Completed
Training data Vectors are histograms, one from each training image
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Bag of Words Model for Image Classification - Lecture 16
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Difficulties: within class variations
- 3 Bag-of-features - Origin: texture recognition
- 4 Bag of Words Model
- 5 Bag-of-features - Origin: bag-of-words (text)
- 6 Bag-of-features for image classification
- 7 feature extraction
- 8 Dense features
- 9 Step 2: Quantization
- 10 K-means Clustering: Step 1 Algorithm: kmeans, Distance Metric Euclidean Distance
- 11 Example: 3-means Clustering
- 12 Examples for visual words
- 13 Training data Vectors are histograms, one from each training image
- 14 Examples for misclassified images
- 15 Evaluation of image classification
- 16 PASCAL 2007 dataset
- 17 Results for PASCAL 2007
- 18 Step 3: Classification
- 19 Image representation
- 20 Spatial pyramid matching
- 21 Spatial pyramid representation
- 22 Scene classification
- 23 Retrieval examples
- 24 Category classification - CalTech 101
- 25 Discussion
- 26 Weizmann Action Dataset
- 27 KTH Data Set
- 28 UCF Sports Action Dataset
- 29 IXMAS Multi-view Data Set
- 30 UCF YouTube Action Dataset (UCF-11)
- 31 Bag of Visual Words model (II)
- 32 Histogram of Optical flow (HOF)
- 33 HOF Steps
