# Human Pose and Action Recognition

**Type:** Topics  
**Canonical URL:** https://scholariq.org/topics/human-pose-and-action-recognition/

## Facts

| Field | Value |
| --- | --- |
| Description | This cluster of papers focuses on the development and application of deep learning techniques for human action recognition and pose estimation. It covers topics such as spatiotemporal feature learning, convolutional networks, 3D human pose estimation, skeleton-based recognition, and video classification. The research aims to advance the understanding and accurate detection of human actions in various environments. |
| Domain | Physical Sciences |
| Field | Computer Science |
| OpenAlex ID | t10812 |
| Works | 185 |

## Topic papers all

Showing 15 of 185.

- [Large-Scale Video Classification with Convolutional Neural Networks](https://scholariq.org/papers/large-scale-video-classification-with-convolutional-neural-networks/)
- [Social LSTM: Human Trajectory Prediction in Crowded Spaces](https://scholariq.org/papers/social-lstm-human-trajectory-prediction-in-crowded-spaces/)
- [On Learning, Representing, and Generalizing a Task in a Humanoid Robot](https://scholariq.org/papers/on-learning-representing-and-generalizing-a-task-in-a-humanoid-robot/)
- [Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis](https://scholariq.org/papers/learning-hierarchical-invariant-spatio-temporal-features-for-action-recognition/)
- [Interactive control of avatars animated with human motion data](https://scholariq.org/papers/interactive-control-of-avatars-animated-with-human-motion-data/)
- [An Analysis Of Convolutional Neural Networks For Image Classification](https://scholariq.org/papers/an-analysis-of-convolutional-neural-networks-for-image-classification/)
- [Sensor-based and vision-based human activity recognition: A comprehensive survey](https://scholariq.org/papers/sensor-based-and-vision-based-human-activity-recognition-a-comprehensive-survey/)
- [Deep Metric Learning: A Survey](https://scholariq.org/papers/deep-metric-learning-a-survey/)
- [A robust human activity recognition system using smartphone sensors and deep learning](https://scholariq.org/papers/a-robust-human-activity-recognition-system-using-smartphone-sensors-and-deep/)
- [End-to-End Learning of Action Detection from Frame Glimpses in Videos](https://scholariq.org/papers/end-to-end-learning-of-action-detection-from-frame-glimpses-in-videos/)
- [Generating Diverse and Natural 3D Human Motions from Text](https://scholariq.org/papers/generating-diverse-and-natural-3d-human-motions-from-text/)
- [VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://scholariq.org/papers/vatex-a-large-scale-high-quality-multilingual-dataset-for-video-and-language/)
- [Interactive control of avatars animated with human motion data](https://scholariq.org/papers/interactive-control-of-avatars-animated-with-human-motion-data-2/)
- [Learning and Reproduction of Gestures by Imitation](https://scholariq.org/papers/learning-and-reproduction-of-gestures-by-imitation/)
- [Synthesizing physically realistic human motion in low-dimensional, behavior-specific spaces](https://scholariq.org/papers/synthesizing-physically-realistic-human-motion-in-low-dimensional-behavior/)

## Topic primary papers

Showing 15 of 69.

- [Large-Scale Video Classification with Convolutional Neural Networks](https://scholariq.org/papers/large-scale-video-classification-with-convolutional-neural-networks/)
- [Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis](https://scholariq.org/papers/learning-hierarchical-invariant-spatio-temporal-features-for-action-recognition/)
- [End-to-End Learning of Action Detection from Frame Glimpses in Videos](https://scholariq.org/papers/end-to-end-learning-of-action-detection-from-frame-glimpses-in-videos/)
- [Generating Diverse and Natural 3D Human Motions from Text](https://scholariq.org/papers/generating-diverse-and-natural-3d-human-motions-from-text/)
- [An Approach to Pose-Based Action Recognition](https://scholariq.org/papers/an-approach-to-pose-based-action-recognition/)
- [Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos](https://scholariq.org/papers/every-moment-counts-dense-detailed-labeling-of-actions-in-complex-videos/)
- [Optimizing Network Structure for 3D Human Pose Estimation](https://scholariq.org/papers/optimizing-network-structure-for-3d-human-pose-estimation/)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://scholariq.org/papers/motionbert-a-unified-perspective-on-learning-human-motion-representations/)
- [Learning Clip Representations for Skeleton-Based 3D Action Recognition](https://scholariq.org/papers/learning-clip-representations-for-skeleton-based-3d-action-recognition/)
- [Human action recognition using fusion of multiview and deep features: an application to video surveillance](https://scholariq.org/papers/human-action-recognition-using-fusion-of-multiview-and-deep-features-an/)
- [Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization](https://scholariq.org/papers/completeness-modeling-and-context-separation-for-weakly-supervised-temporal/)
- [Markerless Motion Capture through Visual Hull, Articulated ICP and Subject Specific Model Generation](https://scholariq.org/papers/markerless-motion-capture-through-visual-hull-articulated-icp-and-subject/)
- [Robust Estimation of 3D Human Poses from a Single Image](https://scholariq.org/papers/robust-estimation-of-3d-human-poses-from-a-single-image/)
- [First Person Action Recognition Using Deep Learned Descriptors](https://scholariq.org/papers/first-person-action-recognition-using-deep-learned-descriptors/)
- [Connectionist Temporal Modeling for Weakly Supervised Action Labeling](https://scholariq.org/papers/connectionist-temporal-modeling-for-weakly-supervised-action-labeling/)

---
Source: ScholarIQ — public research metadata, principally OpenAlex. See https://scholariq.org/sources/ for provenance and https://scholariq.org/methodology/ for what these figures mean.