Hierarchical Clustering Multi-Task Learning for Joint Human Action Grouping and Recognition

By Anan Liu, Yuting Su, Wei-zhi Nie, Mohan Kankanhalli. 2017

374 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

A Survey on Multi-Task Learning (2017, background): “Task Clustering Image segmentation [224] Brain-computer interfaces [225] Age estimation [226] Personalized medical Facial action unit treatment [227] prediction [228] Genetic trait prediction [218] Action recognition [229]”
Graph Structured Network for Image-Text Matching (2020, background): “The local correspondence policy has also been widely used in other fields [32, 17], like [17] that learns distinction and connection among multi-tasks.”
Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction (2019, background): “From traditional hand-crafted features [32, 18, 4, 7, 31, 41] to deep neural networks derived features [44, 11, 8, 35, 15, 23], the improvements are obvious.”
Towards Universal Object Detection by Domain Attention (2019, background): “Various multi-task networks [25, 62, 13, 28, 50, 63] have been proposed for joint solution of tasks such as object recognition, object detection, segmentation, edge detection, human pose, depth, action recognition, etc.”
Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks (2017, methodology): “ networks to implement E. 3.2. Classiﬁcation Objective As label prediction in Eq. (1) is fundamentally a ranking problem, we use a large-margin based ranking loss function for classiﬁcation objective [14,61,32], i.e., given a training pair (x;l) we want a higher dot-product similarity between y l an”
Ordered Pooling of Optical Flow Sequences for Action Recognition (2017, methodology): “There have been extensions of this approach to also include semantics of the action, such as using Fisher vectors [21, 30], using bag of visual words model [19] or combining with depth data [17].”
Fusing shape and motion matrices for view invariant action recognition using 3D skeletons (2017, background): “Human action recognition has been an active research topic in computer vision due to its wide applications in humancomputer interaction and video analysis [1, 2, 3, 4, 5, 6].”
MetaSearch: Incremental Product Search via Deep Meta-Learning (2020, background): “In recent years, many studies have focused on product image classiﬁcation and recognition [28], [53], [54].”
Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning (2020, background): “Though sharing similarities with image-text matching, the video-text matching task is more challenging because videos contain multi-modalities and spatial-temporal evolution [3, 26, 28].”
Video Visual Relation Detection (2017, background): “In action recognition, feature representation plays a crucial role in handling large intra-class variation, background clutter, and camera motion [20, 26, 40].”