Related Experiment Video
Updated: Jun 13, 2025
13:13
Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
Published on: March 19, 2021
2.9K
RetinaViT: Efficient Visual Backbone for Online Video Streams
Tomoyuki Suzuki1, Yoshimitsu Aoki1
1Department of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1, Hiyoshi, Kohoku-ku, Yokohama 223-8522, Kanagawa, Japan.
Sensors (Basel, Switzerland)
|September 14, 2024
Summary
RetinaViT enhances online video understanding by efficiently extracting frame-level visual features. This method significantly speeds up tasks like action recognition, improving both accuracy and efficiency.
Area of Science:
- Computer Vision
- Artificial Intelligence
- Machine Learning
Background:
- Online video understanding is critical for many applications.
- Frame-level visual feature extraction is a major bottleneck in video processing.
- Existing methods struggle with real-time inference speed requirements.
Purpose of the Study:
- To propose RetinaViT, an efficient method for online video understanding.
- To enhance the speed and accuracy of frame-level visual feature extraction.
- To improve the overall efficiency of online video understanding tasks.
Main Methods:
- RetinaViT uses approximated Transformer blocks with event tokens as queries.
- It reuses previously processed tokens and restricts keys/values to spatial neighborhoods.
- Model parameters are tuned via multi-step black-box optimization during training.
Main Results:
- RetinaViT significantly improves the speed/accuracy trade-off on various tasks.
- For action recognition, it reduces inference time by up to 61.9% (CPU) and 50.8% (GPU).
- Accuracy is maintained or slightly improved compared to baseline models.
Conclusions:
- RetinaViT offers a substantial efficiency improvement for online video understanding.
- The method effectively addresses the bottleneck of frame-level feature extraction.
- RetinaViT demonstrates practical benefits for real-world video analysis applications.
Related Concept Videos
01:32The Retina
68.0K
The retina is a layer of nervous tissue at the back of the eye that transduces light into neural signals. This process, called phototransduction, is carried out by rod and cone photoreceptor cells in the back of the retina.
68.0K
01:24Vision
53.1K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
53.1K
01:18Reducing Line Loss
150
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
150
01:26Visual System
557
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
557
01:15Depth Perception and Spatial Vision
609
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
609
01:27Uniform Depth Channel Flow
63
Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...
63