# DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos

arXiv: https://arxiv.org/abs/2505.16376 · HTML: https://mlsanity.com/paper/2505.16376/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 61 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 30 of 44)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language](https://mlsanity.com/paper/1912.03590/) (2019)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [Span-based Localizing Network for Natural Language Video Localization](https://mlsanity.com/paper/2004.13931/) (2020)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [UniVTG: Towards Unified Video-Language Temporal Grounding](https://mlsanity.com/paper/2307.16715/) (2023)
- [Dense Regression Network for Video Grounding](https://mlsanity.com/paper/2004.03545/) (2020)
- [MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions](https://mlsanity.com/paper/2112.00431/) (2021)
- [MAC: Mining Activity Concepts for Language-based Temporal Localization](https://mlsanity.com/paper/1811.08925/) (2018)
- [Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction](https://mlsanity.com/paper/1909.05010/) (2019)
- [TALLFormer: Temporal Action Localization with a Long-memory Transformer](https://mlsanity.com/paper/2204.01680/) (2022)
- [Enriching Local and Global Contexts for Temporal Action Localization](https://mlsanity.com/paper/2107.12960/) (2021)
- [NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory](https://mlsanity.com/paper/2301.00746/) (2023)
- [A Content-Driven Micro-Video Recommendation Dataset at Scale](https://mlsanity.com/paper/2309.15379/) (2023)
- [SnAG: Scalable and Accurate Video Grounding](https://mlsanity.com/paper/2404.02257/) (2024)
- [Tripping through time: Efficient Localization of Activities in Videos](https://mlsanity.com/paper/1904.09936/) (2019)
- [Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2401.00901/) (2023)
- [Helping Hands: An Object-Aware Ego-Centric Video Recognition Model](https://mlsanity.com/paper/2308.07918/) (2023)
- [CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding](https://mlsanity.com/paper/2209.10918/) (2022)
- [Localizing Moments in Long Video Via Multimodal Guidance](https://mlsanity.com/paper/2302.13372/) (2023)
- [Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos](https://mlsanity.com/paper/2303.08345/) (2023)
- [ViGT: Proposal-free Video Grounding with Learnable Token in Transformer](https://mlsanity.com/paper/2308.06009/) (2023)

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

- [HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling](https://mlsanity.com/paper/2510.23043/) (2025)
- [STORM: End-to-End Referring Multi-Object Tracking in Videos](https://mlsanity.com/paper/2604.10527/) (2026)
- [ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency](https://mlsanity.com/paper/2606.25317/) (2026)
- [UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding](https://mlsanity.com/paper/2604.08522/) (2026)
- [Interactive Episodic Memory with User Feedback](https://mlsanity.com/paper/2604.24893/) (2026)

## Abstract (arXiv)

Long Video Temporal Grounding (LVTG) aims at identifying specific moments within lengthy videos based on user-provided text queries for effective content retrieval. The approach taken by existing methods of dividing video into clips and processing each clip via a full-scale expert encoder is challenging to scale due to prohibitive computational costs of processing a large number of clips in long videos. To address this issue, we introduce DeCafNet, an approach employing ``delegate-and-conquer'' strategy to achieve computation efficiency without sacrificing grounding performance. DeCafNet introduces a sidekick encoder that performs dense feature extraction over all video clips in a resource-efficient manner, while generating a saliency map to identify the most relevant clips for full processing by the expert encoder. To effectively leverage features from sidekick and expert encoders that exist at different temporal resolutions, we introduce DeCaf-Grounder, which unifies and refines them via query-aware temporal aggregation and multi-scale temporal refinement for accurate grounding. Experiments on two LTVG benchmark datasets demonstrate that DeCafNet reduces computation by up to 47% while still outperforming existing methods, establishing a new state-of-the-art for LTVG in terms of both efficiency and performance. Our code is available at https://github.com/ZijiaLewisLu/CVPR2025-DeCafNet.