AI Paper Atlas

Research map / Video / Action recognition

LSTA: Long Short-Term Attention for Egocentric Action Recognition

Swathikiran Sudhakaran, Sergio Escalera, Oswald Lanz

CVPR 2019 · Video › Action recognition · approach: Disentangled action recognition · 166 citations (OpenAlex)

Check 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 output pooling to the ConvLSTM baseline (ablation)ConvLSTM · GTEA 61 fixed splitaccuracy (%): 51.72 -> 62.07Improved
Add attention pooling to the ConvLSTM baseline (ablation)ConvLSTM · GTEA 61 fixed splitaccuracy (%): 51.72 -> 66.38Improved
Add both attention pooling and output pooling (ablation)ConvLSTM · GTEA 61 fixed splitaccuracy (%): 51.72 -> 68.1Improved
Add bias control to attention and output pooling (ablation)LSTA · GTEA 61 fixed splitaccuracy (%): 68.1 -> 74.14Improved
Use cross-modal fusion instead of late fusion (ablation)LSTA two-stream network · GTEA 61 fixed splitaccuracy (%): 78.45 -> 79.31Improved
Use LSTA rather than ego-rnnGTEA 61 fixed split · GTEA 61 fixed splitaccuracy (%): 63.79 -> 74.14Improved
Use attention on the motion stream (ablation)Action-pretrained ResNet-34 flow network · GTEA 61 fixed splitaccuracy (%): 36.21 -> 40.52Improved
Use the LSTA two-stream model rather than the strongest reported TSN baselineEPIC-KITCHENS · EPIC-KITCHENS S1Top-1 action accuracy (%): 20.54 -> 30.33Improved
Use the LSTA two-stream model rather than the strongest reported TSN baselineEPIC-KITCHENS · EPIC-KITCHENS S2Top-1 action accuracy (%): 10.89 -> 16.63Improved
Use recurrent attention tracking rather than frame-independent attentionLSTA compared with ego-rnn · GTEA 61 fixed splitaccuracy (%): 63.79 -> 74.14Improved

Later papers that compared with this method

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

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