Yancheng Cai

Evaluating Quality Metrics Through the Lenses of Psychophysical Measurements of Low-Level Vision

Dounia Hammou, Yancheng Cai, Pavan C. Madhusudanarao, Christos G. Bampis et autres

Image and video quality metrics, such as SSIM, LPIPS, and VMAF, aim to predict perceived visual quality and are often assumed to reflect principles of human vision. However, relatively few metrics explicitly incorporate models of human perception, with most relying on hand-crafted …

gb, us (code pays fourni par la source)

CameraVDP: Perceptual Display Assessment with Uncertainty Estimation via Camera and Visual Difference Prediction

Yancheng Cai, Robert Wanat, Rafał Mantiuk

Accurate measurement of images produced by electronic displays is critical for the evaluation of both traditional and computational displays. Traditional display measurement methods based on sparse radiometric sampling and fitting a model are inadequate for capturing spatially varying display artifacts, as they …

gb, us (code pays fourni par la source)

CameraVDP: Perceptual Display Assessment with Uncertainty Estimation via Camera and Visual Difference Prediction

Yancheng Cai, Robert Wanat, Rafał Mantiuk

Accurate measurement of images produced by electronic displays is critical for the evaluation of both traditional and computational displays. Traditional display measurement methods based on sparse radiometric sampling and fitting a model are inadequate for capturing spatially varying display artifacts, as they …

Do computer vision foundation models learn the low-level characteristics of the human visual system?

Yancheng Cai, Fei Yin, Dounia Hammou, Rafał Mantiuk

Computer vision foundation models, such as DINO or OpenCLIP, are trained in a self-supervised manner on large image datasets. Analogously, substantial evidence suggests that the human visual system (HVS) is influenced by the statistical distribution of colors and patterns in the natural …

gb (code pays fourni par la source)

Do computer vision foundation models learn the low-level characteristics of the human visual system?

Yancheng Cai, Fei Yin, Dounia Hammou, Rafał Mantiuk

Computer vision foundation models, such as DINO or OpenCLIP, are trained in a self-supervised manner on large image datasets. Analogously, substantial evidence suggests that the human visual system (HVS) is influenced by the statistical distribution of colors and patterns in the natural …

BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions

Jingdong Zhang, Jiayuan Fan, Peng Ye, Bo Zhang et autres

Multi-task dense prediction aims at handling multiple pixel-wise prediction tasks within a unified network simultaneously for visual scene understanding. However, cross-task feature interactions of current methods are still suffering from incomplete levels of representations, less discriminative semantics in feature participants, and inefficient …

cn, us (code pays fourni par la source)

DrKD: Decoupling response-based distillation for object detection

Yilong Lv, Yancheng Cai, Yujie He, Min Li

cn, gb (code pays fourni par la source)

elaTCSF: A Temporal Contrast Sensitivity Function for Flicker Detection and Modeling Variable Refresh Rate Flicker

Yancheng Cai, Aliakbar Bozorgian, Maliha Ashraf, Robert Wanat et autres

The perception of flicker has been a prominent concern in illumination and electronic display fields for over a century. Traditional approaches often rely on Critical Flicker Frequency (CFF), primarily suited for high-contrast (full-on, full-off) flicker. To tackle varying contrast flicker, the International …

gb, no, us (code pays fourni par la source)

Drkd: Rethinking and Decoupling Response Distillation for Object Detection

Yilong Lv, Yancheng Cai, Yujie He, Min Li

ca, gb, cn (code pays fourni par la source)

Drkd: Decoupling Response-Based Distillation for Object Detection

Yilong Lv, Yancheng Cai, Yujie He, Min Li

ca, gb, cn (code pays fourni par la source)

BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictions

Jingdong Zhang, Jiayuan Fan, Peng Ye, Bo Zhang et autres

Multi-task dense prediction aims at handling multiple pixel-wise prediction tasks within a unified network simultaneously for visual scene understanding. However, cross-task feature interactions of current methods are still suffering from incomplete levels of representations, less discriminative semantics in feature participants, and inefficient …

Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors

Yancheng Cai, Bo Zhang, Baopu Li, Tao Chen et autres

Cross-domain pedestrian detection aims to generalize pedestrian detectors from one label-rich domain to another label-scarce domain, which is crucial for various real-world applications. Most recent works focus on domain alignment to train domain-adaptive detectors either at the instance level or image level. …

gb, cn, us (code pays fourni par la source)