Sunday, August 14, 2011

Table of results for COIL-100 dataset

This is a table documenting some of the best results some paper obtained in COIL-100 dataset.

COIL-100 is a dataset containing images of 100 objects, each with 72 views. Here's a link to the official web site for COIL-100.
  1. Nearest Prime Simplicial Complex for Object Recognition (2011)
    Cited 0 times. 97.19%
  2. Multiple-View Object Recognition in Smart Camera Networks (2011)
    Cited 0 times. 95%
  3. Deep Learning from Temporal Coherence in Video (2009)
    Cited 30 times. 92.5%
  4. Deep Learning of Invariant Features via Simulated Fixations in Video (2012)
    Cited 0 times. 82%
    Additional info: Trained also with 
    van Hataren videos (unrelated to COIL-100) obtained 87%

1 comment:

Rakesh Chalasani said...

I think the results shown here are inconsistent. Please note that in first two papers; Nearest Prime Simplicial Complex for Object Recognition (2011) andMultiple-View Object Recognition in Smart Camera Networks (2011); the number samples for training are 8 and 10 respectively and that of Deep Learning from Temporal Coherence in Video (2009) is only 4 (0, 90, 180 and 270 degree). Taking only 4 views is the usually followed protocol and the above mentioned two papers are inconsistent with this.