AI Paper Atlas

Research map / Video / Action recognition

Lattice Long Short-Term Memory for Human Action Recognition

Lin Sun, Kui Jia, Kevin Chen, Dit-Yan Yeung, Bertram E. Shi, Silvio Savarese

ICCV 2017 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 209 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 long-short term sampling (ablation)ConvLSTM spatial network · UCF-101 split 1accuracy (%): 77.6 -> 80.4Improved
add long-short term sampling (ablation)ConvLSTM temporal network · UCF-101 split 1accuracy (%): 79.1 -> 82.3Improved
add local superposition on memory cell (ablation)ConvLSTM with sampling, spatial network · UCF-101 split 1accuracy (%): 80.4 -> 82.2Improved
add local superposition on memory cell (ablation)ConvLSTM with sampling, temporal network · UCF-101 split 1accuracy (%): 82.3 -> 86.9Improved
add shared controlling gates across RGB and flow (ablation)L2STM spatial network · UCF-101 split 1accuracy (%): 82.2 -> 83.2Improved
add shared controlling gates across RGB and flow (ablation)L2STM temporal network · UCF-101 split 1accuracy (%): 86.9 -> 87.4Improved
replace ConvLSTM with L2STMtwo-stream model · UCF-101 split 1 Human-Object Interactionaccuracy (%): 76.0 -> 86.7Improved
replace ConvLSTM with L2STMtwo-stream model · UCF-101 split 1 Human-Human Interactionaccuracy (%): 89.1 -> 95.4Improved
replace ConvLSTM with L2STMtwo-stream model · UCF-101 split 1 Body Motion Onlyaccuracy (%): 88.1 -> 88.6No clear effect
replace ConvLSTM with L2STMtwo-stream model · UCF-101 split 1 Pizza Tossingaccuracy (%): 21.2 -> 72.7Improved
use long-short term sampling instead of fixed stride random clips (ablation)all LSTM models · UCF-101accuracy (%): about 2% gainImproved
replace VideoLSTM with L2STMLSTM-like action recognizers · UCF-101 meanaccuracy (%): 89.2 -> 93.6Improved

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