Nan Xu

Biological vision integrates cues according to their reliability and context and uses coarse contextual information to form initial hypotheses before directing attention to local evidence. Inspired by these principles, we propose ADCCR (Adaptive Description Composition and Coarse-to-Fine Refinement), a language-guided framework for flexible human keypoint localization. A multi-granularity bank describes each keypoint by its name, anatomical definition, inter-joint relation, and visual appearance. A reliability-aware composer predicts sample-specific gates from the person image, target identity, and candidate cues, replacing predefined sampling probabilities. Counterfactual cue-consistency supervision suppresses inconsistent cues, while a sparse cue-budget regularizer reduces redundancy. The selected description guides a multimodal large language model to estimate a coarse coordinate from the whole-person image. A category-aware crop of the resized person image then focuses text-conditioned heatmap refinement on the candidate region. ADCCR thus provides a functional abstraction of reliability-aware cue integration and selective global-to-local inspection. Trained on COCO, ADCCR achieves 80.1 AP on the validation set, outperforming PoseLLM by 2.5 points. Results on MPII and Human-Art further demonstrate strong cross-dataset generalization.

Biomimetic perception systems integrate heterogeneous cues selectively rather than treating all available information as equally reliable. Inspired by this principle, this study proposes QGFace-LLaVA, a multimodal large language model (MLLM)-centered framework for robust face analysis under imperfect metadata. A pretrained MLLM serves as the shared prompt-conditioned visual–language reasoning backbone, while structured side information, including age, gender, confidence cues, and availability indicators, is regulated through task-aware quality estimation, reliability-guided metadata calibration, gated residual correction, and counterfactual metadata reliability regularization (CMRR). Experiments on FER2013, CelebA-40, and UTKFace cover facial expression recognition, facial attribute recognition, and age estimation under clean, noisy, missing, shuffled, naturally erroneous, and counterfactual metadata conditions. The results show that metadata utility depends jointly on task relevance, metadata reliability, and fusion strategy, and that clean-setting gains do not necessarily imply robustness. QGFace-LLaVA reduces harmful dependence on unreliable metadata, while CMRR provides additional stability under corruption and mismatch. Overall, the framework transfers biomimetic selective cue integration into MLLM-based face analysis by treating metadata as reliability-controlled auxiliary evidence rather than a uniformly beneficial input.

Due to the fast advancement in wireless communication technology, the demand for the modeling and generating of wireless channels is increasing. Deep learning technology is gradually applied in the wireless communication field, and the Generative Adversarial Network (GAN) framework provides a new solution for channel modeling. This paper presents a method based on Wasserstein GAN with gradient penalty (WGAN-GP) guided by an attention mechanism for wireless channel modeling and generating. The feature extraction capability of the model is enhanced by adding a channel attention mechanism in WGAN-GP, and the representation capability of the model is enhanced by adaptively recalibrating the channel feature response. The experimental results demonstrate that the proposed approach accurately models the channel distribution and generates data that closely aligns with the real channel distribution. The proposed method has been shown to achieve superior qualitative and quantitative evaluation compared to the existing method.

Color distortion, low contrast, and blurry details are the main features of underwater images, which can have adverse effects on their quality. To address these issues, a novel enhancement method based on color correction and multiscale fusion is proposed to improve underwater image quality, achieving color correction, contrast enhancement, and detail sharpening at different stages. The method consists of three main steps: color correction using a simple and effective histogram equalization-based method to correct color distortion, decomposition of the V channel of the color-corrected image into low- and high-frequency components using a guided filter, enhancement of the low-frequency component using a dual-interval histogram based on a benign separation threshold strategy, and a complementary pair of gamma functions; the fusion of the two versions of the low-frequency component to enhance image contrast; and finally, the design of an enhancement function to highlight image details. Comparative analysis with existing methods demonstrates that the proposed method achieves high-quality underwater images and favorable qualitative and quantitative evaluations. Compared to the method with the highest score, the average UIQM score of our method exceeds 6%, and the average UCIQE score exceeds 2%.