Table 1: AI-Based Real-Time Detection and Translation of Indian

Sign Language Gestures

No. Title (Year) Author Methodology Used Accuracy Limitation

1 Sign Language Detection Aditya Shinde Employs several computer vision 83% The research focuses primarily on
(2025) and machine learning techniques positive aspects and capabilities,
for real-time gesture recognition. lacking a critical analysis of
drawbacks.
2 Breaking the Barriers: Video Alexander Proposes using Video Vision 75.58% Top-1 CNNs are computationally
Vision Transformers for Brettmann Transformer (ViViT) models (e.g., intensive and struggle with
Word-Level Sign Language VideoMAE) for word-level ASL capturing global temporal
Recognition (2025) recognition. dependencies in video sequences.
3 Text-Driven Diffusion Model Jiayi He Proposes a Text-driven Diffusion BLEU-1: 20.17 Existing two-step (text-to-gloss,
for Sign Language Model (TDM) framework to gloss-to-pose) methods are
Production (2025) generate sign pose sequences complex, computationally
directly from text. expensive, and inefficient.
4 An Efficient Gloss-Free Sign Kang Yin An LLM-based framework that uses SOTA BLEU Most gloss-free methods require
Language Translation Using off-the-shelf encoders to exploit scores domain-specific fine-tuning of visual
Spatial Configurations and spatial and motion features without encoders to achieve optimal results.
Motion Dynamics with domain-specific fine-tuning.
LLMs (2025)
5 Machine Learning based ISL R Thirumahal LSTM for gesture detection & 79% The main drawback is the current
Identification and Transformers for translating accuracy level, suggesting potential
Translation (2024) gestures into text. for further refinement.
6 Sign Language Recognition Jingchen Zou A review of key technical Less Accuracy Existing methods have significant
and Translation Methods approaches for sign language limitations in accuracy, and
Promote Sign Language recognition and translation, complex grammatical structures
Education: A Review (2024) including the use of large language challenge effective translation.
models.
7 Hand Sign Gesture Ayush Kumar Utilizes Decision Trees, CNN, High Accuracy The comprehension of sign
Recognition and Translator k-Nearest Neighbors, and data language is limited, and its
Using Convolution Neural augmentation techniques. specialized nature poses
Networks (CNN) and communication challenges.
k-Nearest Neighbors (k-NN)
(2024)
Continued on next page

1
 Table 1 – continued from previous page
No. Title (Year) Author Methodology Used Accuracy Limitation
8 A New Sign Language Jing Wu A modular sign language High Accuracy Existing generalized systems
Translation System Based on recognition system with regional overlook regional variations in sign
Expert Model (2024) sub-models and robust data languages and fail to address
augmentation. linguistic diversity.
9 Sign Language Translation Ashwin Acharya Fuses MediaPipe’s holistic pipeline 91.05% Challenges in recognizing similar
with fusion of Emotion for sign recognition with an LSTM gestures for multiple words; rapid
Detection (2024) network for emotion detection. gesture transitions complicate
coherent sentence creation.
10 Sign Language to Text So Xue Thong CNNs for static sign recognition 99.20% (static), Environmental conditions affect
Translation with Computer and Long Short-Term Memory 90.08% detection accuracy, and errors
Vision: Bridging the (LSTM) networks for dynamic (dynamic) occur when recognizing similar
Communication Gap (2024) signs. signs.
11 Bidirectional Sign Language Aditya Mahjan CNN for feature extraction and N/A General difficulties in translating
Translation System (2024) classification, combined with and recognizing sign language limit
YOLO3 for real-time object social interactions for
detection. hearing-impaired individuals.
12 Sign Language Detection Mrs. N. Kirthiga A Transformer-based model for 95.85% Difficulty in the accurate
Using Deep Learning (2024) ASL-to-Text generation and a identification of isolated signs;
wearable system using CNN. requires continuous collection of
high-quality data.
13 Real-Time Boundary Nour Albasmy A Multi-FILSTM system with 90.9% Continuous Sign Language
Detection for Continuous Fixed Input-Length LSTM models Recognition faces significant
Arabic Sign Language that analyzes frame sequences for challenges in identifying word
Translation (2024) word boundary detection. boundaries.
14 Overview of Sign Language ITM web of A review of sign language N/A Data scarcity and annotation
Translation Based on conferences representation methods and NLP inconsistencies hinder progress;
Natural Language Processing techniques like transfer learning ethical concerns affect dataset
(2024) and large language models. quality and usage.
15 American Sign Language Khalid Abdel A Multimodal Transformer 94% The datasets used for training the
Recognition Using a Hafeez Network (MTN) for recognition, model are limited, and there are
Multimodal Transformer using MediaPipe Holistic and challenges in recognizing diverse
Network (2024) ResNet50 for data extraction. hand signs effectively.
Continued on next page

2
 Table 1 – continued from previous page
No. Title (Year) Author Methodology Used Accuracy Limitation
16 Recent Advances on Deep Yanqiong Zhang A comprehensive review of deep N/A Major challenges identified are
Learning for Sign Language learning for SLR (CNN, RNN, dataset scale and diversity,
Recognition (2024) Transformer), focusing on the past achieving user independence, and
five years. modeling co-articulation.
17 Improving Gloss-free Sign Jinhui Ye Introduces SignCL, a contrastive +39% to +46% Gloss-free models suffer from a
Language Translation by learning strategy to learn more BLEU ”representation density problem”
Reducing Representation discriminative feature where distinct signs are packed too
Density (2024) representations in a self-supervised closely in feature space.
manner.
18 American Sign Language Yutong Gu Uses a wearable IMU system to 97.34% SER Accuracy drops dramatically in
Recognition and Translation collect data and a (user- user-independent tests due to
Using Perception Neuron CNN-BiLSTM-CTC model for dependent) inter-individual differences in
Wearable Inertial Motion recognition and translation. movement.
Capture System (2024)
19 Enhancing Sign Language Rani Astya Multimodal recognition integrating High Accuracy The recognized vocabulary and
Detection using Tensor Flow visual data from cameras with number of gestures need expansion;
(2023) depth sensors and wearable devices. multimodal integration requires
improvement for better accuracy.
20 Sign Language Detection in Shivkrupa Video data analysis for sign 80-90% Performance is hindered by low
Voice Output (2023) Publication’s language detection using light intensity and uncontrolled
convolutional neural networks. backgrounds.
21 Sign Language Detection Mohit Titarmare Utilizes image and video processing N/A Variations in signing styles affect
(2023) techniques, deep learning recognition accuracy, and changing
algorithms, and sensor technologies. lighting conditions impact gesture
interpretation.
22 Review on Sign Language Chris S. Crawford A review covering a standalone Good Accuracy Datasets for sign language
Translation (2023) translator using Raspberry Pi and translation are scarce, and the lack
hand-mesh/face-mesh models. of annotations makes it difficult for
neural models to learn.
23 American Sign Language Hunter Phillips Five multitask, transfer learning BLEU-4: 40.10 The ASLG-PC12 dataset lacks the
Translation Using Transfer models are used for translation, complexity of real ASL, and
Learning (2023) assessed on the ASLG-PC12 synthetic generation does not
dataset. reflect its diversity.
Continued on next page

3
 Table 1 – continued from previous page
No. Title (Year) Author Methodology Used Accuracy Limitation
24 Sign Language Identification Jans Johnson A skeletal-point feature extraction Good Accuracy There is a lack of knowledge of sign
using Skeletal Point-based framework for hand landmarks language among the public and an
Spatio-Temporal Recurrent combined with LSTM Networks for insufficient availability of
Neural Network (2023) gesture recognition. interpreters.
25 Gesture-to-Text Translation Kaustubh Mani Skin masking for hand 79% to 92% There is a need for a more accurate
Using SURF for Indian Sign Tripathi segmentation and Canny edge and effective model and complexity
Language (2023) detection for sharp edge detection. in developing a simpler model for
the task.
26 Using Artificial Intelligence Carlos Ortı́z León A systematic literature review 90% to 100% There is limited participation from
for Sign Language using the PRISMA methodology, the African continent in research
Translation: A Systematic focusing on CNN for sign language and an underutilization of
Literature Review (2023) translation. Generative Adversarial Networks
(GANs).
27 Continuous Sign Language Lianyu Hu Proposes Correlation Network SOTA WER Current methods in CSLR usually
Recognition with Correlation (CorrNet) to explicitly capture and process frames independently, thus
Network (2023) leverage body trajectories across failing to capture cross-frame
frames to identify signs. trajectories effectively.
28 Self-Emphasizing Network Zekang Liu Proposes a self-emphasizing SOTA WER Previous methods require heavy
for Continuous Sign network (SEN) to emphasize pose-estimation networks or
Language Recognition (2023) informative spatial and temporal additional pre-extracted heatmaps
regions without extra supervision. for supervision, increasing
complexity.
29 Improving Sign Recognition Lee Kezar Trains ISLR models to predict not ∼9% absolute Existing work does not consider
with Phonology (2023) only the sign but also its gain sign language phonology, which this
phonological characteristics (e.g., research aims to address for more
handshape) as an auxiliary task. accurate ISLR.
30 A Few-Shot Approach to Ragib Amin Nihal Proposes a few-shot learning High Addresses the challenge of limited
Sign Language Recognition: approach, training a model on one cross-lingual data availability for most of the
Can Learning One Language sign language (Bangla) to recognize accuracy world’s sign languages.
Enable Understanding of others with limited data.
All? (2023)
Continued on next page

4
 Table 1 – continued from previous page
No. Title (Year) Author Methodology Used Accuracy Limitation
31 Sign Language Translation: Zeyu Liang A survey classifying SLT literature N/A Scarcity of dataset resources is a
A Survey of Approaches and into improving SLR, different major bottleneck; modeling
Techniques (2023) models for SLT, and addressing long-term dependencies is difficult.
data scarcity.
32 Towards Zero-Shot Sign I. Oztel A Zero-Shot Learning framework N/A The difficulty of obtaining suitable
Language Recognition (2023) using textual/attribute descriptions training data for every sign in a
for knowledge transfer to recognize supervised learning setting.
unseen sign classes.
33 Improving Continuous Sign Fangyun Wei Identifies and leverages visually SOTA WER: Data scarcity in monolingual
Language Recognition with similar ”cross-lingual signs” from 16.7 (Test) CSLR; most sign languages are
Cross-Lingual Signs (2023) an auxiliary language dataset to mutually unintelligible, making
improve monolingual CSLR. transfer difficult.
34 CiCo: Domain-Aware Sign Yiting Bao Formulates sign language retrieval SOTA R@1 Data scarcity and the complexity of
Language Retrieval via as a cross-lingual problem, using scores sign-to-word mapping due to
Cross-Lingual Contrastive contrastive learning to map signs different linguistic rules and word
Learning (2023) and words into a shared space. order.
35 Advancement in Generative Vrutti Tanna A review of GAN-based approaches N/A There is a need for continuous
Adversarial Networks for SLP, including text-to-pose and text-to-pose translation and
(GANs) for Image pose-to-video translation. high-quality conditional image
Generation: A Step Towards generation.
Sign Language Production
(2023)
36 Sign Language Translation Rahib H. Abiyev Single Shot Multi Box Detection 99.9% An Intersection over Union (IOU)
Using Deep Convolutional (SSD) for object detection and of 0.5 is inadequate for robust
Neural Networks (2022) Inception v3 plus SVM for object detection.
classification.
37 Real-Time Detection and Cynthia Gasper A bidirectional system using speech 94.62% A lack of public awareness leads to
Translation for Indian Sign recognition to translate spoken isolation for the deaf community,
Language using Motion and words and motion recognition for and there are limited resources for
Speech Recognition (2022) gesture detection. learning Indian Sign Language.
Continued on next page

5
 Table 1 – continued from previous page
No. Title (Year) Author Methodology Used Accuracy Limitation
38 American Sign Language Yutong Gu Uses inertial sensors for capturing 99% The dataset is limited, and
Translation Using Wearable signs and surface electromyography user-independent validation showed
Inertial and (EMG) sensors for detecting facial a significant accuracy drop due to
Electromyography Sensors expressions. inter-individual differences.
(2022)
39 Sign Detect: An app to IEEE A mobile application developed to High Accuracy Existing techniques fail to address
detect sign language (2022) recognize and translate sign portability issues, and there is no
language into English text and comprehensive system for
audio formats. recognizing Alphabets, Numbers,
and Words.
40 Example-Based Machine Élise Bertin-Lemée Text-to-Sign Translation using a N/A The paper explicitly mentions the
Translation from Text to a domain-specific parallel corpus and limitations of the proposed method
Hierarchical Representation a recursive algorithm for building and the test set used to showcase
of Sign Language (2022) candidate translations. its potential.
41 A Simple Multi-Modality Fangyun Wei Progressively pre-trains a visual SOTA BLEU Data scarcity is identified as the
Transfer Learning Baseline network on human actions and a scores key bottleneck for training effective
for Sign Language translation network on a sign language translation models.
Translation (2022) multilingual corpus, then
fine-tunes.
42 Bidirectional Skeleton-Based Konstantinos M. Employs a bidirectional GCN 77.43% Top-1 Deficiencies in the quality and
Isolated Sign Recognition Dafnis framework with explicit start/end annotation accuracy of public
using Graph Convolutional frame detection on skeleton data. corpora (e.g., inconsistent glosses in
Networks (2022) WLASL).
43 Improving Signer Ruth Holmes Evaluates transfer learning and Pose A large performance gap exists
Independent Sign Language different input representations outperforms between signer-dependent and
Recognition for Low (RGB vs. pose) for RGB signer-independent models,
Resource Languages (2022) signer-independent models on especially for low-resource
low-resource languages. languages.
44 Video-Based Sign Language Babita Sonare CNN and RNN deep learning 92.4% Traditional sign language
Translation System Using algorithms for sign language recognition gloves are costly, and
Machine Learning (2021) recognition with an open-source continuous hand movement feature
Text-To-Speech API. extraction is complex.
Continued on next page

6
 Table 1 – continued from previous page
No. Title (Year) Author Methodology Used Accuracy Limitation
45 Enabling Real-time Sign H. Park Data augmentation for a robust 91% Low video resolutions from
Language Translation on dataset and a 3D convolutional depth-only videos and sensitivity to
Mobile Platforms with neural network for sign user motion during sign detection
On-board Depth Cameras classification on mobile devices. are key issues.
(2021)
46 Sign Language Transformers: Necati Cihan Joint learning of Continuous Sign 21.80 BLEU-4 Overfitting occurs when too many
Joint End-to-End Sign Camgoz Language Recognition and layers are added, and joint learning
Language Recognition and Translation using Connectionist degrades recognition performance
Translation (2020) Temporal Classification (CTC) loss. compared to task-specific networks.
47 Spatial-Temporal Graph Cleison Correia de Applies a Spatial-Temporal Graph 61.04% Top-1 The model does not distinguish the
Convolutional Networks for Amorim Convolutional Network (ST-GCN) (20 signs) type of learned joint (e.g., fingers
Sign Language Recognition to human skeletal movements for vs. elbow) and lacks depth
(2020) sign recognition. information.
48 Continuous Sign Language Junfu Pu Applies the Transformer with WER: 38.3 Supervised learning suffers from
Recognition via reinforcement learning (Self-critic (Test) exposure bias and issues with
Reinforcement Learning REINFORCE) to train directly on non-differentiable task metrics.
(2019) the WER metric.
49 Time Series Neural Networks Sujay S Kumar An end-to-end system using visual High Accuracy Prior research focused on intrusive
for Real Time Sign Language cues, deep learning, and Neural and expensive glove-based
Translation (2018) Machine Translation for ASL gloss solutions, which this work aims to
recognition. replace.
50 Sign Language Production Simon Stoll An NMT-based Qualitative Treating sign language as a
using Neural Machine continuous-text-to-gloss network concatenation of isolated glosses
Translation and Generative followed by a GAN for loses context and non-manual
Adversarial Networks (2018) pose-to-video generation. features.

References
[1] Thirumahal, R., Jayaprakash, A. H., Prakash, S., Kesavan, Y., Chirenjeevi, M., & Siva, M. (2024). Machine Learning based ISL Identification and Translation.
Journal of Ubiquitous Computing and Communication Technologies, 6 (4), 353–367. https://doi.org/10.36548/jucct.2024.4.003
[2] Ansari, N., Awari, S., Movva, S. H., Parthasarathy, A., & Poriwade, S. (2024). GesSpy: ML Driven Real Time Sign Language Detection. In 2024 8th International
Conference on Intelligent Computing and Control Systems (ICICCS), 912–917. https://doi.org/10.1109/icipcn63822.2024.00157

7
 [3] Shinde, A. (2025). Indian Sign Language Detection. Indian Scientific Journal Of Research In Engineering And Management, 09 (01), 1–9. https://doi.org/10.
55041/ijsrem41093
[4] Zou, J., Li, J., Tang, J., Huang, Y., Ding, S., & Xu, X. (2024). Sign Language Recognition and Translation Methods Promote Sign Language Education: A Review.
In 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 3479–3484. https://doi.org/10.1109/smc54092.2024.10831194
[5] Kumar, A., Utekar, S., & Viji, D. (2024). Hand Sign Gesture Recognition and Translator Using Convolution Neural Networks (CNN) and k-Nearest Neighbors (k-NN).
In 2024 International Conference on Device Control, and Computing Technologies (ICDCCT), 1–7. https://doi.org/10.1109/icdcot61034.2024.10515667
[6] Wu, J. (2024). A New Sign Language Translation System Based on Expert Model. Applied and Computational Engineering, 81 (1), 210–218. https://doi.org/10.
54254/2755-2721/81/20241162
[7] Acharya, A., Patil, N., Pathak, U., & Bhagwat, S. (2024). Sign Language Translation with fusion of Emotion Detection. In 2024 International Conference on
Computing, Communication, Control and Automation (ICCUBEA), 1–6. https://doi.org/10.1109/iccubea61740.2024.10774760
[8] Astya, R., Agrawal, A., Chauhan, A., Sony, A. K., Thakur, K., & Nand, P. (2023). Enhancing Sign Language Detection using Tensor Flow. In 2023 4th International
Conference on Advancements in Computing, Communication, Computer Sciences and Social Sciences (ICAC3N). https://doi.org/10.1109/icac3n60023.2023.
10541807
[9] Abiyev, R. H., Arslan, M., & Idoko, J. B. (2020). Sign Language Translation Using Deep Convolutional Neural Networks. KSII Transactions on Internet and
Information Systems, 14 (2), 631–653. https://doi.org/10.3837/TIIS.2020.02.009
[10] Sign Language Detection in Voice Output. (2023). International Journal of Advanced Research in Science, Communication and Technology, 300–307. https:
//doi.org/10.48175/ijarsct-9578
[11] Thong, S. X., Tan, E. L., & Goh, C. P. (2024). Sign Language to Text Translation with Computer Vision: Bridging the Communication Gap. In 2024 International
Conference on Digital Applications, Transformation & Economy (ICDXA), 215–219. https://doi.org/10.1109/icdxa61007.2024.10470532
[12] Gasper, C. (2022). Real-Time Detection and Translation for Indian Sign Language using Motion and Speech Recognition. International Journal for Research in
Applied Science and Engineering Technology, 10 (6), 229–232. https://doi.org/10.22214/ijraset.2022.43797

[13] Mahjan, A., Hendre, P., Mankhair, G., Satpute, S. S., & Chaudhari, D. A. (2024). Bidirectional Sign Language Translation System. In 2024 International Conference
on Computing, Communication, Control and Automation (ICCUBEA), 1–7. https://doi.org/10.1109/iccubea61740.2024.10774984
[14] Kirthiga, N., Krishna, M. V., Vadlamudi, V. N., Kiran, M. V. S., & Hussain, D. (2024). Sign Language Detection Using Deep Learning. International Journal for
Research in Applied Science and Engineering Technology. https://doi.org/10.22214/ijraset.2024.58630

[15] Gu, Y., Zheng, C., Todoh, M., & Zha, F. (2022). American Sign Language Translation Using Wearable Inertial and Electromyography Sensors for Tracking Hand
Movements and Facial Expressions. Frontiers in Neuroscience, 16. https://doi.org/10.3389/fnins.2022.962141
[16] Sign Detect: An app to detect sign language. (2022). In 2022 IEEE International Conference on Metrology for Extended Reality, Artificial Intelligence and Neural
Engineering (MetroXRAINE). https://doi.org/10.1109/metroxraine54828.2022.9967529

[17] Camgoz, N. C., Koller, O., Hadfield, S., & Bowden, R. (2020). Sign Language Transformers: Joint End-to-End Sign Language Recognition and Translation. In
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10023–10033. https://doi.org/10.1109/CVPR42600.2020.01004

8
[18] Sonare, B., Padgal, A., Gaikwad, Y., & Patil, A. (2021). Video-Based Sign Language Translation System Using Machine Learning. In 2021 International Conference
on Nascent Technologies in Engineering (ICNTE), 1–4. https://doi.org/10.1109/INCET51464.2021.9456176
[19] Albasmy, N., & Ghantous, M. (2024). Real-Time Boundary Detection for Continuous Arabic Sign Language Translation. In 2024 IEEE International Conference on
Acoustics, Speech, and Signal Processing (ICASSP). https://doi.org/10.1109/icassp48485.2024.10446212
[20] Wang, H. (2025). Overview of Sign Language Translation Based on Natural Language Processing. ITM Web of Conferences, 70, 02010. https://doi.org/10.1051/
itmconf/20257002010
[21] Titarmare, M., Wankar, G., Thapliyal, G., Raut, Y., & Sheikh, R. (2023). Sign Language Detection. International Journal for Research in Applied Science and
Engineering Technology. https://doi.org/10.22214/ijraset.2023.57432
[22] Crawford, C. S. (2023). Review on Sign Language Translation. International Journal For Science Technology And Engineering, 11 (6), 124–127. https://doi.org/
10.22214/ijraset.2023.53478
[23] Hafeez, K., Massoud, M., Menegotti, T., Tannous, J., & Wedge, S. (2024). American Sign Language Recognition Using a Multimodal Transformer Network. In 2024
IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 654–659. https://doi.org/10.1109/ccece59415.2024.10667296

[24] Phillips, H., Lasch, S., & Maddumala, M. (2023). American Sign Language Translation Using Transfer Learning. In 2023 International Conference on AI, Big Data,
IoT and Security (AI-BGIS). https://doi.org/10.1109/aibthings58340.2023.10291026
[25] Johnson, J., Joseph, J., Reji, M., George, M. E., & Sajanraj, T. D. (2023). Sign Language Identification using Skeletal Point-based Spatio-Temporal Recurrent
Neural Network. In 2023 International Conference on Signal and Image Processing (ICSIP), 465–470. https://doi.org/10.1109/icscc59169.2023.10334974

[26] Tripathi, K. M., Kamat, P., Patil, S., Jayaswal, R., Ahirrao, S., & Kotecha, K. (2023). Gesture-to-Text Translation Using SURF for Indian Sign Language. Applied
System Innovation, 6 (2), 35. https://doi.org/10.3390/asi6020035
[27] Kumar, S. S., Wangyal, T., Saboo, V., & Srinath, R. (2018). Time Series Neural Networks for Real Time Sign Language Translation. In 2018 IEEE 13th International
Conference on Industrial and Information Systems (ICIIS), 243–248. https://doi.org/10.1109/ICMLA.2018.00043

[28] Park, H., Lee, Y., & Ko, J. (2021). Enabling Real-time Sign Language Translation on Mobile Platforms with On-board Depth Cameras. Proceedings of the 19th
ACM Conference on Embedded Networked Sensor Systems, 3463498. https://doi.org/10.1145/3463498
[29] Bertin-Lemée, É., Braffort, A., Challant, C., Danet, C., & Filhol, M. (2022). Example-Based Machine Translation from Text to a Hierarchical Representation of Sign
Language. arXiv preprint arXiv:2205.03314. https://doi.org/10.48550/arXiv.2205.03314
[30] Ortı́z León, C., Yupanqui-Allcca, F., & Meneses-Claudio, B. (2023). Using Artificial Intelligence for Sign Language Translation: A Systematic Literature Review.
Applied Sciences, 13 (15), 8847. https://doi.org/10.3390/app13158847
[31] Zhang, Y., & Jiang, X. (2024). Recent Advances on Deep Learning for Sign Language Recognition. Computer Modeling in Engineering & Sciences, 139 (3), 2399-2450.
https://doi.org/10.32604/cmes.2023.045731
[32] Wei, F., Bao, J., Chen, D., Zhang, W., Codella, N., Yuan, L., & Liu, C. (2022). A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

9
[33] Hu, L., Gao, L., Liu, Z., & Feng, W. (2023). Continuous Sign Language Recognition with Correlation Network. In Proceedings of the IEEE/CVF Conference on
Computer Vision and Pattern Recognition (CVPR).
[34] Liu, Z., Hu, L., Gao, L., & Feng, W. (2023). Self-Emphasizing Network for Continuous Sign Language Recognition. In Proceedings of the AAAI Conference on
Artificial Intelligence.
[35] Kezar, L., Thomason, J., & Sehyr, Z. (2023). Improving Sign Recognition with Phonology. In Proceedings of the 17th Conference of the European Chapter of the
Association for Computational Linguistics (EACL).
[36] Ye, J., Wang, X., Jiao, W., Liang, J., & Xiong, H. (2024). Improving Gloss-free Sign Language Translation by Reducing Representation Density. In Advances in
Neural Information Processing Systems (NeurIPS).
[37] He, J., Wang, X., Zhang, R., Tang, S., Wang, Y., & Cheng, L. (2025). Text-Driven Diffusion Model for Sign Language Production. In SLRTP Sign Production
Challenge.
[38] Dafnis, K. M., Chroni, E., Neidle, C., & Metaxas, D. N. (2022). Bidirectional Skeleton-Based Isolated Sign Recognition using Graph Convolutional Networks. In
Proceedings of the Language Resources and Evaluation Conference (LREC).

[39] de Amorim, C. C., Macedo, D., & Zanchettin, C. (2020). Spatial-Temporal Graph Convolutional Networks for Sign Language Recognition. arXiv preprint
arXiv:1901.11164.
[40] Nihal, R. A., & Broti, N. M. (2023). A Few-Shot Approach to Sign Language Recognition: Can Learning One Language Enable Understanding of All?. In Lecture
Notes in Computer Science.

[41] Liang, Z., Li, H., & Chai, J. (2023). Sign Language Translation: A Survey of Approaches and Techniques. Electronics, 12 (12), 2678. https://doi.org/10.3390/
electronics12122678
[42] Pu, J., Zhou, W., & Li, H. (2019). Continuous Sign Language Recognition via Reinforcement Learning. In IEEE International Conference on Image Processing
(ICIP).

[43] Gu, Y., Oku, H., & Todoh, M. (2024). American Sign Language Recognition and Translation Using Perception Neuron Wearable Inertial Motion Capture System.
Sensors, 24 (2), 453.
[44] Oztel, I., Meric, M., Oztel, B. K. O., Ozcinar, M., & Ekenel, H. K. (2023). Towards Zero-Shot Sign Language Recognition. IEEE Transactions on Pattern Analysis
and Machine Intelligence.
[45] Wei, F., Chen, Y., Niu, S., Bao, J., Chen, D., & Zhang, W. (2023). Improving Continuous Sign Language Recognition with Cross-Lingual Signs. In Proceedings of
the IEEE/CVF International Conference on Computer Vision (ICCV).
[46] Bao, Y., Wang, Y., Wei, F., Bao, J., Chen, D., & Zhang, W. (2023). CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning. In
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
[47] Holmes, R., Rushe, E., Fowley, F., & Ventresque, A. (2022). Improving Signer Independent Sign Language Recognition for Low Resource Languages. In Proceedings
of the 4th International Workshop on Sign Language Translation and Avatar Technology (SLTAT).

10
[48] Tanna, V. (2023). Advancement in Generative Adversarial Networks (GANs) for Image Generation: A Step Towards Sign Language Production. Data Science
Prophet.
[49] Stoll, S., Camgoz, N. C., Hadfield, S., & Bowden, R. (2018). Sign Language Production using Neural Machine Translation and Generative Adversarial Networks. In
Proceedings of the British Machine Vision Conference (BMVC).
[50] Yin, K., Shen, H.-L., & Gao, L.-L. (2025). An Efficient Gloss-Free Sign Language Translation Using Spatial Configurations and Motion Dynamics with LLMs. In
Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

11