Although current ReID (Re-Identification) methods have become relatively mature, they still require manual extraction of pedestrian images and annotation of features. They lack semantic understanding capabilities in open scenes. While some ReID models integrated with LLMs (Large Language Models) offer more comprehensive functions and better performance, they still fall short in terms of semantic understanding and cross-modal retrieval. To solve these problems, we introduce SUO-ReID, a semantic understanding-based approach for ReID in open scenes. SUO-ReID combines LVLM (Large Vision-Language Model) with ResNet (Residual Network) to extract high-level semantic features of targets in open scenes. It can also perform more flexible and complex functions, such as searching for or comparing targets with specified features, through instruction inputs. Experimental results show that SUO-ReID achieves an accuracy rate of 95.73% on datasets such as Market-1501 and DukeMTMC and exhibits excellent semantic understanding capabilities in open scenes, supporting cross-modal retrieval. It can also provide a detailed description of the features of the identified object and its surrounding scene. This study provides new insights into the application of large vision-language models in the field of ReID.

Graphics processing units (GPUs) have become extremely important devices for accelerating computing performance in many applications. However, there have been few accurate models to estimate the performance of such applications running on modern GPUs. In this paper, we propose a performance model to estimate the execution times for massively parallel programs running on NVIDIA GPUs, one that takes on-chip resources and cost of data transfer between CPU and GPU into consideration. Four different GPUs with different architectures were used to evaluate our model. We demonstrated the effectiveness of the proposed model by applying it to various tasks in medical image registration. Experiments have demonstrated that by capturing on-chip GPU resources and data transfer time with our model, we were able to obtain a more accurate prediction of the actual running time, compared to the traditional model. Moreover, by using the optimal value of the block size parameter, estimated by our model, to accelerate the landmark tracking task on GPU devices, speedups of approximately 80×, 100×, 200× and 800×, on the C2050, K20c, M5000 and P100 can be achieved, making it possible to track massive numbers of landmarks and thereby improving the registration accuracy.

Left ventricle(LV) motion estimation plays an important role in the diagnosis and treatment of cardiovascular diseases. To improve the accuracy of LV motion estimation, we propose a method by combining point set matching with surface structure features. Firstly, the normal direction of a point is estimated by an approximate approach, and is used to describe the structure feature of the point. Then, the Gaussian mixture model (GMM) is employed to describe the structure features of the points extracted from a LV image. The LV motion estimation is reformulated as the problem of minimizing a statistical discrepancy measure between two Gaussian mixtures. A new cost function is defined based on the distance between two point sets and the discrepancy measure between Gaussian mixtures of structure features of two point sets. Lastly, we solve the new cost function using the combination of Stochastic Gradient Descent (SGD) algorithm and Quasi-Newton method. We evaluate the performance of our method on a cardiac dataset of 33 subjects. Experiments results show that our method is robust when large parameters are needed to be solved. Moreover, the registration accuracy is improved compared to existing point set matching methods.