8 Questions 24 Answers 0 Followers
Questions related from Konstantinos Avgerinakis
I was wondering if anyone knows or have published a technique that sucessfully combines shallow (HOG, SIFT, LBP) with deep (GoogLeNet) representation? I am interested both for images and video cases.
09 September 2017 5,273 3 View
Which are the best available face expression techniques? Any literature/survey, code and dataset available free online? Is there any ground of progress for Kinect sensor?
11 November 2013 4,554 1 View
Particle filtering, PSO, mean shift, Kalman filter are used for tracking objects within video sequences. Under your consideration which one is the most accurate one? Do you have in mind any code...
09 September 2013 6,947 10 View
I am searching for a good visualization tool for presenting my research results in a conference. Do you have any fancy tools in mind?
08 August 2013 4,314 4 View
Which journal is the most appropriate one for computer vision publications? (Name - Impact Factor)? My work proposes an ambient assisted living (AAL) solution based on computer vision...
08 August 2013 6,009 6 View
Several Bag-of-Words techniques appear in the literature for representing either actions or objects, extracted from video sequences and images respectively, into sparse histograms of primitives...
08 August 2013 7,478 5 View
Considering that video recordings took place in a home based environment. Do you believe that skin detection could actually segment human persons from background objects with similar colour (e.g....
07 July 2013 1,934 7 View
I have noticed that someone can find a lot of work on Human activity recognition, but just a few ones focus on human activity detection problem (also referred in literature as activity...
07 July 2013 3,477 20 View