Completed
Object detection Vs proposed approach
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Contextual Image Understanding and Scene Identification in Videos - Thesis Defense
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Image Understanding using context
- 3 Finding the Shared Context
- 4 Improving understanding on videos usin context • Scene Identification
- 5 Image Representation: Top-Down Visual Tree (TDVT)
- 6 How to learn TDVT representations?
- 7 A. Dataset Parsing (pre-processing)
- 8 Inference
- 9 A Labels: Top-down Tree LSTM
- 10 Model: Top-Down Tree LSTM
- 11 B Training 4 Classifiers: Is the node having an X edge? Train 4 classifiers
- 12 Evaluation: User study
- 13 Object detection Vs proposed approach
- 14 Evaluation: Object detection across datasets
- 15 Proposed Framework
- 16 Words weights for each query image
- 17 Incorporation of Context (Random Walk)
- 18 Incorporation of Context Random Walk
- 19 Experimental setup
- 20 Qualitative Results Image Retrieval Application from multiple
- 21 Quantitative results
- 22 Improving Scene identification on Videos
- 23 Improve scene Identification
- 24 Object detection on videos using context
- 25 Improve Object Detection
- 26 Experiments (scene identity)
- 27 Experiments (object detection)
- 28 Conclusions
- 29 Future Work (Image representation)
