# Efficient Video Action Detection with Token Dropout and Context Refinement

arXiv: https://arxiv.org/abs/2304.08451 · HTML: https://mlsanity.com/paper/2304.08451/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 67 references that are in the map.
- First posted on arXiv 17 Apr 2023.

## Builds on (most cited first, 30 of 57)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [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)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [Rethinking Spatial Dimensions of Vision Transformers](https://mlsanity.com/paper/2103.16302/) (2021)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [Adaptive Token Sampling For Efficient Vision Transformers](https://mlsanity.com/paper/2111.15667/) (2021)
- [All Tokens Matter: Token Labeling for Training Better Vision Transformers](https://mlsanity.com/paper/2104.10858/) (2021)
- [AdaFrame: Adaptive Frame Selection for Fast Video Recognition](https://mlsanity.com/paper/1811.12432/) (2018)
- [SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition](https://mlsanity.com/paper/1904.04289/) (2019)
- [Compressed Video Action Recognition](https://mlsanity.com/paper/1712.00636/) (2017)

## Built on by (most cited first, 20 of 20)

- [Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality](https://mlsanity.com/paper/2505.18227/) (2025)
- [CAT: Content-Adaptive Image Tokenization](https://mlsanity.com/paper/2501.03120/) (2025)
- [OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence](https://mlsanity.com/paper/2602.08683/) (2026)
- [Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection](https://mlsanity.com/paper/2411.10922/) (2024)
- [MOVE: Motion-Guided Few-Shot Video Object Segmentation](https://mlsanity.com/paper/2507.22061/) (2025)
- [A Survey on Deep Learning-based Spatio-temporal Action Detection](https://mlsanity.com/paper/2308.01618/) (2023)
- [Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies](https://mlsanity.com/paper/2410.08860/) (2024)
- [A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion](https://mlsanity.com/paper/2501.07451/) (2025)
- [Multiscale Vision Transformers meet Bipartite Matching for efficient single-stage Action Localization](https://mlsanity.com/paper/2312.17686/) (2023)
- [SFMViT: SlowFast Meet ViT in Chaotic World](https://mlsanity.com/paper/2404.16609/) (2024)
- [PO-GUISE+: Pose and object guided transformer token selection for efficient driver action recognition](https://mlsanity.com/paper/2407.13750/) (2024)
- [Video, How Do Your Tokens Merge?](https://mlsanity.com/paper/2506.03885/) (2025)
- [Classification Matters: Improving Video Action Detection with Class-Specific Attention](https://mlsanity.com/paper/2407.19698/) (2024)
- [JARViS: Detecting Actions in Video Using Unified Actor-Scene Context Relation Modeling](https://mlsanity.com/paper/2408.03612/) (2024)
- [JoVALE: Detecting Human Actions in Video Using Audiovisual and Language Contexts](https://mlsanity.com/paper/2412.13708/) (2024)
- [Action tube generation by person query matching for spatio-temporal action detection](https://mlsanity.com/paper/2503.12969/) (2025)
- [Scaling Open-Vocabulary Action Detection](https://mlsanity.com/paper/2504.03096/) (2025)
- [Towards an Effective Action-Region Tracking Framework for Fine-grained Video Action Recognition](https://mlsanity.com/paper/2511.21202/) (2025)
- [Meaningful Moments: A Corpus of VLM-Derived Temporal Importance Labels for Video Action Recognition](https://mlsanity.com/paper/2610.16009/) (2026)
- [Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs](https://mlsanity.com/paper/2610.18858/) (2026)

## Abstract (arXiv)

Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor identification. In this work, we propose an end-to-end framework for efficient video action detection (EVAD) based on vanilla ViTs. Our EVAD consists of two specialized designs for video action detection. First, we propose a spatiotemporal token dropout from a keyframe-centric perspective. In a video clip, we maintain all tokens from its keyframe, preserve tokens relevant to actor motions from other frames, and drop out the remaining tokens in this clip. Second, we refine scene context by leveraging remaining tokens for better recognizing actor identities. The region of interest (RoI) in our action detector is expanded into temporal domain. The captured spatiotemporal actor identity representations are refined via scene context in a decoder with the attention mechanism. These two designs make our EVAD efficient while maintaining accuracy, which is validated on three benchmark datasets (i.e., AVA, UCF101-24, JHMDB). Compared to the vanilla ViT backbone, our EVAD reduces the overall GFLOPs by 43% and improves real-time inference speed by 40% with no performance degradation. Moreover, even at similar computational costs, our EVAD can improve the performance by 1.1 mAP with higher resolution inputs. Code is available at https://github.com/MCG-NJU/EVAD.