Joint segmentation and classification of human actions in video

By Minh Hoai Nguyen, Zhenzhong Lan, Fernando De la Torre. 2011

278 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, 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 Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning human activities and object affordances from RGB-D videos (2012, methodology): “Most works (e.g. Hoai et al., 2011; Shi et al., 2011; Matikainen et al., 2012) consider detecting actions at a ‘sub-activity’ level (e.g. walk, bend, and draw) instead of considering high-level activities.”
Unsupervised Semantic Parsing of Video Collections (2015, methodology): “Additionally, several method for localizing instances of actions in rather longer video sequences have been developed [10, 18, 34, 6, 47].”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “The authors [44] and [45] perform activity classification and clustering respectively but do not consider temporal context.”
Modeling transition patterns between events for temporal human action segmentation and classification (2015, methodology): “1) Training Segment-SVM with Max Margin Optimization: We learn discriminative patterns of each peak and transition segments using a multi-class SVM [6] similar to [9].”
Two streams Recurrent Neural Networks for Large-Scale Continuous Gesture Recognition (2016, methodology): “[12] used a discriminative temporal extension of the spatial bag-of-words model and the inference over the segments was”
3D skeleton-based human action classification: A survey (2016, unknown): “Emerging trends are action recognition “ in the wild ” [43 – 48], and action “ localization ” [49 – 53].”
Video-Based Human Behavior Understanding: A Survey (2013, methodology): “Examples include action [77], [105], [174], and interaction analysis [161], [175].”
Action Recognition by Hierarchical Mid-Level Action Elements (2015, methodology): “Moreover, we demonstrate the effectiveness of our model in real-world applications such as action recognition in large-scale untrimmed videos and action parsing.”
Watch-n-patch: Unsupervised understanding of actions and relations (2015, background): “Among them, the linear models [34] [12] [32] [3] are the most popular, which focus on modeling the action transitions in the activities.”
Maximum Margin Temporal Clustering (2012, background): “Also, recall that TC is an unsupervised problem, and it is diﬀerent from the supervised and weakly-supervised temporal segmentation problems (e.g., Hoai et al. (2011); Nguyen et al. (2009); Oh et al. (2008); Shi et al. (2008)).”
Sequential Max-Margin Event Detectors (2014, methodology): “To allow MSO-SVM+DP [7] for on-line event detection, DP was solved in a sliding window (the maximum frame length of training events) moving through the test sequence.”
Poselet Key-Framing: A Model for Human Activity Recognition (2013, background): “Key volumes: Recent video-based action recognition methods [12, 28] observed that limiting the bag of spatiotemporal interest point representation [9, 17] in a temporal segment boosts recognition performance.”
Weakly Supervised Action Labeling in Videos under Ordering Constraints (2014, methodology): “In computer vision, the temporal order of events has been exploited in [25], where a DTW-like algorithm is used at test time to improve the performance of nonmaximum suppression on the output of pre-trained action detectors.”
Human Activity Learning using Object Affordances from RGB-D Videos (2012, methodology): “There has been a lot of work on human activity detection from images [6, 7] and from videos [8, 9, 10, 11, 12, 13, 14, 15, 16].”