Kinematics-Centric Continuous Sign Language Retrieval with Gloss-Guided Boundary-Aware Alignment
cs.CV
Submitted: 2026-10-04
Updated: 2026-10-04
Comments: Accepted by ACM Multimedia 2026 (ACM MM 2026)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning
- SignX: Continuous Sign Recognition in Compact Pose-Rich Latent Space
- Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation
- Distilling the Knowledge in a Neural Network
- SignSplat: Rendering Sign Language via Gaussian Splatting
- MediaPipe: A Framework for Building Perception Pipelines
- CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
- Representation Learning with Contrastive Predictive Coding
- DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation
- MaDiS: Taming Masked Diffusion Language Models for Sign Language Generation
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models