Papers › SpotFast Networks with Memory Augmented Lateral Transformers for Lipreading

SpotFast Networks with Memory Augmented Lateral Transformers for Lipreading

21 May 2020arXiv:2005.10903archive 2025-07-28

Peratham Wiriyathammabhum

This paper presents a novel deep learning architecture for word-level lipreading. Previous works suggest a potential for incorporating a pretrained deep 3D Convolutional Neural Networks as a front-end feature extractor. We introduce a SpotFast networks, a variant of the state-of-the-art SlowFast networks for action recognition, which utilizes a temporal window as a spot pathway and all frames as a fast pathway. We further incorporate memory augmented lateral transformers to learn sequential features for classification. We evaluate the proposed model on the LRW dataset. The experiments show that our proposed model outperforms various state-of-the-art models and incorporating the memory augmented lateral transformers makes a 3.7% improvement to the SpotFast networks.

PaperPDFCode

Code

perathambkk/lipreading officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionLipreading

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lipreading Lip Reading in the Wild SpotFast + Transformer + Product-Key memory Top-1 Accuracy 84.4 #17 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections