# TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval

arXiv: https://arxiv.org/abs/2409.01156 · HTML: https://mlsanity.com/paper/2409.01156/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning in multimodal models, one of 12 directions in Efficient LLM inference and serving.
- Builds on 63 of its 74 references that are in the map.
- First posted on arXiv 2 Sep 2024.

## Placed in

- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 30 of 63)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)

## Built on by (most cited first, 30 of 40)

- [FastVGGT: Training-Free Acceleration of Visual Geometry Transformer](https://mlsanity.com/paper/2509.02560/) (2025)
- [DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models](https://mlsanity.com/paper/2411.15024/) (2024)
- [HoliTom: Holistic Token Merging for Fast Video Large Language Models](https://mlsanity.com/paper/2505.21334/) (2025)
- [FastVID: Dynamic Density Pruning for Fast Video Large Language Models](https://mlsanity.com/paper/2503.11187/) (2025)
- [Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality](https://mlsanity.com/paper/2505.18227/) (2025)
- [xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs](https://mlsanity.com/paper/2410.16267/) (2024)
- [LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs](https://mlsanity.com/paper/2506.21862/) (2025)
- [LinVT: Empower Your Image-level Large Language Model to Understand Videos](https://mlsanity.com/paper/2412.05185/) (2024)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps](https://mlsanity.com/paper/2503.18223/) (2025)
- [HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator](https://mlsanity.com/paper/2411.17261/) (2024)
- [Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval](https://mlsanity.com/paper/2510.02745/) (2025)
- [StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding](https://mlsanity.com/paper/2512.12560/) (2025)
- [LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding](https://mlsanity.com/paper/2602.20913/) (2026)
- [Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention](https://mlsanity.com/paper/2603.21957/) (2026)
- [SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding](https://mlsanity.com/paper/2510.20622/) (2025)
- [Mitigating Semantic Collapse in Partially Relevant Video Retrieval](https://mlsanity.com/paper/2510.27432/) (2025)
- [Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models](https://mlsanity.com/paper/2603.01400/) (2026)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking](https://mlsanity.com/paper/2606.01113/) (2026)
- [DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval](https://mlsanity.com/paper/2506.08887/) (2025)
- [AdaTP: Attention-Debiased Token Pruning for Video Large Language Models](https://mlsanity.com/paper/2505.20100/) (2025)
- [Task-Related Token Compression in Multimodal Large Language Models from an Explainability Perspective](https://mlsanity.com/paper/2506.01097/) (2025)
- [BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance](https://mlsanity.com/paper/2506.03589/) (2025)
- [WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation](https://mlsanity.com/paper/2607.23265/) (2026)
- [TCMA: Text-Conditioned Multi-granularity Alignment for Drone Cross-Modal Text-Video Retrieval](https://mlsanity.com/paper/2510.10180/) (2025)
- [Fast Enough to Act: Spatio-Temporal Visual Token Merging for Low-Latency Robotic VLMs and VLAs](https://mlsanity.com/paper/2606.29350/) (2026)
- [Binding Multiple Modalities via Multimodal Wasserstein Barycenter](https://mlsanity.com/paper/2609.33800/) (2026)
- [CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones](https://mlsanity.com/paper/2509.21764/) (2025)
- [PSTTS: A Plug-and-Play Token Selector for Efficient Event-based Spatio-temporal Representation Learning](https://mlsanity.com/paper/2509.22481/) (2025)

## Abstract (arXiv)

Most text-video retrieval methods utilize the text-image pre-trained models like CLIP as a backbone. These methods process each sampled frame independently by the image encoder, resulting in high computational overhead and limiting practical deployment. Addressing this, we focus on efficient text-video retrieval by tackling two key challenges: 1. From the perspective of trainable parameters, current parameter-efficient fine-tuning methods incur high inference costs; 2. From the perspective of model complexity, current token compression methods are mainly designed for images to reduce spatial redundancy but overlook temporal redundancy in consecutive frames of a video. To tackle these challenges, we propose Temporal Token Merging (TempMe), a parameter-efficient and training-inference efficient text-video retrieval architecture that minimizes trainable parameters and model complexity. Specifically, we introduce a progressive multi-granularity framework. By gradually combining neighboring clips, we reduce spatio-temporal redundancy and enhance temporal modeling across different frames, leading to improved efficiency and performance. Extensive experiments validate the superiority of our TempMe. Compared to previous parameter-efficient text-video retrieval methods, TempMe achieves superior performance with just 0.50M trainable parameters. It significantly reduces output tokens by 95% and GFLOPs by 51%, while achieving a 1.8X speedup and a 4.4% R-Sum improvement. With full fine-tuning, TempMe achieves a significant 7.9% R-Sum improvement, trains 1.57X faster, and utilizes 75.2% GPU memory usage. The code is available at https://github.com/LunarShen/TempMe.