# Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval

arXiv: https://arxiv.org/abs/2506.07471 · HTML: https://mlsanity.com/paper/2506.07471/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2003.03773/) (2020)
- [TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval](https://mlsanity.com/paper/2001.09099/) (2020)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?](https://mlsanity.com/paper/2301.00184/) (2022)
- [Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval](https://mlsanity.com/paper/1906.04402/) (2019)
- [Disentangled Representation Learning for Text-Video Retrieval](https://mlsanity.com/paper/2203.07111/) (2022)
- [Video Corpus Moment Retrieval with Contrastive Learning](https://mlsanity.com/paper/2105.06247/) (2021)
- [UATVR: Uncertainty-Adaptive Text-Video Retrieval](https://mlsanity.com/paper/2301.06309/) (2023)
- [Co-learning: Learning from Noisy Labels with Self-supervision](https://mlsanity.com/paper/2108.04063/) (2021)
- [Multi-granularity Correspondence Learning from Long-term Noisy Videos](https://mlsanity.com/paper/2401.16702/) (2024)
- [CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval](https://mlsanity.com/paper/2109.10016/) (2021)
- [Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment](https://mlsanity.com/paper/2305.12218/) (2023)
- [A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus](https://mlsanity.com/paper/2011.09046/) (2020)
- [Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval](https://mlsanity.com/paper/2209.13307/) (2022)
- [GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval](https://mlsanity.com/paper/2310.05195/) (2023)

## Built on by (most cited first, 10 of 10)

- [HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning](https://mlsanity.com/paper/2507.17402/) (2025)
- [Mitigating Semantic Collapse in Partially Relevant Video Retrieval](https://mlsanity.com/paper/2510.27432/) (2025)
- [Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning](https://mlsanity.com/paper/2509.01383/) (2025)
- [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)
- [ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2508.19024/) (2025)
- [Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2603.23902/) (2026)
- [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)
- [CurvSpec: Adaptive Multi-Curvature Learning for Partial Relevant Video Retrieval](https://mlsanity.com/paper/2609.36815/) (2026)

## Abstract (arXiv)

Partially Relevant Video Retrieval~(PRVR) aims to retrieve a video where a specific segment is relevant to a given text query. Typical training processes of PRVR assume a one-to-one relationship where each text query is relevant to only one video. However, we point out the inherent ambiguity between text and video content based on their conceptual scope and propose a framework that incorporates this ambiguity into the model learning process. Specifically, we propose Ambiguity-Restrained representation Learning~(ARL) to address ambiguous text-video pairs. Initially, ARL detects ambiguous pairs based on two criteria: uncertainty and similarity. Uncertainty represents whether instances include commonly shared context across the dataset, while similarity indicates pair-wise semantic overlap. Then, with the detected ambiguous pairs, our ARL hierarchically learns the semantic relationship via multi-positive contrastive learning and dual triplet margin loss. Additionally, we delve into fine-grained relationships within the video instances. Unlike typical training at the text-video level, where pairwise information is provided, we address the inherent ambiguity within frames of the same untrimmed video, which often contains multiple contexts. This allows us to further enhance learning at the text-frame level. Lastly, we propose cross-model ambiguity detection to mitigate the error propagation that occurs when a single model is employed to detect ambiguous pairs for its training. With all components combined, our proposed method demonstrates its effectiveness in PRVR.