NEIL: Extracting Visual Knowledge from Web Data
Citations
3,842 citations
3,513 citations
Cites background from "NEIL: Extracting Visual Knowledge f..."
...However, it includes as building blocks several components that the CV, NLP, and KR [4, 6, 25, 29, 3] communities have made significant progress on during the past few decades....
[...]
2,393 citations
2,365 citations
Cites background from "NEIL: Extracting Visual Knowledge f..."
...However, it includes as building blocks several components that the CV, NLP, and KR [4, 6, 25, 29, 3] communities have made significant progress on during the past few decades....
[...]
1,954 citations
References
49,639 citations
"NEIL: Extracting Visual Knowledge f..." refers background in this paper
...One way to build initial classifiers is via a few manually labeled seed images....
[...]
...It is an attempt to develop the world’s largest visual structured knowledge base with minimum human labeling effort....
[...]
46,906 citations
31,952 citations
"NEIL: Extracting Visual Knowledge f..." refers methods in this paper
...We also compare the performance of detectors trained after aspect-ratio, HOG clustering and our proposed clustering procedure....
[...]
...However, clustering using K-means has two issues: (1) High Dimensionality: We use the Color HOG (CHOG) [20] representation and standard distance metrics do not work well in such high-dimensions [10]; (2) Scalability: Most clustering approaches tend to partition the complete feature space....
[...]
...For the object and attribute section, we use CHOG [20] features with a bin size of 8....
[...]
...However, instead of using the high-dimensional CHOG representation for clustering, we use the detection signature of each window (represented as a vector of seed detector ELDA scores on the window) to create aK × K affinity matrix....
[...]
...The feature vector includes 512D GIST [27] features, concatenated with bag of words representations for SIFT [24], HOG [7], Lab color space, and Texton [26]....
[...]
10,501 citations
"NEIL: Extracting Visual Knowledge f..." refers methods in this paper
...We train the detectors using latent SVM model (without parts) [13]....
[...]
6,882 citations
"NEIL: Extracting Visual Knowledge f..." refers methods in this paper
...The feature vector includes 512D GIST [27] features, concatenated with bag of words representations for SIFT [24], HOG [7], Lab color space, and Texton [26]....
[...]