Action Recognition

866 papers with code • 49 benchmarks • 104 datasets

Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.

In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.

Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.

Libraries

Use these libraries to find Action Recognition models and implementations
20 papers
3,836
10 papers
2,941
4 papers
547
See all 7 libraries.

Latest papers with no code

Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects

no code yet • 25 Mar 2024

We interact with the world with our hands and see it through our own (egocentric) perspective.

Emotion Recognition from the perspective of Activity Recognition

no code yet • 24 Mar 2024

In this paper, we treat emotion recognition from the perspective of action recognition by exploring the application of deep learning architectures specifically designed for action recognition, for continuous affect recognition.

Hierarchical NeuroSymbolic Approach for Action Quality Assessment

no code yet • 20 Mar 2024

Action quality assessment (AQA) applies computer vision to quantitatively assess the performance or execution of a human action.

Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition

no code yet • 19 Mar 2024

Global obfuscation hides privacy sensitive regions, but also contextual regions important for action recognition.

ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More

no code yet • 19 Mar 2024

Then, we propose a conceptual reasoning-based uncertainty estimation module, which simulates the recognition process to enrich the semantic representation.

VideoBadminton: A Video Dataset for Badminton Action Recognition

no code yet • 19 Mar 2024

In this paper, we introduce the VideoBadminton dataset derived from high-quality badminton footage.

Multi-View Video-Based Learning: Leveraging Weak Labels for Frame-Level Perception

no code yet • 18 Mar 2024

In this paper, we propose a novel learning framework, where the weak labels are first used to train a multi-view video-based base model, which is subsequently used for downstream frame-level perception tasks.

A Survey of IMU Based Cross-Modal Transfer Learning in Human Activity Recognition

no code yet • 17 Mar 2024

We also distinguish and expound on many related but inconsistently used terms in the literature, such as transfer learning, domain adaptation, representation learning, sensor fusion, and multimodal learning, and describe how cross-modal learning fits with all these concepts.

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

no code yet • 15 Mar 2024

Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e. g., joint location), and may suffer from local information loss and low generalization ability.

Skeleton-Based Human Action Recognition with Noisy Labels

no code yet • 15 Mar 2024

In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark.