Context-Aware RCNN: A Baseline for Action Detection in Videos

Wu, Jian-Chao; Kuang, Zhen‐Bang; Wang, Limin; Zhang, Wayne; Wu, Guorong

doi:10.1007/978-3-030-58595-2_27

Cited by 67 publications

(41 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The object was not clear enough, even though the zoom-in strategy was used. The results in [26,27] indicate that the clarity and resolution of images influences the performance of RCNN-based methods. We may solve this problem by using a high-definition (HD) camera.…”

Section: Effectiveness Of the Proposed Methodsmentioning

confidence: 99%

Vegetable Size Measurement Based on Stereo Camera and Keypoints Detection

Zheng

Sun

Meng

et al. 2022

Sensors

View full text Add to dashboard Cite

This work focuses on the problem of non-contact measurement for vegetables in agricultural automation. The application of computer vision in assisted agricultural production significantly improves work efficiency due to the rapid development of information technology and artificial intelligence. Based on object detection and stereo cameras, this paper proposes an intelligent method for vegetable recognition and size estimation. The method obtains colorful images and depth maps with a binocular stereo camera. Then detection networks classify four kinds of common vegetables (cucumber, eggplant, tomato and pepper) and locate six points for each object. Finally, the size of vegetables is calculated using the pixel position and depth of keypoints. Experimental results show that the proposed method can classify four kinds of common vegetables within 60 cm and accurately estimate their diameter and length. The work provides an innovative idea for solving the vegetable’s non-contact measurement problems and can promote the application of computer vision in agricultural automation.

show abstract

Section: Effectiveness Of the Proposed Methodsmentioning

confidence: 99%

Vegetable Size Measurement Based on Stereo Camera and Keypoints Detection

Zheng

Sun

Meng

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The correlation between the candidate component detections is measured by calculating the line integral on the corresponding PAF along the line segment connecting the position of the candidate component, as described in ( 12) and (13).…”

Section: Letmentioning

confidence: 99%

“…Besides, the human detector may not accurately identify the position of the human body when it is occluded, resulting in missing some of the detected objects. Further, such a mechanism is more likely to cause the loss of detected objects in the blurred part since most of these networks are composed of a series of main networks from high-resolution to low-resolution [13][14].…”

Section: Introductionmentioning

confidence: 99%

Multi-Cascade Perceptual Human Posture Recognition Enhancement Network

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The current researches trend to adopt a low-resolution hot spot map to restore the original highresolution representation to save computing cost, resulting in unsatisfactory detection performance, especially in human body recognition with a highly complex background. Aiming at this problem, we proposed a model of parallel connection of multiple sub-networks with different resolution levels on a high-resolution main network. It can maintain the network structure of a high-resolution hot spot map in the whole operation process. By using this structure in the human key point vector field network, the accuracy of human posture recognition has been improved with high-speed operation. To validate the proposed model's effectiveness, two common benchmark data sets of COCO key point data set and MPII human posture data set are used for evaluation. Experimental results show that our network achieves the accuracy of 72.3% AP and 92.2% AP in the two data sets, respectively, which is 3%-4% higher than those of the existing mainstream researches. In our test, only the accuracy of backbone's SimpleBaseline with ResNet-152 is close to ours, yet our network realized a much lower computing cost.

show abstract

“…There are some attempts to incorporate the spatiotemporal interaction with atomic action detection pipelines [8,30,31]. Nevertheless, they ignore the discrepancy between different contextual interactions.…”

Section: Introductionmentioning

confidence: 99%

LSTC: Boosting Atomic Action Detection with Long-Short-Term Context

Zhang

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

In this paper, we place the atomic action detection problem into a Long-Short Term Context (LSTC) to analyze how the temporal reliance among video signals affect the action detection results. To do this, we decompose the action recognition pipeline into shortterm and long-term reliance, in terms of the hypothesis that the two kinds of context are conditionally independent given the objective action instance. Within our design, a local aggregation branch is utilized to gather dense and informative short-term cues, while a high order long-term inference branch is designed to reason the objective action class from high-order interaction between actor and other person or person pairs. Both branches independently predict the context-specific actions and the results are merged in the end. We demonstrate that both temporal grains are beneficial to atomic action recognition. On the mainstream benchmarks of atomic action detection, our design can bring significant performance gain from the existing state-of-the-art pipeline. CCS CONCEPTS• Computing methodologies → Activity recognition and understanding.

show abstract

Context-Aware RCNN: A Baseline for Action Detection in Videos

Cited by 67 publications

References 34 publications

Vegetable Size Measurement Based on Stereo Camera and Keypoints Detection

Vegetable Size Measurement Based on Stereo Camera and Keypoints Detection

Multi-Cascade Perceptual Human Posture Recognition Enhancement Network

LSTC: Boosting Atomic Action Detection with Long-Short-Term Context

Contact Info

Product

Resources

About