Food-101 - Mining Discriminative Components with Random Forests
Explore this paper's citation graph
Summary
A novel method to mine discriminative parts using Random Forests (rf), which allows us to mine for parts simultaneously for all classes and to share knowledge among them, and compares nicely to other s-o-a component-based classification methods.
- Published
- 2014-09-06
- Cited by
- 3,522
- References
- 42
- Access
- Open access
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:12726540
References
- Real-Time Mobile Food Recognition System
- Three things everyone should know to improve object retrieval
- Ensemble of exemplar-SVMs for object detection and beyond
- Combining randomization and discrimination for fine-grained image categorization
- Efficient Graph-Based Image Segmentation
- Structured class-labels in random forests for semantic image labelling
- Cutting-plane training of structural SVMs
- Blocks That Shout: Distinctive Parts for Scene Classification
- Automatic Chinese food identification and quantity estimation
- Vlfeat: an open and portable library of computer vision algorithms
- Selective Search for Object Recognition
- Validity of the Remote Food Photography Method (RFPM) for estimating energy and nutrient intake in near real-time
- PFID: Pittsburgh fast-food image dataset
- A food image recognition system with Multiple Kernel Learning
- Semantic texton forests for image categorization and segmentation
- Max-Margin Multiple-Instance Dictionary Learning
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Harvesting Mid-level Visual Concepts from Large-Scale Internet Images
- Platemate: crowdsourcing nutritional analysis from food photographs
- Learning Collections of Part Models for Object Recognition
Cited by
- Context Based Image Analysis With Application in Dietary Assessment and Evaluation
- Mining Mid-level Visual Patterns with Deep CNN Activations
- From categories to subcategories: Large-scale image classification with partial class label refinement
- Mid-level deep pattern mining
- Image Representations and New Domains in Neural Image Captioning
- What’s Cookin’? Interpreting Cooking Videos using Text, Speech and Vision
- PlateClick: Bootstrapping Food Preferences Through an Adaptive Visual Interface
- Fine-Grained Image Search
- Fine-Grained Image Classification by Exploring Bipartite-Graph Labels
- Learning Concept Embeddings with Combined Human-Machine Expertise
- No spare parts: Sharing part detectors for image categorization
- Im2Calories: Towards an Automated Mobile Vision Food Diary
- BubbLeNet: Foveated Imaging for Visual Discovery
- Large-Scale Image Recognition with Random Forests
- A Structured Committee for Food Recognition
- Incremental Learning of Random Forests for Large-Scale Image Classification
- Max-margin analysis based patch sampling for discovery of mid-level parts
- Food image recognition using deep convolutional network with pre-training and fine-tuning
- Food Recognition and Detection with Minimum Supervision
- Recipe recognition with large multimodal food dataset
Related papers
No related papers recorded.