# Cascaded Boundary Regression for Temporal Action Detection

arXiv: https://arxiv.org/abs/1705.01180 · HTML: https://mlsanity.com/paper/1705.01180/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2017.

## Built on by (most cited first, 30 of 35)

- [Learning Salient Boundary Feature for Anchor-free Temporal Action Localization](https://mlsanity.com/paper/2103.13137/) (2021)
- [Generic Event Boundary Detection: A Benchmark for Event Segmentation](https://mlsanity.com/paper/2101.10511/) (2021)
- [FineAction: A Fine-Grained Video Dataset for Temporal Action Localization](https://mlsanity.com/paper/2105.11107/) (2021)
- [Self-Supervised Learning for Semi-Supervised Temporal Action Proposal](https://mlsanity.com/paper/2104.03214/) (2021)
- [Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation](https://mlsanity.com/paper/2107.11443/) (2021)
- [Class Semantics-based Attention for Action Detection](https://mlsanity.com/paper/2109.02613/) (2021)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [Graph Convolutional Module for Temporal Action Localization in Videos](https://mlsanity.com/paper/2112.00302/) (2021)
- [Support-Set Based Cross-Supervision for Video Grounding](https://mlsanity.com/paper/2108.10576/) (2021)
- [C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation](https://mlsanity.com/paper/2212.11078/) (2022)
- [SVIP: Sequence VerIfication for Procedures in Videos](https://mlsanity.com/paper/2112.06447/) (2021)
- [AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation](https://mlsanity.com/paper/2210.02578/) (2022)
- [AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation](https://mlsanity.com/paper/2110.11474/) (2021)
- [Structured Attention Composition for Temporal Action Localization](https://mlsanity.com/paper/2205.09956/) (2022)
- [A Survey on Natural Language Video Localization](https://mlsanity.com/paper/2104.00234/) (2021)
- [Discerning Generic Event Boundaries in Long-Form Wild Videos](https://mlsanity.com/paper/2106.10090/) (2021)
- [Towards High-Quality Temporal Action Detection with Sparse Proposals](https://mlsanity.com/paper/2109.08847/) (2021)
- [Learning to Combine the Modalities of Language and Video for Temporal Moment Localization](https://mlsanity.com/paper/2109.02925/) (2021)
- [Motion Aware Self-Supervision for Generic Event Boundary Detection](https://mlsanity.com/paper/2210.05574/) (2022)
- [Temporal Segment Transformer for Action Segmentation](https://mlsanity.com/paper/2302.13074/) (2023)
- [Pyramid Region-based Slot Attention Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/2206.10095/) (2022)
- [Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021](https://mlsanity.com/paper/2107.12618/) (2021)
- [Graph Convolution Neural Network For Weakly Supervised Abnormality Localization In Long Capsule Endoscopy Videos](https://mlsanity.com/paper/2110.09110/) (2021)
- [Temporal Action Localization with Multi-temporal Scales](https://mlsanity.com/paper/2208.07493/) (2022)
- [POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization](https://mlsanity.com/paper/2310.13585/) (2023)
- [Bridging the gap between Human Action Recognition and Online Action Detection](https://mlsanity.com/paper/2101.08851/) (2021)
- [Few-Shot Action Localization without Knowing Boundaries](https://mlsanity.com/paper/2106.04150/) (2021)
- [Multi-Modulation Network for Audio-Visual Event Localization](https://mlsanity.com/paper/2108.11773/) (2021)
- [Adaptive Perception Transformer for Temporal Action Localization](https://mlsanity.com/paper/2208.11908/) (2022)
- [Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos](https://mlsanity.com/paper/2208.12940/) (2022)

## Abstract (arXiv)

Temporal action detection in long videos is an important problem. State-of-the-art methods address this problem by applying action classifiers on sliding windows. Although sliding windows may contain an identifiable portion of the actions, they may not necessarily cover the entire action instance, which would lead to inferior performance. We adapt a two-stage temporal action detection pipeline with Cascaded Boundary Regression (CBR) model. Class-agnostic proposals and specific actions are detected respectively in the first and the second stage. CBR uses temporal coordinate regression to refine the temporal boundaries of the sliding windows. The salient aspect of the refinement process is that, inside each stage, the temporal boundaries are adjusted in a cascaded way by feeding the refined windows back to the system for further boundary refinement. We test CBR on THUMOS-14 and TVSeries, and achieve state-of-the-art performance on both datasets. The performance gain is especially remarkable under high IoU thresholds, e.g. map@tIoU=0.5 on THUMOS-14 is improved from 19.0% to 31.0%.