← Back to all news
arXiv Machine Learning By Himadri Bhuyan, Rohit Dhaipule, Partha Pratim Das

Sequence Recognition in Bharatnatyam dance

Read the original on arXiv Machine Learning →

The paper presents a method for recognizing sequences of key postures and motions in Bharatanatyam Adavus using a CNN for key postures (99% accuracy) and an SVM for motions (84% accuracy). It then matches these sequences to ground truth with an Edit Distance algorithm, achieving 98% accuracy. The study claims novelty by considering both postures and motions, measuring prediction time, and testing scalability across all 15 Adavus and 58 variations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computation and Language
2d ago

Maswao: An automatically collected, prepared, and benchmarked dataset for South African Sign Language

The paper introduces Maswao, a dataset of South African Sign Language (SASL) created through automated collection and preparation of video content from public sources, minimal human labor, and weak sentence alignment using audio-to-text ASR and motion analysis. The authors benchmark the dataset on sign‑to‑text translation, showing Transformer models outperform recurrent baselines with BLEU‑1 to BLEU‑4 scores ranging from 13.78 to 1.54. The study highlights the potential of automated dataset creation for under‑represented sign languages and demonstrates promising translation results that encourage further research.

By Thapelo Sindane, Unarine Netshifhefhe, Vukosi Marivate, Abiodun Modupe, Herkulaas Combrink, Ketro Sithole
llmscomputer-visionmultimodalbenchmarks
More like this →