Call for Papers:Vol.12 Issue.2

Submission
Last date		 28-Apr-2026
Acceptance Status In One Day
Paper Publish In Two Days
Submit ManuScript

News & Updates

Submit Article

Dear Authors, Article publish in our journal for Volume-12,Issue-2. For article submission on below link: Submit Manuscript


Join As Board

Dear Reviewer, You can join our Reviewer team without given any charges in our journal. Submit Details on below link: Join As Board


Paper Publication Charges

IJARIIE APP
Download Android App

For Authors

Archives

IJARIIE Board

Downloads

Android App

Download IJARIIE APP

Authors

Title: :  Generating Text Conditioned 3D Human Motion
PaperId: :  28356
Published in:   International Journal Of Advance Research And Innovative Ideas In Education
Publisher:   IJARIIE
e-ISSN:   2395-4396
Volume/Issue:    Volume 12 Issue 2 2026
DUI:    16.0415/IJARIIE-28356
Licence: :   IJARIIE is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author NameAuthor Institute
Shilna KoyileriyanVimal Jyothi Engineering College

Abstract

Computer Science and Engineering
text-to-motion generation, diffusion models, HumanML3D dataset, 3D human motion, natural language processing, motion synthesis.
A novel approach to generating 3D human motions from textual descriptions using a two-stage framework that incorporates a temporal variational autoencoder (VAE). The first stage, text-to-length sampling, predicts the length of the motion sequence by approximating a probability distribution conditioned on the input text. This step enables the generation of variable-length motions that align naturally with diverse textual inputs. In the second stage, text-to-motion generation, the model synthesizes human motions consistent with the sampled lengths and input descriptions. At its core, the approach utilizes a temporal VAE, featuring a triplet structure of prior, posterior, and generator networks to learn the mapping between textual semantics and motion dynamics. To further enhance motion fidelity, a motion snippet code representation is proposed as an internal format, encapsulating localized temporal semantics to ensure smooth and realistic motions faithful to the input text. The framework’s flexibility accommodates a range of textual complexities, from simple commands to detailed narratives, ensuring both diversity and naturalness in the output. This approach is evaluated on a new large-scale dataset, HumanML3D, which includes 14,616 motion clips and 44,970 text descriptions, as well as on the KIT Motion-Language dataset. Quantitative metrics and user studies demonstrate significant advancements over baseline methods in terms of motion quality, diversity, and alignment with textual input. By addressing the challenges of variable sequence lengths, semantic diversity, and textual complexity, this two-stage VAE-based framework sets a new benchmark for text-driven 3D motion generation, with applications spanning animation, gaming, and human-computer interaction.

Citations

Copy and paste a formatted citation or use one of the links to import into a bibliography manager and reference.

IJARIIE Shilna Koyileriyan. "Generating Text Conditioned 3D Human Motion" International Journal Of Advance Research And Innovative Ideas In Education Volume 12 Issue 2 2026 Page 1641-1653
MLA Shilna Koyileriyan. "Generating Text Conditioned 3D Human Motion." International Journal Of Advance Research And Innovative Ideas In Education 12.2(2026) : 1641-1653.
APA Shilna Koyileriyan. (2026). Generating Text Conditioned 3D Human Motion. International Journal Of Advance Research And Innovative Ideas In Education, 12(2), 1641-1653.
Chicago Shilna Koyileriyan. "Generating Text Conditioned 3D Human Motion." International Journal Of Advance Research And Innovative Ideas In Education 12, no. 2 (2026) : 1641-1653.
Oxford Shilna Koyileriyan. 'Generating Text Conditioned 3D Human Motion', International Journal Of Advance Research And Innovative Ideas In Education, vol. 12, no. 2, 2026, p. 1641-1653. Available from IJARIIE, http://ijariie.com/AdminUploadPdf/Generating_Text_Conditioned_3D_Human_Motion_ijariie28356.pdf (Accessed : ).
Harvard Shilna Koyileriyan. (2026) 'Generating Text Conditioned 3D Human Motion', International Journal Of Advance Research And Innovative Ideas In Education, 12(2), pp. 1641-1653IJARIIE [Online]. Available at: http://ijariie.com/AdminUploadPdf/Generating_Text_Conditioned_3D_Human_Motion_ijariie28356.pdf (Accessed : )
IEEE Shilna Koyileriyan, "Generating Text Conditioned 3D Human Motion," International Journal Of Advance Research And Innovative Ideas In Education, vol. 12, no. 2, pp. 1641-1653, Mar-App 2026. [Online]. Available: http://ijariie.com/AdminUploadPdf/Generating_Text_Conditioned_3D_Human_Motion_ijariie28356.pdf [Accessed : ].
Turabian Shilna Koyileriyan. "Generating Text Conditioned 3D Human Motion." International Journal Of Advance Research And Innovative Ideas In Education [Online]. volume 12 number 2 ().
Vancouver Shilna Koyileriyan. Generating Text Conditioned 3D Human Motion. International Journal Of Advance Research And Innovative Ideas In Education [Internet]. 2026 [Cited : ]; 12(2) : 1641-1653. Available from: http://ijariie.com/AdminUploadPdf/Generating_Text_Conditioned_3D_Human_Motion_ijariie28356.pdf
BibTex EndNote RefMan RefWorks

Number Of Downloads



Save in Google Drive

Similar-Paper

TitleArea of ResearchAuther NameAction
Generating Text Conditioned 3D Human MotionComputer Science and EngineeringShilna Koyileriyan Download
WORD-LEVEL BLUR FOR REAL-TIME SCREEN ABUSE DETECTION: IMPLEMENTATION AND EVALUATIONcomputer Engineeringsohel sayyad Download
Heart Attack Risk Prediction Using Retinal Eye ImagesMachine LearningPrasanthi Siri Kuruma Download
Real Time Zero Knowledge Privacy & Ai Security for currency Transaction Using EthereumComputer EngineeringPANTHULA SAI MURALI Download
JANMITRA - AI POWERED PLATFORM BRIDGING SOCIETIES WITH NGO'S AND ORGANIZATIONScomputer engineeringUMESH AAGDE Download
Improvising Personalized Travel Recommendation System with Recency Effectscomputer science engineeringMrs. Fathima Zahera Download
Ensemble Models and Explainable AI for Malware DetectionComputer Science M Vandana Download
Smart E-Healthcare SystemComputer EngineeringVattikoti Sai Download
SURVEY ON RETAIL INSIGHT GENERATOR: VISION AI FOR CUSTOMER ANALYTICS AND HEATMAPSComputer EngineeringAmalkrishna K B Download
SMART COLLEGE SECURITY:AI-POWERED IDCARD VIOLATION AND FACE RECOGNITIONSYSTEMComputer science Athira Thomas Download
Consumer Behavioural Analysis Using Advanced Clustering TechniquesComputer Science and EngineeringSupriya Thati Download
A Low-Cost Smartphone-Based Sign Language Translator Using Computer Vision for Real-Time Deaf–Hearing CommunicationComputer Science and EngineeringHarsh Mishra Download
Predicting Stock Market Trends using Deep Learning TechniquesComputer Science and EngineeringAkruthi Shere Download
A SURVEY ON SMART VOTING SYSTEM USING BLOCKCHAINComputer Science EngineeringAleena Shaju Download
A SURVEY ON SECURESCAN 360: CYBER INTEGRATED SYSTEM FOR THREAT DETECTION AND IMAGE AUTHENTICATIONComputer Science and EngineeringAparna Sunil Download
12