AI Paper Atlas

Research map / Video / Action recognition

Fine-grained Video Categorization with Redundancy Reduction Attention

Chen Zhu, Xiao Tan, Feng Zhou, Xiao Liu, Kaiyu Yue, Errui Ding, Yi Ma

ECCV 2018 · Video › Action recognition · approach: Temporal action segmentation · 51 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 L_e (ensemble loss) to L_i (ablation)RRA · ActivityNet v1.3 valmAP (ensemble): 82.97 -> 83.42Improved
add L_c (concatenation loss) to L_e+L_i (ablation)RRA · ActivityNet v1.3 valmAP (ensemble): 83.42 -> 82.59Hurt
add L_c to L_i (ablation)RRA · ActivityNet v1.3 valmAP (ensemble): 82.97 -> 82.80Hurt
train with L_e alone (no per-glimpse supervision) (ablation)RRA · ActivityNet v1.3 valmAP (ensemble): 83.42 -> 36.24Hurt
increase glimpses from 1 to 4 (ablation)RRA · ActivityNet v1.3 valmAP: 80.89 -> 83.42Improved
increase glimpses from 4 to 5 (ablation)RRA · ActivityNet v1.3 valmAP: 83.42 -> 82.94Hurt
add spatio-temporal attention instead of average pooling (ablation)RRA · ActivityNet v1.3 valmAP: 80.20 -> 83.42Improved
use spatio-temporal attention instead of spatial attention with temporal average pooling (ablation)RRA · ActivityNet v1.3 valmAP: 81.97 -> 83.42Improved
add batch normalization in the reduction module (ablation)RRA · ActivityNet v1.3 valmAP: 82.41 -> 83.42Improved
add ReLU in the reduction module (ablation)RRA · ActivityNet v1.3 valmAP: 83.15 -> 83.42Improved
use tanh activation rather than none or -ReLU(x) (ablation)RRA · ActivityNet v1.3 valmAP: 82.75 -> 83.42Improved
use sequential redundancy-reduction glimpses instead of 4 parallel glimpses (ablation)RRA · ActivityNet v1.3 valmAP: 82.39 -> 83.42Improved

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