AI Paper Atlas

Research map / Video / Action recognition

Long Short-Term Transformer for Online Action Detection

Mingze Xu, Yuanjun Xiong, Hao Chen, Xinyu Li, Wei Xia, Zhuowen Tu, Stefano Soatto

NeurIPS 2021 · Video › Action recognition · approach: Fully supervised temporal action detection · 11 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
use two-stage rather than one-stage memory compression (ablation)LSTR · THUMOS'14, m_L=512smAP: 68.7 -> 69.5Improved
use two-stage compression for speed (ablation)LSTR · THUMOS'14 runtimeFPS: 59.5 -> 91.6Improved
add LSTR encoder (learned long-term compression) before decoder (ablation)LSTR · THUMOS'14, m_L=512smAP: 67.0 -> 69.5Improved
add LSTR decoder using short-term memory as queries (ablation)LSTR · THUMOS'14, m_L=512smAP: 65.4 -> 69.5Improved
use learned adaptive compression instead of strided downsampling to 16 features (ablation)LSTR · THUMOS'14mAP: 65.9 -> 69.5Improved
cross-attention instead of average pooling or concatenation for memory integration (ablation)LSTR · THUMOS'14, m_L=512smAP: 68.7 -> 69.5Improved
transformer decoder units rather than self-attention encoder for the LSTR encoder (ablation)LSTR · THUMOS'14, m_L=512smAP: 67.0 -> 69.5Improved
learned attention compression instead of a projection layer (ablation)LSTR · THUMOS'14, m_L=512smAP: 66.9 -> 69.5Improved
separate long/short memory with encoder-decoder instead of single Transformer encoder on concatenated memory (ablation)LSTR · THUMOS'14, m_L=512smAP: 66.5 -> 69.5Improved
downsample long-term memory with stride up to 4 (ablation)LSTR · THUMOS'14mAP: 69.5 -> 69.5No clear effect
add GRU to cover history beyond memories (ablation)LSTR · THUMOS'14mAPMixed
increase long-term memory length (ablation)LSTR · THUMOS'14mAP: 66.6 -> 69.5Improved

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