AI Paper Atlas

Research map / Video / Action recognition

Efficient Spatio-Temporal Tactile Object Recognition with Randomized Tiling Convolutional Networks in a Hierarchical Fusion Strategy

Lele Cao, Ramamohanarao Kotagiri, Fuchun Sun, Hongbo Li, Wenbing Huang, Zay Maung Maung Aye

AAAI 2016 · Video › Action recognition · approach: Skeleton-based action recognition · 28 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
weight-tuning (pretrain and finetune) of convolutional weights (ablation)3T-RTCN · frame-wise accuracy on tactile datasetsaccuracy: +1.01%Improved
weight-tuning of convolutional weights (ablation)3T-RTCN · training timetraining time: roughly 25 timesHurt
replace macro-fusion 3T-RTCN with micro-fusion 3D ConvNet (ablation)3T-RTCN · tactile datasetsaccuracy: average gap of 5.2%Hurt
increase tactile flow/difference stacking size n from 2 to 5 (ablation)3T-RTCN · tactile datasetsaccuracyNo clear effect
use multiple RTCN layers instead of one (ablation)3T-RTCN · tactile datasetsrecognition ratioNo clear effect
use 3T-RTCN instead of JKSCtactile recognition · HCs10avg recognition accuracy %: 93.5 -> 91.2Hurt
use 3T-RTCN instead of best baselinetactile recognition · SD10avg recognition accuracy %: 97.5 -> 100.0Improved

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