# SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval

arXiv: https://arxiv.org/abs/2407.16394 · HTML: https://mlsanity.com/paper/2407.16394/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 58 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Builds on (most cited first, 30 of 38)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation](https://mlsanity.com/paper/2003.13830/) (2020)
- [Use What You Have: Video Retrieval Using Representations From Collaborative Experts](https://mlsanity.com/paper/1907.13487/) (2019)
- [Improving Sign Language Translation with Monolingual Data by Sign Back-Translation](https://mlsanity.com/paper/2105.12397/) (2021)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language](https://mlsanity.com/paper/2008.08143/) (2020)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues](https://mlsanity.com/paper/2007.12131/) (2020)
- [Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining](https://mlsanity.com/paper/2307.14768/) (2023)
- [TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval](https://mlsanity.com/paper/2207.07852/) (2022)
- [Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings](https://mlsanity.com/paper/1908.03477/) (2019)
- [CenterCLIP: Token Clustering for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2205.00823/) (2022)
- [TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation](https://mlsanity.com/paper/2010.05468/) (2020)
- [Multi-channel Transformers for Multi-articulatory Sign Language Translation](https://mlsanity.com/paper/2009.00299/) (2020)
- [SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition](https://mlsanity.com/paper/2110.05382/) (2021)
- [Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations](https://mlsanity.com/paper/2211.11427/) (2022)
- [Unified Coarse-to-Fine Alignment for Video-Text Retrieval](https://mlsanity.com/paper/2309.10091/) (2023)
- [Boosting Continuous Sign Language Recognition via Cross Modality Augmentation](https://mlsanity.com/paper/2010.05264/) (2020)
- [Global-local Enhancement Network for NMFs-aware Sign Language Recognition](https://mlsanity.com/paper/2008.10428/) (2020)
- [Watch, read and lookup: learning to spot signs from multiple supervisors](https://mlsanity.com/paper/2010.04002/) (2020)
- [Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation](https://mlsanity.com/paper/2109.13318/) (2021)
- [Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment](https://mlsanity.com/paper/2305.12218/) (2023)

## Built on by (most cited first, 5 of 5)

- [Uni-Sign: Toward Unified Sign Language Understanding at Scale](https://mlsanity.com/paper/2501.15187/) (2025)
- [C2RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval](https://mlsanity.com/paper/2408.09949/) (2024)
- [Scaling up Multimodal Pre-training for Sign Language Understanding](https://mlsanity.com/paper/2408.08544/) (2024)
- [Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval](https://mlsanity.com/paper/2607.09263/) (2026)
- [Kinematics-Centric Continuous Sign Language Retrieval with Gloss-Guided Boundary-Aware Alignment](https://mlsanity.com/paper/2610.05306/) (2026)

## Abstract (arXiv)

Different from traditional video retrieval, sign language retrieval is more biased towards understanding the semantic information of human actions contained in video clips. Previous works typically only encode RGB videos to obtain high-level semantic features, resulting in local action details drowned in a large amount of visual information redundancy. Furthermore, existing RGB-based sign retrieval works suffer from the huge memory cost of dense visual data embedding in end-to-end training, and adopt offline RGB encoder instead, leading to suboptimal feature representation. To address these issues, we propose a novel sign language representation framework called Semantically Enhanced Dual-Stream Encoder (SEDS), which integrates Pose and RGB modalities to represent the local and global information of sign language videos. Specifically, the Pose encoder embeds the coordinates of keypoints corresponding to human joints, effectively capturing detailed action features. For better context-aware fusion of two video modalities, we propose a Cross Gloss Attention Fusion (CGAF) module to aggregate the adjacent clip features with similar semantic information from intra-modality and inter-modality. Moreover, a Pose-RGB Fine-grained Matching Objective is developed to enhance the aggregated fusion feature by contextual matching of fine-grained dual-stream features. Besides the offline RGB encoder, the whole framework only contains learnable lightweight networks, which can be trained end-to-end. Extensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods on various datasets.