| AGM | Active Grammar Model |
| API | Application Programming Interface |
| CA | Cognitive Attention |
| CNN | Convolutional Neural Network |
| CS | Cognitive Subtraction |
| DNN | Deep Neural Network |
| FLOP | Floating Point Operations |
| GPU | Graphic Process Unit |
| ILSVRC | ImageNet Large-Scale Visual Recognition Challenge |
| MCG | Multiscale Combinatorial Grouping |
| PLSA | Passive Learning Sensor Architecture |
| R-CNN | Regions with Convolutional Neural Networks |
| RELU | Rectifier Linear Unit |
| RGB-D | Red Green Blue Depth |
| ROI | Region Of Interest |
| SIFT | Scale Invariant Feature Transform |
| SP | Semantic Processing step |
| SV | Semantic Vector |
| SVM | Support Vector Machine |
| TH | Top-Hat |
| t-SNE | t-distributed Stochastic Neighbor Embedding |
| VGG | Visual Geometry Group |
| VOC | Visual Object Challenge |