AI Paper Atlas

Research map / Video / Action recognition

What Can Simple Arithmetic Operations Do for Temporal Modeling?

Wenhao Wu, Yuxin Song, Zhun Sun, Jingdong Wang, Chang Xu, Wanli Ouyang

ICCV 2023 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 20 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 any single arithmetic operation (add/sub/mul/div) as temporal cue (ablation)ResNet-18 temporal-irrespective baseline · Something-Something V1top-1 accuracy: 16.5% -> 46.5% (multiplication)Improved
combine subtraction and multiplication (ablation)ATM on ResNet-18 · Something-Something V1top-1 accuracy: 46.5% -> 48.2%Improved
add addition on top of subtraction and multiplication (ablation)ATM on ResNet-18 · Something-Something V1top-1 accuracy: 48.2% -> 48.1%No clear effect
enlarge temporal context range Z from 1 to 4 (ablation)ATM on ResNet-18 · Something-Something V1top-1 accuracy: 43.7% -> 48.2%Improved
increase Z from 4 to 6 (ablation)ATM on ResNet-18 · Something-Something V1top-1 accuracy: 48.2% -> 48.0%No clear effect
add temporal convolution to ATM (ablation)ATM on ResNet-18 · Something-Something V1top-1 accuracy: 48.2% -> 48.7%Improved
add temporal convolution to ATM (ablation)ATM on ViT-B/16 · Something-Something V1top-1 accuracy: 56.1% -> 58.1%Improved
use conv stack feature extractor instead of FC or MLP (ablation)ATM on ResNet-18 · Something-Something V1top-1 accuracy: 47.8% -> 48.7%Improved
insert ATM at res5 instead of res3 (ablation)ATM on ResNet-18 · Something-Something V1top-1 accuracy: 48.7% -> 43.1%Hurt
insert ATM at res2 instead of res3 (ablation)ATM on ResNet-18 · Something-Something V1top-1 accuracy: 48.7% -> 48.8%No clear effect
insert ATM in middle ViT layer (7) instead of early layer (2) (ablation)ATM on ViT-B/16 · Something-Something V1top-1 accuracy: 36.9% -> 58.1%Improved
increase frames from 8 to 16 with ResNet-50 (ablation)ATM · Something-Something V1top-1 accuracy: 53.9% -> 56.3%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