# Intrinsic Temporal Adaptation of CLIP for Partially Relevant Video Retrieval

arXiv: https://arxiv.org/abs/2609.04800 · HTML: https://mlsanity.com/paper/2609.04800/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [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)
- [TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval](https://mlsanity.com/paper/2001.09099/) (2020)
- [Use What You Have: Video Retrieval Using Representations From Collaborative Experts](https://mlsanity.com/paper/1907.13487/) (2019)
- [Interpreting CLIP's Image Representation via Text-Based Decomposition](https://mlsanity.com/paper/2310.05916/) (2023)
- [Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning](https://mlsanity.com/paper/2003.00392/) (2020)
- [Dual Encoding for Zero-Example Video Retrieval](https://mlsanity.com/paper/1809.06181/) (2018)
- [Multimodal Language Models See Better When They Look Shallower](https://mlsanity.com/paper/2504.21447/) (2025)
- [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)
- [HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning](https://mlsanity.com/paper/2507.17402/) (2025)
- [GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2405.13824/) (2024)
- [Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2506.07471/) (2025)
- [Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval](https://mlsanity.com/paper/2504.13035/) (2025)
- [Mitigating Semantic Collapse in Partially Relevant Video Retrieval](https://mlsanity.com/paper/2510.27432/) (2025)
- [Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2510.12283/) (2025)
- [ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2508.19024/) (2025)

## Abstract (arXiv)

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos that contain moments relevant to a text query. Since the target moment occupies only a portion of the video, PRVR requires retrieval based on fine-grained understanding beyond coarse video-level matching. However, existing methods often rely on frozen CLIP frame features, which lack temporal understanding. Even with recent progress in parameter-efficient CLIP adaptation, video-level predictions can still be supported by imprecise frame-level evidence. In this paper, we propose an Intrinsic Temporal Adaptation (ITA) framework for PRVR. First, our Backbone-Internal Temporal Adaptation allows the last few visual transformer layers to attend over groups of neighboring frames. This provides temporally aware frame embeddings while keeping CLIP frozen and training only adaptation parameters. Second, we introduce Affinity-Weighted Gradient Propagation to address the weakly supervised nature of PRVR, softly aggregating top-k frames based on text-frame affinities and propagating learning signals to multiple query-relevant frames. Our method achieves state-of-the-art performance on PRVR benchmarks, demonstrates robust cross-dataset transfer, and retrieves substantially more accurate frame-level evidence within ground-truth query-relevant moments. Our code is available at github.com/hynnsk/ITA.