Recent Progress in Appearance-based Action Recognition
- URL: http://arxiv.org/abs/2011.12619v1
- Date: Wed, 25 Nov 2020 10:18:12 GMT
- Title: Recent Progress in Appearance-based Action Recognition
- Authors: Jack Humphreys, Zhe Chen, and Dacheng Tao
- Abstract summary: Action recognition is a task to identify various human actions in a video.
Recent appearance-based methods have achieved promising progress towards accurate action recognition.
- Score: 73.6405863243707
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Action recognition, which is formulated as a task to identify various human
actions in a video, has attracted increasing interest from computer vision
researchers due to its importance in various applications. Recently,
appearance-based methods have achieved promising progress towards accurate
action recognition. In general, these methods mainly fulfill the task by
applying various schemes to model spatial and temporal visual information
effectively. To better understand the current progress of appearance-based
action recognition, we provide a comprehensive review of recent achievements in
this area. In particular, we summarise and discuss several dozens of related
research papers, which can be roughly divided into four categories according to
different appearance modelling strategies. The obtained categories include 2D
convolutional methods, 3D convolutional methods, motion representation-based
methods, and context representation-based methods. We analyse and discuss
representative methods from each category, comprehensively. Empirical results
are also summarised to better illustrate cutting-edge algorithms. We conclude
by identifying important areas for future research gleaned from our
categorisation.
Related papers
- Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks [9.388897214344572]
Three-dimensional (3D) reconstruction from two-dimensional images is an active research field in computer vision.
Traditionally, parametric techniques have been employed for this task.
Recent advancements have seen a shift towards learning-based methods.
arXiv Detail & Related papers (2024-08-29T11:16:34Z) - A Comprehensive Review of Few-shot Action Recognition [64.47305887411275]
Few-shot action recognition aims to address the high cost and impracticality of manually labeling complex and variable video data.
It requires accurately classifying human actions in videos using only a few labeled examples per class.
arXiv Detail & Related papers (2024-07-20T03:53:32Z) - A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models [22.522156479335706]
This paper conducts the first large-scale empirical study to compare the performance of existing state-of-the-art fairness improving techniques.
Our findings reveal substantial variations in the performance of each method across different datasets and sensitive attributes.
Different fairness evaluation metrics, due to their distinct focuses, yield significantly different assessment results.
arXiv Detail & Related papers (2024-01-08T06:53:33Z) - Better Understanding Differences in Attribution Methods via Systematic Evaluations [57.35035463793008]
Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions.
We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods.
We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models.
arXiv Detail & Related papers (2023-03-21T14:24:58Z) - Towards Better Understanding Attribution Methods [77.1487219861185]
Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions.
We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods.
We also propose a post-processing smoothing step that significantly improves the performance of some attribution methods.
arXiv Detail & Related papers (2022-05-20T20:50:17Z) - Evaluation of Self-taught Learning-based Representations for Facial
Emotion Recognition [62.30451764345482]
This work describes different strategies to generate unsupervised representations obtained through the concept of self-taught learning for facial emotion recognition.
The idea is to create complementary representations promoting diversity by varying the autoencoders' initialization, architecture, and training data.
Experimental results on Jaffe and Cohn-Kanade datasets using a leave-one-subject-out protocol show that FER methods based on the proposed diverse representations compare favorably against state-of-the-art approaches.
arXiv Detail & Related papers (2022-04-26T22:48:15Z) - Continuous Human Action Recognition for Human-Machine Interaction: A
Review [39.593687054839265]
Recognising actions within an input video are challenging but necessary tasks for applications that require real-time human-machine interaction.
We provide on the feature extraction and learning strategies that are used on most state-of-the-art methods.
We investigate the application of such models to real-world scenarios and discuss several limitations and key research directions.
arXiv Detail & Related papers (2022-02-26T09:25:44Z) - Deep Gait Recognition: A Survey [15.47582611826366]
Gait recognition is an appealing biometric modality which aims to identify individuals based on the way they walk.
Deep learning has reshaped the research landscape in this area since 2015 through the ability to automatically learn discriminative representations.
We present a comprehensive overview of breakthroughs and recent developments in gait recognition with deep learning.
arXiv Detail & Related papers (2021-02-18T18:49:28Z) - A Grid-based Representation for Human Action Recognition [12.043574473965318]
Human action recognition (HAR) in videos is a fundamental research topic in computer vision.
We propose a novel method for action recognition that encodes efficiently the most discriminative appearance information of an action.
Our method is tested on several benchmark datasets demonstrating that our model can accurately recognize human actions.
arXiv Detail & Related papers (2020-10-17T18:25:00Z) - Delving into 3D Action Anticipation from Streaming Videos [99.0155538452263]
Action anticipation aims to recognize the action with a partial observation.
We introduce several complementary evaluation metrics and present a basic model based on frame-wise action classification.
We also explore multi-task learning strategies by incorporating auxiliary information from two aspects: the full action representation and the class-agnostic action label.
arXiv Detail & Related papers (2019-06-15T10:30:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.