Datasets › CAS-VSR-W1k (LRW-1000)

CAS-VSR-W1k (LRW-1000)

Introduced by Shuang Yang et al. in LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild1 Jan 2019 archive 2025-07-28

LRW-1000 has been renamed as CAS-VSR-W1k.* It 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.

Source: VIPL Image Source: https://arxiv.org/pdf/1810.06990v6.pdf

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Lipreading CAS-VSR-W1k (LRW-1000) SyncVSR (Word Boundary) Top-1 Accuracy 58.2 SyncVSR: Data-Efficient Visual Speech Recognition with... KAIST-AILab/SyncVSR 9 Compare

Papers archive 2025-07-28

8 shown of 8 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 9. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

research-only, non-commercial

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • CAS-VSR-W1k (LRW-1000)

1 variant name, as the archive lists them.

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