6 accepted papers
In the field of Blind Image Quality Assessment (BIQA), accurately predicting the perceptual quality of authentically distorted images remains highly challenging due to the diverse and complex distortions present in natural environments. Although existing methods have achieved notable accuracy, their…
Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the response preference by using the output probabilities of response pairs under contrastive prompt pairs, which could achiev…
Precise and smooth control of an electromagnetic actuated micropositioner is a challenging task due to the system's nonlinear electromagnetic dynamics, as well as its unique structure and application scenarios. The main challenges include high-order nonlinearity, modeling uncertainties, input buffet
In prior studies, domain adversarial neural networks (DANNs) are used to align image-level features regardless of foreground and background. However, the conventional discriminator in DANNs may leads the feature extractor to disregard cross-domain features rather than aligning them. This phenomenon…
Image-text retrieval is a fundamental task to bridge vision and language by exploiting various strategies to fine-grained alignment between regions and words. This is still tough mainly because of one-to-many correspondence, where a set of matches from another modality can be accessed by a random qu…
We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant methods that use the bird-eye view (BEV), our proposed detector detects objects from the range view (RV, a.k.a. range image)…