# Rethinking the Faster R-CNN Architecture for Temporal Action Localization

arXiv: https://arxiv.org/abs/1804.07667 · HTML: https://mlsanity.com/paper/1804.07667/

## Key facts

- Cited by 194 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2018.

## Built on by (most cited first, 30 of 194)

- [Prompting Visual-Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2112.04478/) (2021)
- [Video Transformer Network](https://mlsanity.com/paper/2102.00719/) (2021)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [Learning Salient Boundary Feature for Anchor-free Temporal Action Localization](https://mlsanity.com/paper/2103.13137/) (2021)
- [End-to-end Temporal Action Detection with Transformer](https://mlsanity.com/paper/2106.10271/) (2021)
- [Relaxed Transformer Decoders for Direct Action Proposal Generation](https://mlsanity.com/paper/2102.01894/) (2021)
- [Temporal Context Aggregation Network for Temporal Action Proposal Refinement](https://mlsanity.com/paper/2103.13141/) (2021)
- [Temporal Alignment Networks for Long-term Video](https://mlsanity.com/paper/2204.02968/) (2022)
- [OadTR: Online Action Detection with Transformers](https://mlsanity.com/paper/2106.11149/) (2021)
- [TALLFormer: Temporal Action Localization with a Long-memory Transformer](https://mlsanity.com/paper/2204.01680/) (2022)
- [Object-Region Video Transformers](https://mlsanity.com/paper/2110.06915/) (2021)
- [CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning](https://mlsanity.com/paper/2103.16392/) (2021)
- [UnLoc: A Unified Framework for Video Localization Tasks](https://mlsanity.com/paper/2308.11062/) (2023)
- [Generic Event Boundary Detection: A Benchmark for Event Segmentation](https://mlsanity.com/paper/2101.10511/) (2021)
- [Enriching Local and Global Contexts for Temporal Action Localization](https://mlsanity.com/paper/2107.12960/) (2021)
- [FineAction: A Fine-Grained Video Dataset for Temporal Action Localization](https://mlsanity.com/paper/2105.11107/) (2021)
- [Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering](https://mlsanity.com/paper/2105.13353/) (2021)
- [Activity Graph Transformer for Temporal Action Localization](https://mlsanity.com/paper/2101.08540/) (2021)
- [ReAct: Temporal Action Detection with Relational Queries](https://mlsanity.com/paper/2207.07097/) (2022)
- [Implicit Temporal Modeling with Learnable Alignment for Video Recognition](https://mlsanity.com/paper/2304.10465/) (2023)
- [A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2101.00545/) (2021)
- [Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/2108.05029/) (2021)
- [ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2203.15187/) (2022)
- [An Empirical Study of End-to-End Temporal Action Detection](https://mlsanity.com/paper/2204.02932/) (2022)
- [Self-Supervised Learning for Semi-Supervised Temporal Action Proposal](https://mlsanity.com/paper/2104.03214/) (2021)
- [VidChapters-7M: Video Chapters at Scale](https://mlsanity.com/paper/2309.13952/) (2023)
- [Weakly Supervised Temporal Adjacent Network for Language Grounding](https://mlsanity.com/paper/2106.16136/) (2021)
- [Class Semantics-based Attention for Action Detection](https://mlsanity.com/paper/2109.02613/) (2021)
- [DCAN: Improving Temporal Action Detection via Dual Context Aggregation](https://mlsanity.com/paper/2112.03612/) (2021)
- [Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding](https://mlsanity.com/paper/2203.02966/) (2022)

## Abstract (arXiv)

We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key shortcomings of existing approaches: (1) we improve receptive field alignment using a multi-scale architecture that can accommodate extreme variation in action durations; (2) we better exploit the temporal context of actions for both proposal generation and action classification by appropriately extending receptive fields; and (3) we explicitly consider multi-stream feature fusion and demonstrate that fusing motion late is important. We achieve state-of-the-art performance for both action proposal and localization on THUMOS'14 detection benchmark and competitive performance on ActivityNet challenge.