Action from Still Image Dataset and Inverse Optimal Control to Learn Task Specific Visual Scanpaths

By Stefan Mathe, Cristian Sminchisescu. 2013

60 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Reinforcement Learning

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 Reinforcement Learning

Citations in the corpus

Extreme Clicking for Efficient Object Annotation (2017, background): “Alternative types of supervision information such as eye-tracking data [44, 46], text from news articles or web pages [17, 28], or even movie scripts [7] have also been explored.”
Recurrent Models of Visual Attention (2014, neutral): “[15, 22]).”
Top-down visual saliency via joint CRF and dictionary learning (2012, methodology): “In addition, we briefly describe the relevant CRF and dictionary learning methods.”
Pictorial Human Spaces: How Well Do Humans Perceive a 3D Articulated Pose? (2013, methodology): “To evaluate how consistent the subjects are in their order of fixating areas of interest (AOIs), we used the hidden Markov modeling recently developed by [14].”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, background): “Alternative types of supervision information such as eye-tracking data [44, 46], text from news articles or web pages [17, 28], or even movie scripts [7] have also been explored.”
A Neural Autoregressive Approach to Attention-based Recognition (2015, background): “Recently, Mathe and Sminchisescu (2013) showed that the choice of fixation points is highly dependent on the tasks being solved, even for the same given image.”
Saliency-based Sequential Image Attention with Multiset Prediction (2017, methodology): “While we focus on using reinforcement learning for multiset classification with only class labels as annotation, RL has been applied to other computer vision tasks, including modeling eye movements based on annotated human scan paths [29], optimizing prediction performance subject to a computational”
Reinforcement Learning for Visual Object Detection (2016, methodology): “More recently, reinforcement learning[36] has been applied to visual analysis problems like image classification[24, 19, 29], face detection[14], tracking and recognizing objects in video[2], learning a sequential policy for RGB-D semantic segmentation[1], or scanpath prediction[27].”
TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking (2015, background): “[26, 23, 18] demonstrated that eye tracking datasets on a larger scale are critical to leverage the power of machine learning techniques and greatly improve the performance of visual attention models.”