Challenge: a new method for analyzing prosody in sign languages uses the velocity profile of the hands . the velocity profiles of hand movements can be used to analyse prosodic structure .
Approach: They propose a method for extracting velocity information from unlabeled video of sign language using CoTracker.
Outcome: The proposed method can extract prosodic information from unlabeled video clips.

Similar Papers

Improving Handshape Representations for Sign Language Processing: A Graph Neural Network Approach (2025.emnlp-main)

Copied to clipboard

Challenge: Existing systems for sign language recognition process a signing sequence holistically, leaving handshape information implicit, which limits both recognition accuracy and linguistic analysis.
Approach: They propose a graph neural network that separates temporal dynamics from static handshape configurations in continuous signing sequences.
Outcome: The proposed approach achieves 46% accuracy across 37 handshape classes, compared to 25% for baseline methods.
SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale (2025.findings-acl)

Copied to clipboard

Challenge: Existing work on sign language video processing focuses on the face, hands and body posture of the signer.
Approach: They propose to learn the handshapes and rich facial expressions of sign languages in a self-supervised fashion by learning from individual frames rather than video sequences.
Outcome: The proposed model is more efficient than previous work on sign language pre-training.
Linguistically-driven Framework for Computationally Efficient and Scalable Sign Recognition (L18-1)

Copied to clipboard

Challenge: a new general framework for sign recognition from monocular video is presented . the framework exploits state-of-the-art learning methods while incorporating features based on what we know about the linguistic composition of lexical signs.
Approach: They propose a general framework for sign recognition from monocular video . they exploit state-of-the-art learning methods while incorporating features from linguistic information .
Outcome: The proposed framework exploits state-of-the-art learning methods while incorporating features based on what we know about linguistic composition of lexical signs.
Sign Language Video Segmentation Using Temporal Boundary Identification (2025.acl-srw)

Copied to clipboard

Challenge: Sign language segmentation focuses on identifying temporal boundaries within video . previous methods have relied on frame-level and phrase-level segmentation.
Approach: They propose to use synchronized subtitle data to facilitate temporal boundary recognition by a sequence-to-sequence model with and without attention for subtitle boundary identification.
Outcome: The proposed model outperforms baseline models on optical flow data and aligned subtitles from BOBSL and YouTube-ASL.
Handshape-Aware Sign Language Recognition: Extended Datasets and Exploration of Handshape-Inclusive Methods (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing work on sign language recognition encodes videos without acknowledging phonological attributes of signs.
Approach: They propose a single-encoder network and a dual-encoding network for handshape-inclusive sign language recognition.
Outcome: The proposed methods outperform baseline methods in the PHOENIX14T-HS dataset . the proposed methods consistently outperformed baseline methods .
Linguistically Motivated Sign Language Segmentation (2023.findings-emnlp)

Copied to clipboard

Challenge: Sign language segmentation is a crucial task in sign language processing systems.
Approach: They propose to combine two kinds of segmentation: segmentation into individual signs and segmentation to segment into phrases, larger units comprising several signs.
Outcome: The proposed model is based on linguistic cues observed in sign language corpora and replaces the predominant IO tagging scheme with BIO taging to account for continuous signing.
Modeling Intensification for Sign Language Generation: A Computational Approach (2022.findings-acl)

Copied to clipboard

Challenge: End-to-end sign language generation models do not accurately represent prosody in sign language.
Approach: They propose to model intensification in a data-driven manner to improve prosody in generated sign languages by modeling temporal and spatial variations.
Outcome: The proposed models improve the prosody of generated sign languages by using data-driven models.
A Low-Cost Motion Capture Corpus in French Sign Language for Interpreting Iconicity and Spatial Referencing Mechanisms (2022.lrec-1)

Copied to clipboard

Challenge: Existing tools for automatic translation of sign language videos into transcribed texts are limited.
Approach: They propose to use deep learning methods to circumvent the use of models in spatial referencing recognition by a 3D skeleton and a software program to capture and post-process the LSF-SHELVES corpus.
Outcome: The proposed system targets iconicity and spatial referencing in french sign language . it is light-weight and low-cost to collect data from a large panel of signers .
Unsupervised Discrete Representations of American Sign Language (2024.emnlp-main)

Copied to clipboard

Challenge: Modern NLP models use discrete tokens to represent continuous signals, such as videos, audio, or gestures . modalities that are continuous are difficult to use with discrete models, such a LLM .
Approach: They propose a method that discretizes sequences of fingerspelling signs into tokens . they also propose 'loss function' to improve interpretability of the tokens.
Outcome: The proposed method improves the performance of the tokenizer on downstream tasks.
Sign Languages and the Online World Online Dictionaries & Lexicostatistics (L18-1)

Copied to clipboard

Challenge: Several online dictionaries documenting the lexicon of a variety of sign languages are available . methodological issues must be addressed regarding how these resources are used for research purposes.
Approach: They propose a web-based tool for annotating the articulatory features of signs . they compare handshapes for four Asian SLs and handshape for the entire sample .
Outcome: The proposed tool compares handshapes and handsights of Asian SLs with European, American, and Brazilian SL samples.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations