# StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval

arXiv: https://arxiv.org/abs/2601.20597 · HTML: https://mlsanity.com/paper/2601.20597/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 10 of 10)

- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning](https://mlsanity.com/paper/2207.12819/) (2022)
- [CenterCLIP: Token Clustering for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2205.00823/) (2022)
- [A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval](https://mlsanity.com/paper/2208.02080/) (2022)
- [Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routing](https://mlsanity.com/paper/2503.10111/) (2025)
- [Low-rank Prompt Interaction for Continual Vision-Language Retrieval](https://mlsanity.com/paper/2501.14369/) (2025)
- [DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype](https://mlsanity.com/paper/2503.18042/) (2025)
- [CluMo: Cluster-based Modality Fusion Prompt for Continual Learning in Visual Question Answering](https://mlsanity.com/paper/2408.11742/) (2024)

## Abstract (arXiv)

Continual Text-to-Video Retrieval (CTVR) is a challenging multimodal continual learning setting, where models must incrementally learn new semantic categories while maintaining accurate text-video alignment for previously learned ones, thus making it particularly prone to catastrophic forgetting. A key challenge in CTVR is feature drift, which manifests in two forms: intra-modal feature drift caused by continual learning within each modality, and non-cooperative feature drift across modalities that leads to modality misalignment. To mitigate these issues, we propose StructAlign, a structured cross-modal alignment method for CTVR. First, StructAlign introduces a simplex Equiangular Tight Frame (ETF) geometry as a unified geometric prior to mitigate modality misalignment. Building upon this geometric prior, we design a cross-modal ETF alignment loss that aligns text and video features with category-level ETF prototypes, encouraging the learned representations to form an approximate simplex ETF geometry. In addition, to suppress intra-modal feature drift, we design a Cross-modal Relation Preserving loss, which leverages complementary modalities to preserve cross-modal similarity relations, providing stable relational supervision for feature updates. By jointly addressing non-cooperative feature drift across modalities and intra-modal feature drift, StructAlign effectively alleviates catastrophic forgetting in CTVR. Extensive experiments on benchmark datasets demonstrate that our method consistently outperforms state-of-the-art continual retrieval approaches.