# End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames

arXiv: https://arxiv.org/abs/2311.17241 · HTML: https://mlsanity.com/paper/2311.17241/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 80 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Builds on (most cited first, 30 of 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [BMN: Boundary-Matching Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1907.09702/) (2019)
- [VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks](https://mlsanity.com/paper/2112.06825/) (2021)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)

## Built on by (most cited first, 30 of 47)

- [BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding](https://mlsanity.com/paper/2503.21483/) (2025)
- [MMAD: Multi-label Micro-Action Detection in Videos](https://mlsanity.com/paper/2407.05311/) (2024)
- [Challenges and Trends in Egocentric Vision: A Survey](https://mlsanity.com/paper/2503.15275/) (2025)
- [Adapting Short-Term Transformers for Action Detection in Untrimmed Videos](https://mlsanity.com/paper/2312.01897/) (2023)
- [Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory](https://mlsanity.com/paper/2411.16934/) (2024)
- [Online Micro-gesture Recognition Using Data Augmentation and Spatial-Temporal Attention](https://mlsanity.com/paper/2507.09512/) (2025)
- [OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection](https://mlsanity.com/paper/2502.20361/) (2025)
- [SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning](https://mlsanity.com/paper/2504.00527/) (2025)
- [From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding](https://mlsanity.com/paper/2510.02262/) (2025)
- [From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge](https://mlsanity.com/paper/2511.07049/) (2025)
- [Harnessing Temporal Causality for Advanced Temporal Action Detection](https://mlsanity.com/paper/2407.17792/) (2024)
- [Temporal Action Detection Model Compression by Progressive Block Drop](https://mlsanity.com/paper/2503.16916/) (2025)
- [Zero-shot Action Localization via the Confidence of Large Vision-Language Models](https://mlsanity.com/paper/2410.14340/) (2024)
- [Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models](https://mlsanity.com/paper/2501.13795/) (2025)
- [DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer](https://mlsanity.com/paper/2505.05711/) (2025)
- [MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection](https://mlsanity.com/paper/2511.17929/) (2025)
- [Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning](https://mlsanity.com/paper/2401.04105/) (2024)
- [Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism](https://mlsanity.com/paper/2407.13078/) (2024)
- [TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos](https://mlsanity.com/paper/2503.06526/) (2025)
- [SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding](https://mlsanity.com/paper/2510.13016/) (2025)
- [Grounding-MD: Grounded Video-language Pre-training for Open-World Moment Detection](https://mlsanity.com/paper/2504.14553/) (2025)
- [ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA](https://mlsanity.com/paper/2607.01737/) (2026)
- [MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding](https://mlsanity.com/paper/2607.16284/) (2026)
- [LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos](https://mlsanity.com/paper/2607.25125/) (2026)
- [End-to-End Action Segmentation Transformer](https://mlsanity.com/paper/2503.06316/) (2025)
- [Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization](https://mlsanity.com/paper/2601.21078/) (2026)
- [Exploring High-Order Self-Similarity for Video Understanding](https://mlsanity.com/paper/2604.20760/) (2026)
- [Semi-Supervised Pipe Video Temporal Defect Interval Localization](https://mlsanity.com/paper/2407.15170/) (2024)
- [FDDet: Frequency-Decoupling for Boundary Refinement in Temporal Action Detection](https://mlsanity.com/paper/2504.00647/) (2025)
- [ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization](https://mlsanity.com/paper/2505.17555/) (2025)

## Abstract (arXiv)

Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training. However, due to the memory bottleneck, only models with limited scales and limited data volumes can afford end-to-end training, which inevitably restricts TAD performance. In this paper, we reduce the memory consumption for end-to-end training, and manage to scale up the TAD backbone to 1 billion parameters and the input video to 1,536 frames, leading to significant detection performance. The key to our approach lies in our proposed temporal-informative adapter (TIA), which is a novel lightweight module that reduces training memory. Using TIA, we free the humongous backbone from learning to adapt to the TAD task by only updating the parameters in TIA. TIA also leads to better TAD representation by temporally aggregating context from adjacent frames throughout the backbone. We evaluate our model across four representative datasets. Owing to our efficient design, we are able to train end-to-end on VideoMAEv2-giant and achieve 75.4% mAP on THUMOS14, being the first end-to-end model to outperform the best feature-based methods. Code is available at https://github.com/sming256/AdaTAD.