Pith. sign in

REVIEW 1 cited by

Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.00448 v1 pith:ZL2Z4BJR submitted 2022-11-01 cs.CV

classification cs.CV
keywords cslrbackgroundbackgroundsdatasetsigncontinuousexistinglanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The goal of this work is background-robust continuous sign language recognition. Most existing Continuous Sign Language Recognition (CSLR) benchmarks have fixed backgrounds and are filmed in studios with a static monochromatic background. However, signing is not limited only to studios in the real world. In order to analyze the robustness of CSLR models under background shifts, we first evaluate existing state-of-the-art CSLR models on diverse backgrounds. To synthesize the sign videos with a variety of backgrounds, we propose a pipeline to automatically generate a benchmark dataset utilizing existing CSLR benchmarks. Our newly constructed benchmark dataset consists of diverse scenes to simulate a real-world environment. We observe even the most recent CSLR method cannot recognize glosses well on our new dataset with changed backgrounds. In this regard, we also propose a simple yet effective training scheme including (1) background randomization and (2) feature disentanglement for CSLR models. The experimental results on our dataset demonstrate that our method generalizes well to other unseen background data with minimal additional training images.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Isharah: A Large-Scale Multi-Scene Dataset for Continuous Sign Language Recognition

    cs.CV 2025-06 conditional novelty 7.0 of 10

    Isharah is a new 30,000-clip, multi-scene Saudi Sign Language dataset with gloss and translation annotations, plus signer-independent and unseen-sentence benchmarks for continuous sign language recognition and translation.

Pith tools