al. 2010; Parikh and Grauman 2011a; Rohrbach et al. 2012).”
3D Object Detection with Multiple Kinects (2012, methodology): “Our MPII Multi-Kinect dataset is collected with four Kinect cameras at training and test time in the same kitchen as [18].”
Transfer Learning in a Transductive Setting (2013, methodology): “Words in the text can be matched to labels either literally or by using WordNet expansion [22].”
Grounding Action Descriptions in Videos (2013, methodology): “For the experiments reported below we use the same setup as Rohrbach et al. (2012b) and use all videos in MPII Composites and MPII Cooking (Rohrbach et al., 2012a), excluding the 127 videos used during evaluation.”
A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching (2013, unknown): “The recent data set [24] is also about cooking but it has a fixed scene and no object annotations.”
Temporally Grounding Natural Sentence in Video (2018, methodology): “TACoS3 consists of 127 videos selected from the MPII Cooking Composite Activities video corpus (Rohrbach et al., 2012).”
Latent Hierarchical Model of Temporal Structure for Complex Activity Classification (2014, background): “In this paper, complex activities refer to those with long temporal structures such as Sports actions [12], Cooking Composite actions [17], and so on.”