# TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection

arXiv: https://arxiv.org/abs/1905.13417 · HTML: https://mlsanity.com/paper/1905.13417/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2019.

## Built on by (most cited first, 30 of 36)

- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions](https://mlsanity.com/paper/2105.07404/) (2021)
- [TubeR: Tubelet Transformer for Video Action Detection](https://mlsanity.com/paper/2104.00969/) (2021)
- [ROAD: The ROad event Awareness Dataset for Autonomous Driving](https://mlsanity.com/paper/2102.11585/) (2021)
- [Unified Graph Structured Models for Video Understanding](https://mlsanity.com/paper/2103.15662/) (2021)
- [Meta-Adapter: An Online Few-shot Learner for Vision-Language Model](https://mlsanity.com/paper/2311.03774/) (2023)
- [Holistic Interaction Transformer Network for Action Detection](https://mlsanity.com/paper/2210.12686/) (2022)
- [DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection](https://mlsanity.com/paper/2207.10909/) (2022)
- [Dynamic Grained Encoder for Vision Transformers](https://mlsanity.com/paper/2301.03831/) (2023)
- [End-to-End Spatio-Temporal Action Localisation with Video Transformers](https://mlsanity.com/paper/2304.12160/) (2023)
- [Proposal Relation Network for Temporal Action Detection](https://mlsanity.com/paper/2106.11812/) (2021)
- [End-to-End Semi-Supervised Learning for Video Action Detection](https://mlsanity.com/paper/2203.04251/) (2022)
- [Spatio-Temporal Action Detection Under Large Motion](https://mlsanity.com/paper/2209.02250/) (2022)
- [MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generation](https://mlsanity.com/paper/2406.18815/) (2024)
- [GrootVL: Tree Topology is All You Need in State Space Model](https://mlsanity.com/paper/2406.02395/) (2024)
- [BoxSnake: Polygonal Instance Segmentation with Box Supervision](https://mlsanity.com/paper/2303.11630/) (2023)
- [Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition](https://mlsanity.com/paper/2106.05058/) (2021)
- [Semi-supervised Active Learning for Video Action Detection](https://mlsanity.com/paper/2312.07169/) (2023)
- [YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection](https://mlsanity.com/paper/2302.06848/) (2023)
- [Relation Modeling in Spatio-Temporal Action Localization](https://mlsanity.com/paper/2106.08061/) (2021)
- [A Survey on Deep Learning-based Spatio-temporal Action Detection](https://mlsanity.com/paper/2308.01618/) (2023)
- [Open-Vocabulary Spatio-Temporal Action Detection](https://mlsanity.com/paper/2405.10832/) (2024)
- [Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling](https://mlsanity.com/paper/2106.11811/) (2021)
- [Identity-aware Graph Memory Network for Action Detection](https://mlsanity.com/paper/2108.11559/) (2021)
- [Context-aware Proposal Network for Temporal Action Detection](https://mlsanity.com/paper/2206.09082/) (2022)
- [RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical Flow](https://mlsanity.com/paper/2209.14408/) (2022)
- [Time and Frequency Network for Human Action Detection in Videos](https://mlsanity.com/paper/2103.04680/) (2021)
- [Point3D: tracking actions as moving points with 3D CNNs](https://mlsanity.com/paper/2203.10584/) (2022)
- [Boosting Semi-Supervised Temporal Action Localization by Learning from Non-Target Classes](https://mlsanity.com/paper/2403.11189/) (2024)
- [A Semantic and Motion-Aware Spatiotemporal Transformer Network for Action Detection](https://mlsanity.com/paper/2405.08204/) (2024)

## Abstract (arXiv)

Current state-of-the-art approaches for spatio-temporal action detection have achieved impressive results but remain unsatisfactory for temporal extent detection. The main reason comes from that, there are some ambiguous states similar to the real actions which may be treated as target actions even by a well-trained network. In this paper, we define these ambiguous samples as "transitional states", and propose a Transition-Aware Context Network (TACNet) to distinguish transitional states. The proposed TACNet includes two main components, i.e., temporal context detector and transition-aware classifier. The temporal context detector can extract long-term context information with constant time complexity by constructing a recurrent network. The transition-aware classifier can further distinguish transitional states by classifying action and transitional states simultaneously. Therefore, the proposed TACNet can substantially improve the performance of spatio-temporal action detection. We extensively evaluate the proposed TACNet on UCF101-24 and J-HMDB datasets. The experimental results demonstrate that TACNet obtains competitive performance on JHMDB and significantly outperforms the state-of-the-art methods on the untrimmed UCF101-24 in terms of both frame-mAP and video-mAP.