Scale-Aware Tracking Method with Appearance Feature Filtering and Inter-Frame Continuity.

Visual object tracking is a fundamental task in computer vision that requires estimating the position and scale of a target object in a video sequence. However, scale variation is a difficult challenge that affects the performance and robustness of many trackers, especially those based on the discriminative correlation filter (DCF). Existing scale estimation methods based on multi-scale features are computationally expensive and degrade the real-time performance of the DCF-based tracker, especially in scenarios with restricted computing power. In this paper, we propose a practical and efficient solution that can handle scale changes without using multi-scale features and can be combined with any DCF-based tracker as a plug-in module. We use color name (CN) features and a salient feature to reduce the target appearance model's dimensionality. We then estimate the target scale based on a Gaussian distribution model and introduce global and local scale consistency assumptions to restore the target's scale. We fuse the tracking results with the DCF-based tracker to obtain the new position and scale of the target. We evaluate our method on the benchmark dataset Temple Color 128 and compare it with some popular trackers. Our method achieves competitive accuracy and robustness while significantly reducing the computational cost.

Origin of the ease of association of color names: Comparison between humans and AI.

Rapid evolution of artificial intelligence (AI) based on deep neural networks has resulted in artificial systems such as generative pre-trained transformer 3 (GPT-3), which can generate human-like language. Such a system may provide a novel platform for studying how human perception is related to knowledge and the ability of language generation. We compared the frequency distribution of basic color terms in the answers of human subjects and GPT-3 when both were asked similar questions regarding color names associated with the letters of the alphabet. We found that GPT-3 generated basic color terms at a frequency very similar to that of human non-synaesthetes. A similar frequency was observed when color names associated with numerals were tested indicating that simple co-occurrence of alphabet and color word in the trained dataset cannot explain the results. We suggest that the proposed experimental framework using the latest AI models has the potential to explore the mechanisms of human perception.

Neural responses to rapidly selecting color names with different novelty.

It is well known that different names of color can lead to distinct attractions to people. To study the neural mechanism underlying this phenomenon, an implicit association test task was designed for color names, in which participants were required to select the possible meanings of a Greek phrase from two color names (in Chinese). The behavioral results showed that the participants were more likely to select novel names for long Greek phrases and dates names for short Greek phrases. The EEG results showed that the mean amplitude of N1 was greater for selections of novel color names than selections of dates names for Greek phrases. Meanwhile, the mean amplitude of N3 for novel color names was more negative than that of dates color names. Significant interaction effect of N3 was also found for the four kinds of selections between Greek phrases and Chinese color names. Moreover, a frontal-positive and occipital-negative distribution for scalp topography of N1 was found, while the scalp topography of N3 was opposite as frontal-negative and occipital-positive distribution, suggesting the importance of visual cortex for perception of the color names and prefrontal cortex for integration and decision of selection. In summary, the results here indicated that colors with novel names could easily attract people's attention than colors with dates names, which might shed light on the usage of color names in real life.