Keyphrases
Affine-invariant
57%
Bag-of-features
30%
Binary Code Learning
40%
Binary Codes
48%
Binary Hypercube
38%
Bounding Box
60%
Canonical Correlation Analysis
55%
Class Label
28%
Classification Task
51%
Clothing
42%
Feature Vector
40%
Fill-in
30%
Generative Models
28%
Iconic Images
26%
Image Collection
40%
Image Description
46%
Image Parsing
53%
Image Region
63%
Image-text Retrieval
30%
Indoor Scene
33%
Iterative Quantization
28%
Local Features
36%
Mean Squared Error
24%
Multi-task
24%
Multiple Choice Questions
30%
Multiple Moving Objects
24%
Nonparametric
30%
Novel Representation
28%
Object Categories
65%
Object Instance
36%
Object Mask
24%
Object Recognition
28%
Order of Magnitude
34%
Photo Collections
30%
Question Answering
36%
Scene Parsing
24%
Sentence Model
24%
Smooth Surface
39%
Sparse Sets
28%
Sparse Texture
24%
Spatial Pyramid Matching
24%
Text Embedding
36%
Text-to-image
48%
Texture Recognition
48%
Texture Representation
24%
Training Data
24%
Training Set
26%
Unsupervised Learning
27%
Video Clips
24%
Visual Question Answering
39%
Computer Science
3d Reconstruction
24%
Affine Invariant
73%
Annotation
36%
Art Performance
24%
Artificial Intelligence
40%
Classification Accuracy
28%
Classification Task
46%
Comparative Evaluation
30%
Contextual Information
24%
Convolutional Neural Network
42%
Correlation Analysis
63%
Embedding Space
30%
Feature Vector
40%
Gaussian Kernel
24%
Generative Model
36%
Graphic Hardware
24%
Hamming Distance
24%
Hashing
24%
High Dimensional Data
24%
Image Collections
55%
image feature
27%
Image Representation
24%
Image Retrieval
24%
Image Sequence
24%
Image Synthesis
24%
Image Understanding
24%
Information Retrieval
100%
local feature
40%
multi agent
27%
Multiple Task
24%
Object (Databases)
24%
Object Category
57%
Object Detection
24%
Object Instance
30%
Object Recognition
30%
Parallelization
24%
Parsing
85%
Quantisation Error
28%
Single Network
24%
Spatial Relationship
24%
structure-from-motion
24%
Superpixel
24%
Textured Surface
24%
Training Data
34%
Training Image
27%
Unlabeled Data
24%
Video Matching
24%
Video Sequences
40%
Virtual Try-On
36%
Visual Question Answering
34%
