RESUMO
Group re-identification (GReID) aims to correctly associate group images belonging to the same group identity, which is a crucial task for video surveillance. Existing methods only model the member feature representations inside each image (regarded as spatial members), which leads to potential failures in long-term video surveillance due to cloth-changing behaviors. Therefore, we focus on a new task called cloth-changing group re-identification (CCGReID), which needs to consider group relationship modeling in GReID and robust group representation against cloth-changing members. In this paper, we propose the separable spatial-temporal residual graph (SSRG) for CCGReID. Unlike existing GReID methods, SSRG considers both spatial members inside each group image and temporal members among multiple group images with the same identity. Specifically, SSRG constructs full graphs for each group identity within the batched data, which will be completely and non-redundantly separated into the spatial member graph (SMG) and temporal member graph (TMG). SMG aims to extract group features from spatial members, and TMG improves the robustness of the cloth-changing members by feature propagation. The separability enables SSRG to be available in the inference rather than only assisting supervised training. The residual guarantees efficient SSRG learning for SMG and TMG. To expedite research in CCGReID, we develop two datasets, including GroupPRCC and GroupVC, based on the existing CCReID datasets. The experimental results show that SSRG achieves state-of-the-art performance, including the best accuracy and low degradation (only 2.15% on GroupVC). Moreover, SSRG can be well generalized to the GReID task. As a weakly supervised method, SSRG surpasses the performance of some supervised methods and even approaches the best performance on the CSG dataset.
RESUMO
Curcumin is a natural polyphenol compound with anti-diabetic, anti-oxidative, and anti-inflammatory effects. Although many studies have reported the protective effect of curcumin in diabetes mellitus or diabetic nephropathy, there is a lack of research on curcumin in diabetic retinopathy. The purpose of this study was to investigate the therapeutic effects of curcumin on the diabetic retinal injury. Streptozotocin (STZ)-induced diabetic rats (60, n = 12 each) were respectively given curcumin orally (200 mg/kg/day), insulin subcutaneously (4-6 IU/day), and combined therapy with curcumin and insulin for 4 weeks. Retinal histopathological changes, oxidative stress markers, and transcriptome profiles from each group were observed. Curcumin, insulin, or combination therapy significantly reduced blood glucose, alleviated oxidative stress, and improved pathological damage in diabetic rats. Curcumin not only significantly reduced retinal edema but also had a better anti-photoreceptor apoptosis effect than insulin. In the early stage of diabetes, the enhancement of oxidative stress in the retina induced the adaptive activation of the nuclear factor E2-associated factor 2 (Nrf2) pathway. Treatment of curcumin alleviated the compensatory activation of the Nrf2 pathway induced by oxidative stress, by virtue of its antioxidant ability to transfer hydrogen atoms to free radicals. When curcumin combined with insulin, the effect of maintaining Nrf2 pathway homeostasis in diabetic rats was better than that of insulin alone. Transcriptomic analyses revealed that curcumin either alone, or combined with insulin, inhibited the AGE-RAGE signaling pathway and the extracellular matrix (ECM)-receptor interaction in the diabetic retina. Thus, at the early stage of diabetes, curcumin can be used to alleviate diabetic retinal injury through its anti-oxidative effect. If taking curcumin as a potential complementary therapeutic option in combination with antihyperglycemic agents, which would lead to more effective therapeutic outcomes against diabetic complications.