# Mitigating Semantic Collapse in Partially Relevant Video Retrieval

arXiv: https://arxiv.org/abs/2510.27432 · HTML: https://mlsanity.com/paper/2510.27432/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [BSN: Boundary Sensitive Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1806.02964/) (2018)
- [Temporal Action Detection with Structured Segment Networks](https://mlsanity.com/paper/1704.06228/) (2017)
- [Token Merging for Fast Stable Diffusion](https://mlsanity.com/paper/2303.17604/) (2023)
- [TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval](https://mlsanity.com/paper/2001.09099/) (2020)
- [Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching](https://mlsanity.com/paper/2102.02973/) (2021)
- [UATVR: Uncertainty-Adaptive Text-Video Retrieval](https://mlsanity.com/paper/2301.06309/) (2023)
- [Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model](https://mlsanity.com/paper/2405.15330/) (2024)
- [TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2409.01156/) (2024)
- [VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval](https://mlsanity.com/paper/2211.12764/) (2022)
- [4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models](https://mlsanity.com/paper/2503.10437/) (2025)
- [Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval](https://mlsanity.com/paper/2403.17998/) (2024)
- [ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2406.09936/) (2024)
- [Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval](https://mlsanity.com/paper/2309.17093/) (2023)
- [GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval](https://mlsanity.com/paper/2310.05195/) (2023)
- [Towards Efficient Partially Relevant Video Retrieval with Active Moment Discovering](https://mlsanity.com/paper/2504.10920/) (2025)
- [Knowledge Distillation with Feature Maps for Image Classification](https://mlsanity.com/paper/1812.00660/) (2018)
- [Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval](https://mlsanity.com/paper/2404.15516/) (2024)

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

- [Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval](https://mlsanity.com/paper/2604.03653/) (2026)
- [Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2605.06083/) (2026)
- [Auxiliary Descriptive Knowledge for Few-Shot Adaptation of Vision-Language Model](https://mlsanity.com/paper/2512.17313/) (2025)
- [Intrinsic Temporal Adaptation of CLIP for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2609.04800/) (2026)
- [Concentrate After Imagination: Text-Conditioned Evidence Grounding for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2609.08999/) (2026)

## Abstract (arXiv)

Partially Relevant Video Retrieval (PRVR) seeks videos where only part of the content matches a text query. Existing methods treat every annotated text-video pair as a positive and all others as negatives, ignoring the rich semantic variation both within a single video and across different videos. Consequently, embeddings of both queries and their corresponding video-clip segments for distinct events within the same video collapse together, while embeddings of semantically similar queries and segments from different videos are driven apart. This limits retrieval performance when videos contain multiple, diverse events. This paper addresses the aforementioned problems, termed as semantic collapse, in both the text and video embedding spaces. We first introduce Text Correlation Preservation Learning, which preserves the semantic relationships encoded by the foundation model across text queries. To address collapse in video embeddings, we propose Cross-Branch Video Alignment (CBVA), a contrastive alignment method that disentangles hierarchical video representations across temporal scales. Subsequently, we introduce order-preserving token merging and adaptive CBVA to enhance alignment by producing video segments that are internally coherent yet mutually distinctive. Extensive experiments on PRVR benchmarks demonstrate that our framework effectively prevents semantic collapse and substantially improves retrieval accuracy.