AI Paper Atlas

Research map / Detection and segmentation / CNN features

Bounding-box Channels for Visual Relationship Detection

Sho Inayoshi, Keita Otani, Antonio Tejero-de-Pablos, Tatsuya Harada

ECCV 2020 · Detection and segmentation › CNN features · approach: RGB-D salient object detection · 10 citations (OpenAlex)

Read the paperCheck 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
add bounding-box channels (vs CAI-like baseline without them)CAI-style VRD network · VRD phrase detection, k=70 (R-CNN proposals)R@100: 19.24 -> 28.38Improved
add bounding-box channels (vs CAI-like baseline without them)CAI-style VRD network · VRD relationship detection, k=70 (R-CNN proposals)R@100: 17.39 -> 22.86Improved
use Faster R-CNN proposals instead of R-CNN proposals [13]BBCNet · VRD phrase detection, k=10R@50: 24.46 -> 36.71Improved
use Faster R-CNN proposals instead of R-CNN proposals [13]BBCNet · VRD relationship detection, k=10R@50: 19.90 -> 30.61Improved
keep 10 predicates per object pair instead of 1BBCNet · VRD phrase detection (R-CNN proposals)R@50: 19.72 -> 24.46Improved
use word2vec semantic features instead of posterior-probability features (zero-shot)BBCNet vs VRD-Full · VRD zero-shot phrase detection, k=10R@50: 7.56 -> 12.57Improved
use bounding-box channels with ground-truth boxes (predicate detection) on zero-shot tripletsBBCNet vs LK distillation · VRD predicate detection zero-shot, k=1R@100/50: 19.17 -> 27.54Improved
BBCNet versus LSVR on relationship detection at k=1 (R-CNN proposals)BBCNet · VRD relationship detection, k=1R@50: 16.08 -> 15.87Hurt
BBCNet versus RelDN at the lowest recall cutoffBBCNet · Visual Genome SGDET (graph constraint)R@20: 21.1 -> 20.4Hurt
BBCNet versus RelDN on scene graph detectionBBCNet · Visual Genome SGDET (graph constraint)R@100: 32.7 -> 34.3Improved

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