# Boundary-Denoising for Video Activity Localization

arXiv: https://arxiv.org/abs/2304.02934 · HTML: https://mlsanity.com/paper/2304.02934/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 72 references that are in the map.
- First posted on arXiv 6 Apr 2023.

## Builds on (most cited first, 30 of 46)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [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)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [BMN: Boundary-Matching Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1907.09702/) (2019)
- [Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language](https://mlsanity.com/paper/1912.03590/) (2019)
- [Video Transformer Network](https://mlsanity.com/paper/2102.00719/) (2021)
- [BSN: Boundary Sensitive Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1806.02964/) (2018)
- [Temporal Action Detection with Structured Segment Networks](https://mlsanity.com/paper/1704.06228/) (2017)
- [G-TAD: Sub-Graph Localization for Temporal Action Detection](https://mlsanity.com/paper/1911.11462/) (2019)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval](https://mlsanity.com/paper/2001.09099/) (2020)
- [Local-Global Video-Text Interactions for Temporal Grounding](https://mlsanity.com/paper/2004.07514/) (2020)
- [Dense Regression Network for Video Grounding](https://mlsanity.com/paper/2004.03545/) (2020)
- [Learning Salient Boundary Feature for Anchor-free Temporal Action Localization](https://mlsanity.com/paper/2103.13137/) (2021)
- [UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2203.12745/) (2022)
- [Relaxed Transformer Decoders for Direct Action Proposal Generation](https://mlsanity.com/paper/2102.01894/) (2021)
- [CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos](https://mlsanity.com/paper/1703.01515/) (2017)
- [MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions](https://mlsanity.com/paper/2112.00431/) (2021)
- [Video Self-Stitching Graph Network for Temporal Action Localization](https://mlsanity.com/paper/2011.14598/) (2020)
- [Interventional Video Grounding with Dual Contrastive Learning](https://mlsanity.com/paper/2106.11013/) (2021)
- [MAC: Mining Activity Concepts for Language-based Temporal Localization](https://mlsanity.com/paper/1811.08925/) (2018)

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

- [VideoLLM: Modeling Video Sequence with Large Language Models](https://mlsanity.com/paper/2305.13292/) (2023)
- [A Survey on Deep Learning-based Spatio-temporal Action Detection](https://mlsanity.com/paper/2308.01618/) (2023)
- [Multi-Scale Contrastive Learning for Video Temporal Grounding](https://mlsanity.com/paper/2412.07157/) (2024)
- [The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning](https://mlsanity.com/paper/2501.07305/) (2025)
- [DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2308.15109/) (2023)
- [ResidualViT for Efficient Temporally Dense Video Encoding](https://mlsanity.com/paper/2509.13255/) (2025)
- [Enhance Multi-Scale Spatial-Temporal Coherence for Configurable Video Anomaly Detection](https://mlsanity.com/paper/2305.07328/) (2023)
- [PESFormer: Boosting Macro- and Micro-expression Spotting with Direct Timestamp Encoding](https://mlsanity.com/paper/2410.18695/) (2024)
- [OZ-TAL: Online Zero-Shot Temporal Action Localization](https://mlsanity.com/paper/2605.09976/) (2026)
- [Inconsistency-aware Multimodal Schr"odinger Bridge for Deepfake Localization](https://mlsanity.com/paper/2605.23113/) (2026)

## Abstract (arXiv)

Video activity localization aims at understanding the semantic content in long untrimmed videos and retrieving actions of interest. The retrieved action with its start and end locations can be used for highlight generation, temporal action detection, etc. Unfortunately, learning the exact boundary location of activities is highly challenging because temporal activities are continuous in time, and there are often no clear-cut transitions between actions. Moreover, the definition of the start and end of events is subjective, which may confuse the model. To alleviate the boundary ambiguity, we propose to study the video activity localization problem from a denoising perspective. Specifically, we propose an encoder-decoder model named DenoiseLoc. During training, a set of action spans is randomly generated from the ground truth with a controlled noise scale. Then we attempt to reverse this process by boundary denoising, allowing the localizer to predict activities with precise boundaries and resulting in faster convergence speed. Experiments show that DenoiseLoc advances %in several video activity understanding tasks. For example, we observe a gain of +12.36% average mAP on QV-Highlights dataset and +1.64% mAP@0.5 on THUMOS'14 dataset over the baseline. Moreover, DenoiseLoc achieves state-of-the-art performance on TACoS and MAD datasets, but with much fewer predictions compared to other current methods.