AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

When VLAD Met Hilbert

Mehrtash Harandi, Mathieu Salzmann, Fatih Porikli

CVPR 2016 · Learning theory and algorithms › Kernels and regression theory · approach: RKHS kernel methods · 0 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use kernel VLAD rather than log-Euclidean VLAD for SPD descriptorsVLAD on SPD data · QMUL, HOCoffee, HOCaccuracy: 87.6% -> 92.7%; 77.2 % -> 84.0 %; 79.7% -> 84.1 %Mixed
Use local-subspace approximation sVLAD instead of global Nyström approximation nVLADKernel VLAD approximations · QMUL, HOCoffee, HOC; Ballet, CIFAR, CMU-PIE; VOC 2007; FMDaccuracy / mAP / CCR: 88.9% -> 92.7%; 83.4% -> 84.0 %; 81.4% -> 84.1 %; 88.9% -> 94.4%; 62.2 % -> 65.2 %; 79.5 % -> 80.1%; 56.2% -> 60.3%; 52.Improved
Use kernel VLAD rather than holistic Grassmann sparse codingGrassmannian image-set recognition · Ballet, CIFAR, CMU-PIEaccuracy: 79.7 % -> 94.4%; 59.9 % -> 67.9 %; 75.5% -> 86.3 %Improved
Use sVLAD rather than conventional VLAD with Euclidean descriptorsVLAD with SIFT descriptors · VOC 2007mAP: 54.7% -> 60.3%Improved
Use sVLAD rather than conventional VLAD with Euclidean descriptorsVLAD with SIFT descriptors · FMDCCR: 49.4% -> 55.2%Improved
Increase the lE-VLAD dictionary to 256 atomslE-VLAD · Balletaccuracy: 91.1 % -> 91.7%Improved
Use enlarged lE-VLAD rather than sVLADGrassmannian VLAD · Balletaccuracy: 91.7% vs 94.4%Hurt
Add signed square-root normalization to sVLAD (ablation)sVLAD · QMULaccuracy: roughly 1%Improved
Use sVLAD rather than kVLAD, enabling square-root normalizationKernel VLAD on SPD data · QMULaccuracy: 92.2% -> 92.7%Improved
Use sVLAD rather than kVLADKernel VLAD on SPD data · HOCoffeeaccuracy: 84.0 % vs 85.3 %Hurt
Use kVLAD rather than sVLADKernel VLAD on Grassmannian data · CMU-PIEaccuracy: 80.1% -> 86.3 %Improved
Use sVLAD rather than kVLADKernel VLAD on Grassmannian data · Balletaccuracy: 92.2 % -> 94.4%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy