AI Paper Atlas

Research map / Video / Video segmentation and tracking

Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading

Xingxuan Zhang, Feng Cheng, Shilin Wang

ICCV 2019 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 101 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 short-range temporal fusion (TF-block-a) instead of position-wise feed-forward layers (ablation)Conv-seq2seq · LRWWER (%): 22.0 -> 19.3Improved
add multi-scale branches (kernel 1 and shortcut) to TF-block-a, giving TF-block-b (ablation)Conv-seq2seq · LRWWER (%): 19.3 -> 18.7Improved
add multi-scale branches (TF-block-b vs TF-block-a) (ablation)Conv-seq2seq · LRS2-BBCWER (%): 58.5 -> 55.6Improved
use causal convolution in the encoder (TF-block-c instead of b) (ablation)Conv-seq2seq · LRWWER (%): 18.7 -> 20.1Hurt
add bidirectional mechanism to causal encoder (TF-block-d vs c) (ablation)Conv-seq2seq · LRWWER (%): 20.1 -> 18.8Improved
use Conv-seq2seq with TF-block-b instead of Transformer-seq2seqsequence model · LRS3-TEDWER (%): 70.8 -> 65.5Improved
replace global average pooling by simplified STFM (ablation)Conv-seq2seq · LRWWER (%): 18.7 -> 16.8Improved
add temporal convolutions to STFM-simple (full STFM) (ablation)Conv-seq2seq · LRS3-TEDWER (%): 62.5 -> 60.1Improved
replace global average pooling by STFM (ablation)Conv-seq2seq · LRS2-BBCWER (%): 55.6 -> 51.7Improved
replace global average pooling by STFM (ablation)TM-CTC · LRWWER (%): 35.2 -> 33.7Improved
replace global average pooling by STFM (ablation)TM-seq2seq · LRS3-TEDWER (%): 69.8 -> 65.0Improved
restrict self-attention to local width 50 at test time (ablation)Conv-seq2seq · LRWWER (%): 0.8% dropNo clear effect

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