AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learning Long-Term Dependencies for Action Recognition With a Biologically-Inspired Deep Network

Yemin Shi, Yonghong Tian, Yaowei Wang, Wei Zeng, Tiejun Huang

ICCV 2017 · Architectures and efficiency › RNNs and normalization · approach: Efficient recurrent architectures · 72 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
replace 2-layer GRU with shuttleNet (2 processors, 2 steps)CNN-RNN two-stream on GoogLeNet · UCF101 split 1 (GoogLeNet base)two-stream accuracy: 90.27% -> 91.94%Improved
replace 2-layer LSTM with shuttleNetCNN-RNN two-stream on GoogLeNet · UCF101 split 1 (GoogLeNet base)two-stream accuracy: 88.58% -> 91.94%Improved
add RNN (GRU, 2 layers) to GoogLeNetGoogLeNet · UCF101 split 1 (GoogLeNet base)two-stream accuracy: 85.91% -> 90.27%Improved
add output selector (attention over 2 processors) in 1 stepshuttleNet 2 processors 1 step · UCF101 split 1 two streamstwo-stream accuracy: 91.7% vs 90.27% (2-layer GRU)Improved
share processor across 2 steps (loop connection) with 1 processor (ablation)shuttleNet · UCF101 split 1 two streamstwo-stream accuracy: 90.27% -> 91.65%Improved
use 2 steps instead of 1 step (ablation)shuttleNet 2 processors · UCF101 split 1 spatial stream, shuttleNet setting studyspatial accuracy: 82.37% -> 83.03%Improved
use 3 steps instead of 2 steps (ablation)shuttleNet 2 processors · UCF101 split 1 spatial stream, shuttleNet setting studyspatial accuracy: 83.03% -> 80.89%Hurt
increase processors from 1 to 3 at 2 steps (ablation)shuttleNet · UCF101 split 1 spatial stream, shuttleNet setting studyspatial accuracy: 82.9% -> 83.19%Improved
increase processors and steps to 3 and 3 (ablation)shuttleNet · UCF101 split 1 spatial stream, shuttleNet setting studyspatial accuracy: 83.03% -> 82.13%Hurt
switch base CNN from GoogLeNet to Inception-ResNet-v2shuttleNet · UCF101 (mean of 3 splits)two-stream accuracy: 92.3% -> 94.4%Improved
late-fuse hand-crafted MIFS featuresshuttleNet two streams · HMDB51 (mean of 3 splits)accuracy: 66.6% -> 71.7%Improved
late-fuse MIFS featuresshuttleNet two streams · UCF101 (mean of 3 splits)accuracy: 94.4% -> 95.4%Improved

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