# Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors

arXiv: https://arxiv.org/abs/1505.04868 · HTML: https://mlsanity.com/paper/1505.04868/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2015.

## Built on by (most cited first, 30 of 58)

- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions](https://mlsanity.com/paper/2105.07404/) (2021)
- [Group-aware Contrastive Regression for Action Quality Assessment](https://mlsanity.com/paper/2108.07797/) (2021)
- [Activity Graph Transformer for Temporal Action Localization](https://mlsanity.com/paper/2101.08540/) (2021)
- [MGMAE: Motion Guided Masking for Video Masked Autoencoding](https://mlsanity.com/paper/2308.10794/) (2023)
- [TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2112.03587/) (2021)
- [Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition](https://mlsanity.com/paper/2112.09690/) (2021)
- [MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations](https://mlsanity.com/paper/2403.10943/) (2024)
- [Hypergraph-based Multi-View Action Recognition using Event Cameras](https://mlsanity.com/paper/2403.19316/) (2024)
- [When Video Classification Meets Incremental Classes](https://mlsanity.com/paper/2106.15827/) (2021)
- [EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding](https://mlsanity.com/paper/2309.02423/) (2023)
- [Deep Unsupervised Key Frame Extraction for Efficient Video Classification](https://mlsanity.com/paper/2211.06742/) (2022)
- [Spatio-Temporal Attention and Gaussian Processes for Personalized Video Gaze Estimation](https://mlsanity.com/paper/2404.05215/) (2024)
- [Human Activity Recognition Using Tools of Convolutional Neural Networks: A State of the Art Review, Data Sets, Challenges and Future Prospects](https://mlsanity.com/paper/2202.03274/) (2022)
- [Continuous Human Action Recognition for Human-Machine Interaction: A Review](https://mlsanity.com/paper/2202.13096/) (2022)
- [TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction](https://mlsanity.com/paper/2210.14714/) (2022)
- [Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure](https://mlsanity.com/paper/2104.05758/) (2021)
- [A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation](https://mlsanity.com/paper/2312.05830/) (2023)
- [A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities](https://mlsanity.com/paper/2408.05436/) (2024)
- [Vision-based Human Fall Detection Systems using Deep Learning: A Review](https://mlsanity.com/paper/2207.10952/) (2022)
- [Video-based Human Action Recognition using Deep Learning: A Review](https://mlsanity.com/paper/2208.03775/) (2022)
- [Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition](https://mlsanity.com/paper/2508.03695/) (2025)
- [Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval](https://mlsanity.com/paper/2101.00820/) (2021)
- [CyclingNet: Detecting cycling near misses from video streams in complex urban scenes with deep learning](https://mlsanity.com/paper/2102.00565/) (2021)
- [Programmatic Concept Learning for Human Motion Description and Synthesis](https://mlsanity.com/paper/2206.13502/) (2022)
- [Learning Discriminative Representations for Multi-Label Image Recognition](https://mlsanity.com/paper/2107.11159/) (2021)
- [SkateboardAI: The Coolest Video Action Recognition for Skateboarding](https://mlsanity.com/paper/2311.11467/) (2023)
- [Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal Modeling](https://mlsanity.com/paper/2403.06978/) (2024)
- [Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition](https://mlsanity.com/paper/2411.05692/) (2024)
- [On the Post-hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classification](https://mlsanity.com/paper/2102.08634/) (2021)

## Abstract (arXiv)

Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted features and deep-learned features. Specifically, we utilize deep architectures to learn discriminative convolutional feature maps, and conduct trajectory-constrained pooling to aggregate these convolutional features into effective descriptors. To enhance the robustness of TDDs, we design two normalization methods to transform convolutional feature maps, namely spatiotemporal normalization and channel normalization. The advantages of our features come from (i) TDDs are automatically learned and contain high discriminative capacity compared with those hand-crafted features; (ii) TDDs take account of the intrinsic characteristics of temporal dimension and introduce the strategies of trajectory-constrained sampling and pooling for aggregating deep-learned features. We conduct experiments on two challenging datasets: HMDB51 and UCF101. Experimental results show that TDDs outperform previous hand-crafted features and deep-learned features. Our method also achieves superior performance to the state of the art on these datasets (HMDB51 65.9%, UCF101 91.5%).