paper-with-me

Papers

MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading

2024-04-18 · WenHao Zhang, Jun Wang, Yong Luo, Lei Yu, Wei Yu, Zheng He, Jialie Shen

Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts.

📄 PDF Abstract BibTeX arXiv:2404.11979

Code (1)

whu125/mtga 공식 구현 pytorch

Tasks

Lip Reading

Similar Papers 제목 키워드 기반

Multi-Task Genetic Algorithm with Multi-Granularity Encoding for Protein-Nucleotide Binding Site Prediction

2026-03-16 · Yiming Gao, Liuyi Xu, Pengshan Cui, Yining Qian 외 arxiv

Accurate identification of protein-nucleotide binding sites is fundamental to deciphering molecular mechanisms and accelerating drug discovery. However, current computational methods often struggle with suboptimal perfor…

Drug Discovery

Multi-Label Clinical Time-Series Generation via Conditional GAN

2022-04-10 · Chang Lu, Chandan K. Reddy, Ping Wang, Dong Nie 외

In recent years, deep learning has been successfully adopted in a wide range of applications related to electronic health records (EHRs) such as representation learning and clinical event prediction. However, due to priv…

Representation LearningTime SeriesTime Series AnalysisTime Series Generation

Multi-Tasking Genetic Algorithm (MTGA) for Fuzzy System Optimization

2018-12-15 · Dongrui Wu, Xianfeng Tan

Multi-task learning uses auxiliary data or knowledge from relevant tasks to facilitate the learning in a new task. Multi-task optimization applies multi-task learning to optimization to study how to effectively and effic…

Multi-Task Learning

Learning to Learn Transferable Generative Attack for Person Re-Identification

2024-09-06 · Yuan Bian, Min Liu, Xueping Wang, Yunfeng Ma 외

Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider c…

Meta-LearningPerson Re-Identification

SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network

2018-09-01 · ECCV 2018 9 · Yancheng Bai, Yongqiang Zhang, Mingli Ding, Bernard Ghanem

Object detection is a fundamental and important problem in computer vision. Although impressive results have been achieved on large/medium sized objects on large-scale detection benchmarks (e.g. the COCO dataset), the pe…

Generative Adversarial NetworkObjectobject-detectionObject Detection+3