AI Paper Atlas

Research map / Video / Action recognition

TALLFormer: Temporal Action Localization with a Long-Memory Transformer

Feng Cheng, Gedas Bertasius

ECCV 2022 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 143 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 temporal consistency module (ablation)TALLFormer · THUMOS14 (Swin-T 112)average mAP: 51.1 -> 52.6Improved
increase temporal support from 8s to 40s (ablation)TALLFormer · THUMOS14 (Swin-T 112)average mAP: 41.5 -> 53.3Improved
reduce clip sampling rate from 0.6 to 0.15 (ablation)TALLFormer · THUMOS14 (Swin-B 224)average mAP: 60.0 -> 59.0No clear effect
use long memory with sampling instead of full end-to-end (r=1.0) (ablation)TALLFormer · THUMOS14 (Swin-B 224)GPU memory: 45 GB at r=0.6 -> 12 GB at r=0.15Improved
unfreeze backbone (end-to-end) instead of frozen featuresTALLFormer vs LT-Frozen · THUMOS14 (12GB cap)average mAP: 52.7 -> 59.0Improved
use long temporal support with memory instead of short temporal support ST-E2ETALLFormer vs ST-E2E · THUMOS14 (32GB cap)average mAP: 55.1 -> 59.2Improved
use dense 15 fps instead of sparse 8 fps for 32s ST-E2EST-E2E · THUMOS14 (12GB cap)average mAP: 42.9 -> 31.9Hurt
use larger Swin backbone (Swin-B instead of Swin-T) (ablation)TALLFormer · THUMOS14average mAP: 57.0 -> 59.2Improved
raise spatial resolution from 112x112 to 168x168DaoTAD Swin-T · THUMOS14mAP: 52.8 -> 55.1Improved
freeze 4 backbone stages instead of 2DaoTAD Swin-T · THUMOS14mAP: 52.8 -> 44.3Hurt
use Swin-B backbone instead of I3DTALLFormer-12 · ActivityNet-1.3average mAP: 27.2 -> 33.7Improved
use single RGB model instead of two-stream with external classifierTALLFormer-32 vs AFSD · ActivityNet-1.3average mAP: 34.4 -> 35.6Improved

Later papers that compared with this method

3 later accepted papers report TALLFormer as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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