Papers › Adaptive Semantic-Spatio-Temporal Graph Convolutional Network for Lip Reading

Adaptive Semantic-Spatio-Temporal Graph Convolutional Network for Lip Reading

16 Aug 2021IEEE Transactions on Multimedia 2021 8archive 2025-07-28

Changchong Sheng, Xinzhong Zhu, Huiying Xu, Matti Pietikäinen, Li Liu

The goal of this work is to recognize words, phrases, and sentences being spoken by a talking face without given the audio. Current deep learning approaches for lip reading focus on exploring the appearance and optical flow information of videos. However, these methods do not fully exploit the characteristics of lip motion. In addition to appearance and optical flow, the mouth contour deformation usually conveys significant information that is complementary to others. However, the modeling of dynamic mouth contour has received little attention than that of appearance and optical flow. In this work, we propose a novel model of dynamic mouth contours called Adaptive Semantic-Spatio-Temporal Graph Convolution Network (ASST-GCN), to go beyond previous methods by automatically learning both the spatial and temporal information from videos. To combine the complementary information from appearance and mouth contour, a two-stream visual front-end network is proposed. Experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art lip reading methods on several large-scale lip reading benchmarks.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Landmark-based LipreadingLip ReadingOptical Flow Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Landmark-based Lipreading LRW Adaptive GCN Top 1 Accuracy 60.7 #4 of 5 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