AI Paper Atlas

Research map / Video / Action recognition

Encouraging LSTMs to Anticipate Actions Very Early

Mohammad Sadegh Aliakbarian, Fatemeh Sadat Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson, Lars Andersson

ICCV 2017 · Video › Action recognition · approach: Action anticipation and latent actions · 177 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 action-aware features to context-aware features via multi-stage LSTM (ablation)MS-LSTM with anticipation loss · UCF-101 anticipationaccuracy, earliest: 62.80 -> 80.5Improved
add context-aware features to action-aware features via multi-stage LSTM (ablation)MS-LSTM with anticipation loss · UCF-101 anticipationaccuracy, earliest: 69.33 -> 80.5Improved
add context-aware features to action-aware features via multi-stage LSTM (ablation)MS-LSTM with anticipation loss · UCF-101 anticipationaccuracy, latest: 77.86 -> 83.37Improved
process features sequentially (multi-stage) instead of concatenating (ablation)Ours MS-LSTM · UCF-101 recognition (split 1)accuracy: 77.16 -> 83.37Improved
process features sequentially instead of two parallel LSTMs (ablation)Ours MS-LSTM · UCF-101 recognition (split 1)accuracy: 78.63 -> 83.37Improved
process context-aware features first, then action-aware (not swapped) (ablation)Ours MS-LSTM · UCF-101 recognition (split 1)accuracy: 78.80 -> 83.37Improved
add the LSTM stages on top of the CNN (ablation)Ours · UCF-101 anticipationaccuracy, earliest: 69.53 -> 80.5Improved
add the LSTM stages on top of the CNN (ablation)Ours · UCF-101 anticipationaccuracy, latest: 73.80 -> 83.4Improved
add average pooling of predictions over time (ablation)Ours · UCF-101 recognition (split 1)accuracy: 82.16 -> 83.37Improved
increase hidden units from 1024 to 2048 (ablation)Ours · UCF-101 recognition (split 1)accuracy: 81.94 -> 82.16Improved
replace cross-entropy loss with the proposed anticipation loss (ablation)MS-LSTM · UCF-101 recognition (split 1)accuracy: 78.93 -> 83.37Improved
replace linearly growing loss with the proposed anticipation loss (ablation)MS-LSTM · UCF-101 recognition (split 1)accuracy: 81.27 -> 83.37Improved

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