# TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks

arXiv: https://arxiv.org/abs/2011.11479 · HTML: https://mlsanity.com/paper/2011.11479/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 30 of 77)

- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Perception Test: A Diagnostic Benchmark for Multimodal Video Models](https://mlsanity.com/paper/2305.13786/) (2023)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [UniVTG: Towards Unified Video-Language Temporal Grounding](https://mlsanity.com/paper/2307.16715/) (2023)
- [End-to-end Temporal Action Detection with Transformer](https://mlsanity.com/paper/2106.10271/) (2021)
- [TriDet: Temporal Action Detection with Relative Boundary Modeling](https://mlsanity.com/paper/2303.07347/) (2023)
- [Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning](https://mlsanity.com/paper/2402.11435/) (2024)
- [UnLoc: A Unified Framework for Video Localization Tasks](https://mlsanity.com/paper/2308.11062/) (2023)
- [LocVTP: Video-Text Pre-training for Temporal Localization](https://mlsanity.com/paper/2207.10362/) (2022)
- [An Empirical Study of End-to-End Temporal Action Detection](https://mlsanity.com/paper/2204.02932/) (2022)
- [Spotting Temporally Precise, Fine-Grained Events in Video](https://mlsanity.com/paper/2207.10213/) (2022)
- [Class Semantics-based Attention for Action Detection](https://mlsanity.com/paper/2109.02613/) (2021)
- [Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2107.12589/) (2021)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding](https://mlsanity.com/paper/2406.07471/) (2024)
- [Unsupervised Pre-training for Temporal Action Localization Tasks](https://mlsanity.com/paper/2203.13609/) (2022)
- [Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts](https://mlsanity.com/paper/2104.06779/) (2021)
- [TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization](https://mlsanity.com/paper/2303.09055/) (2023)
- [RCL: Recurrent Continuous Localization for Temporal Action Detection](https://mlsanity.com/paper/2203.07112/) (2022)
- [Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization](https://mlsanity.com/paper/2106.14118/) (2021)
- [Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization](https://mlsanity.com/paper/2103.15233/) (2021)
- [Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization](https://mlsanity.com/paper/2211.14053/) (2022)
- [DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion](https://mlsanity.com/paper/2303.14863/) (2023)
- [DyFADet: Dynamic Feature Aggregation for Temporal Action Detection](https://mlsanity.com/paper/2407.03197/) (2024)
- [SVIP: Sequence VerIfication for Procedures in Videos](https://mlsanity.com/paper/2112.06447/) (2021)
- [UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection](https://mlsanity.com/paper/2404.04933/) (2024)
- [VideoGLUE: Video General Understanding Evaluation of Foundation Models](https://mlsanity.com/paper/2307.03166/) (2023)
- [TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression](https://mlsanity.com/paper/2404.02405/) (2024)
- [Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach](https://mlsanity.com/paper/2106.11549/) (2021)
- [Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2212.09335/) (2022)

## Abstract (arXiv)

Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracted from video encoders typically trained for trimmed action classification tasks, making such features not necessarily suitable for temporal localization. In this work, we propose a novel supervised pretraining paradigm for clip features that not only trains to classify activities but also considers background clips and global video information to improve temporal sensitivity. Extensive experiments show that using features trained with our novel pretraining strategy significantly improves the performance of recent state-of-the-art methods on three tasks: Temporal Action Localization, Action Proposal Generation, and Dense Video Captioning. We also show that our pretraining approach is effective across three encoder architectures and two pretraining datasets. We believe video feature encoding is an important building block for localization algorithms, and extracting temporally-sensitive features should be of paramount importance in building more accurate models. The code and pretrained models are available on our project website.