您当前的位置:

Lip Reading: CAS-VSR-W1k (The original LRW-1000)

发布时间:2018-10-17

1. Overview

LRW-1000 is a naturally-distributed large-scale benchmark for word-level lipreading in the wild, including 1000 classes with about 718,018 video samples from more than 2000 individual speakers. There are more than 1,000,000 Chinese character instances in total. Each class corresponds to the syllables of a Mandarin word which is composed by one or several Chinese characters. This dataset aims to cover a natural variability over different speech modes and imaging conditions to incorporate challenges encountered in practical applications. It has a large variation over several aspects, including the number of samples in each class, resolution of videos, lighting conditions, and speakers' attributes such as pose, age, gender, and make-up and so on, as shown in Fig. 1 and Fig. 2. 

* Note that LRW-1000 has been rename as CAS-VSR-W1k. You may refer to it as “CAS-VSR-W1k (The original LRW-1000)”.

Fig.1 The diversity of the speakers' appearance in CAS-VSR-W1k (the original LRW-1000)

Fig.2 Lip Samples in CAS-VSR-W1k (the original LRW-1000)

2. Statistics

  • >1,000,000 Chinese character instances

  • 718,018 samples with an average of 718 samples in each class

  • 1000 classes, with each class corresponds to the syllables of a Mandarin word

  • ~2000 different speakers with a large coverage over speech modes, including speech rate, viewpoint, age, gender, make-up and so on

3. Evaluation Protocols

We provide two evaluation metrics for experiments.

A). The recognition accuracy over all 1000 classes is naturally considered as the base metric, since this is a classification task.

B). Motivated by the large diversity of the data shown in many aspects, such as the number of samples in each class, we also provide the Kappa Coefficient as a second evaluation metric.

4. Download

The database is public to universities and research institutes for research purpose only. To request a copy of the database, please do as follows:

  • Download the database Release Agreement, read it carefully, and complete it appropriately. Note that the agreement should be signed by a full-time staff member (that is, student is not acceptable). Then, please scan the signed agreement, send it to lipreading@vipl.ict.ac.cn and cc to the signatory's email. When we receive your signed agreement file, we would provide the download link to you.

  • Before using the dataset, you are recommended to refer to the following paper:
    Shuang Yang, Yuanhang Zhang, Dalu Feng, Mingmin Yang, Chenhao Wang, Jingyun Xiao, Keyu Long, Shiguang Shan, Xilin Chen, "LRW-1000: A Naturally-Distribute Large-Scale Benchmark or Li Reaing in the Wil,"IEEE FG 2019

5. Contact Info

lipreading@vipl.ict.ac.cn

附件下载:

Agreement

Paper

Code



附件下载:

上一篇:

FRHT Dataset

下一篇:

DEVISIGN Database