Recognizing human actions by attributes

By Jingen Liu, Benjamin Kuipers, Silvio Savarese. 2011

630 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

Transductive Multi-View Zero-Shot Learning (2015, background): “X S ∈ R n s × t and X T ∈ R n T × t denote the t − dimensional low-level feature vectors of auxiliary and target instances respectively. z S and z T are the auxiliary and target class label vectors.”
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].”
An embarrassingly simple approach to zero-shot learning (2015, background): “This has proved to be particularly useful for images [10, 11, 21], as well as videos [13, 24].”
Evaluation of output embeddings for fine-grained image classification (2014, background): “caption generation [28, 39], face recognition [48, 6], image retrieval [49, 11], action recognition [33, 57] and image classification [29, 2].”
Zero-Shot Object Detection (2018, background): “Zero-shot learning has been shown to be effective in situations where there is a lack of annotated data [12,14,31,38,53,54,59,60].”
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].”
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].”
Clothing Attributes Assisted Person Reidentification (2015, methodology): “[16] use an information theoretic approach to discover the attributes of human actions automati-”
Posebits for Monocular Human Pose Estimation (2014, background): “Advantages of attributes have been demonstrated for object categorization [8, 25], and human action recognition [11, 28] with emphasis on transfer learning between classes.”
Attribute Learning for Understanding Unstructured Social Activity (2012, methodology): “Like [13], we therefore use standard classifiers to learn this mapping from the γis obtained from our SLAS attribute learner.”
High-level event recognition in unconstrained videos (2012, background): “Movements can also be referred as attributes which have been recently used in human action recognition [73] following their successful use in face recognition in a single image.”
A Discriminative Model with Multiple Temporal Scales for Action Prediction (2014, neutral): “This problem has been addressed by introducing human knowledge into models and using semantic descriptions or attributes to characterize complex human actions [7,8,10].”
Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions (2017, methodology): “Inspired by zero-shot image classification [24], several works have performed zero-shot action classification by learning a mapping of actions to attributes [11, 30, 64].”
Video Event Understanding Using Natural Language Descriptions (2013, methodology): “[14] uses attributes to perform action recognition in videos.”
Transfer Learning in a Transductive Setting (2013, background): “To transfer labels from labeled to unlabeled data label propagation is widely used [34, 33] and has shown to work successfully in several applications [13, 7].”
A Comparative Study of Encoding, Pooling and Normalization Methods for Action Recognition (2012, methodology): “In ℓ1 normalization , feature p is normalized by its ℓ1-norm: p=p/ í µí± í µí± í µí°¾ í µí±=1 L2, In ℓ2 normalization [4], feature p is normalized by its ℓ2-norm: p=p/ í µí± í µí± 2 í µí°¾ í µí±=1 Power, In power normalization , we apply the following function for each dimension of feature p :”
Human action recognition by learning bases of action attributes and parts (2011, background): “Inspired by the recent work of learning attributes for object recognition [7, 13, 1, 21] and action recognition in videos [17], the attributes we use are linguistically related description of the actions.”
Action Recognition with Actons (2013, background): “More recently, along the line of research on attributes for 2D static images [25], dedicated efforts have been given to designing/learning mid-level representations [15, 23, 21] for action recognition in dynamic videos, and promising results greatly inspire researchers to explore this direction.”