AI Paper Atlas

Research map / Video / Action recognition

Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition

Xiangbo Shu, Jinhui Tang, Guo-Jun Qi, Wei Liu, Jian Jun Yang

TPAMI 2019 · Video › Action recognition · approach: Disentangled action recognition · 220 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 modeling with LSTM instead of per-frame CNN features only (ablation)B2 vs B1 · BITaccuracy (%): 71.88 -> 83.50Improved
model inter-related motion with Co-LSTSM instead of independent single-person LSTMs (B4) (ablation)Co-LSTSM · BITaccuracy (%): 88.50 -> 92.88Improved
add Single-Person LSTMs with hierarchical Co-LSTM instead of Co-LSTSM (ablation)H-LSTCM · BITaccuracy (%): 92.88 -> 94.03Improved
add Single-Person LSTMs with hierarchical Co-LSTM instead of Co-LSTSM (ablation)H-LSTCM · UTaccuracy (%): 95 -> 98.33Improved
add hierarchical single-person dynamics and Co-LSTM instead of Co-LSTSM+ (ablation)H-LSTCM · CADaccuracy (%): 79.14 -> 83.75Improved
extended Co-LSTSM+ instead of multiple single-person LSTMs plus whole LSTM (B4) (ablation)Co-LSTSM+ · CADaccuracy (%): 78.46 -> 79.14No clear effect
add hierarchical Co-LSTM instead of B4 (ablation)H-LSTCM · Volleyballaccuracy (%): 82.5 -> 88.4Improved
multiple LSTMs per person (B3) instead of merging persons into one box (B2) (ablation)B3 vs B2 · CADaccuracy (%): 63.71 -> 66.02Improved
hierarchical LSTM with single-person dynamics instead of best LSTM-based prior (Ke et al.)H-LSTCM · BITaccuracy (%): 85.20 -> 94.03Improved
H-LSTCM versus prior best on Volleyball (Shu et al.)H-LSTCM · Volleyballaccuracy (%): 83.6 -> 88.4Improved
H-LSTCM versus Ibrahim et al. LSTM on CADH-LSTCM · CADaccuracy (%): 81.50 -> 83.75Improved

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