We present VisAssist, the first large-scale video question-answering dataset with 13,413 real-world videos captured by visually impaired users, addressing a critical gap in assistive vision research. Unlike existing benchmarks relying on third-person footage, VisAssist provides authentic first-person perspectives that uniquely capture challenges in blind photography—including unconventional framing, motion artifacts, and frequent information omission. Benchmark evaluations of SOTA multimodal models reveal systematic limitations: severe deficiencies in spatial reasoning when processing dynamic first-person viewpoints, an inability to distinguish missing information from poor capture quality leading to hazardous hallucinations, and fragile text understanding especially for non-Latin scripts under suboptimal conditions. This work establishes a vital real-world benchmark and underscores the need for specialized architectures in visual assistance systems.

Conventional retinal implants involve complex surgical procedures and require invasive implantation. Temporal Interference Stimulation (TIS) has achieved noninvasive and focused stimulation of deep brain regions by delivering high-frequency currents with small frequency differences on multiple electrodes. In this study, we conducted in silico investigations to evaluate extraocular TIS’s potential as a novel visual restoration approach. Different from the previously published retinal TIS model, the new model of extraocular TIS incorporated a biophysically detailed retinal ganglion cell (RGC) population, enabling a more accurate simulation of retinal outputs under electrical stimulation. Using this improved model, we made the following major discoveries: (1) the maximum value of TIS envelope electric potential ([Formula: see text] showed a strong correlation with TIS-induced RGC activation; (2) the preferred stimulating/return electrode (SE/RE) locations to achieve focalized TIS were predicted; (3) the performance of extraocular TIS was better than same-frequency sinusoidal stimulation (SSS) in terms of lower RGC threshold and more focused RGC activation; (4) the optimal stimulation parameters to achieve lower threshold and focused activation were identified; and (5) spatial selectivity of TIS could be improved by integrating current steering strategy and reducing electrode size. This study provides insights into the feasibility and effectiveness of a low-invasive stimulation approach in enhancing vision restoration.

ConvNet-based object detection networks have achieved outstanding performance on clean images. However, many works have shown that these detectors perform poorly on corrupted images caused by noises, blurs, poor weather conditions and so on. With the development of security-sensitive applications, the detector's practicability has raised increasing concerns. Existing approaches improve detector robustness via extra operations (image restoration or training on extra labeled data) or by applying adversarial training at the expense of performance degradation on clean images. In this paper, we present Selective Adversarial Learning with Constraints (SALC) as a universal detector training approach to simultaneously improve the detector's precision and robustness. We first propose a unified formulation of adversarial samples for multitask adversarial learning, which significantly diversifies the obtained adversarial samples when integrated into the adversarial training of the detector. Next, we examine our findings on model bias against adversarial attacks of different strengths and differences in Batch Normalization (BN) statistics among clean images and different adversarial samples. On this basis, we propose a batch local comparison strategy with two BN branches to balance the detector's accuracy and robustness. Furthermore, to avoid performance degradation caused by overwhelming subtask losses, we leverage task-aware ratio thresholds to control the influence of learning in each subtask. The proposed approach can be applied to various detectors without any extra labeled data, inference time costs, or model parameters. Extensive experiments show that our SALC achieves state-of-the-art results on both clean benchmarks (Pascal VOC and MS-COCO) and corruption benchmarks (Pascal VOC-C and MS-COCO-C).

Despite many advances in the development of retinal prostheses, clinical reports show that current retinal prosthesis subjects can only perceive prosthetic vision with poor visual acuity. A possible approach for improving visual acuity is to produce virtual electrodes (VEs) through electric field modulation. Generating controllable and localized VEs is a crucial factor in effectively improving the perceptive resolution of the retinal prostheses. In this paper, we aimed to design a microelectrode array (MEA) that can produce converged and controllable VEs by current steering stimulation strategies. Through computational modeling, we designed a three-dimensional concentric ring-disc MEA and evaluated its performance with different stimulation strategies. Our simulation results showed that electrode-retina distance (ERD) and inter-electrode distance (IED) can dramatically affect the distribution of electric field. Also the converged VEs could be produced when the parameters of the three-dimensional MEA were appropriately set. VE sites can be controlled by manipulating the proportion of current on each adjacent electrode in a current steering group (CSG). In addition, spatial localization of electrical stimulation can be greatly improved under quasi-monopolar (QMP) stimulation. This study may provide support for future application of VEs in epiretinal prosthesis for potentially increasing the visual acuity of prosthetic vision.