AI Paper Atlas

Research map / Video / Action recognition

AssembleNet++: Assembling Modality Representations via Attention Connections - Supplementary Material -

Michael S. Ryoo, AJ Piergiovanni, Juhana Kangaspunta, Anelia Angelova

ECCV 2020 · Video › Action recognition · approach: Disentangled action recognition

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 omnipresent object-modality connections (ablation)AssembleNet++ block connectivity · Charades v1mAP: 47.18 -> 50.43Improved
replace weighted connections with peer-attention (no object) (ablation)AssembleNet++ · Charades v1mAP: 47.18 -> 52.39Improved
replace weighted connections with peer-attention (with object) (ablation)AssembleNet++ · Charades v1mAP: 50.43 -> 56.38Improved
use peer-attention instead of self-attention (ablation)AssembleNet++ with object · Charades v1mAP: 55.40 -> 56.38Improved
use static attention instead of none (ablation)AssembleNet++ with object · Charades v1mAP: 50.43 -> 51.15Improved
add peer-attention instead of 1x1 conv with same parameters (ablation)AssembleNet++ · Charades v1mAP: 50.24 -> 56.38Improved
use searched peer-attention instead of random connectivity (ablation)AssembleNet++ · Charades v1mAP: 53.40 -> 56.38Improved
use searched peer-attention instead of random connectivity (ablation)AssembleNet++ · Toyota Smarthomemean per-class accuracy: 60.23 -> 63.64Improved
add 1x1 conv instead of attention (ablation)AssembleNet++ base · Toyota Smarthomemean per-class accuracy: 59.16 -> 59.44No clear effect
add object modality and peer-attention (ablation)AssembleNet-50 baseline · Toyota Smarthomemean per-class accuracy: 57.42 -> 63.64Improved
add self-attention only (no object) (ablation)AssembleNet-50 baseline · Toyota Smarthomeclassification accuracy: 77.59 -> 77.77No clear effect
add object modality and attention to RGB R(2+1)D (ablation)RGB R(2+1)D · Charades v1mAP: 36.51 -> 45.30Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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