dual-branch-cross-attention-network-for-electroencephalography-facial

Dual-Branch Cross-Attention Network for Electroencephalography and Facial Multimodal Emotion Recognition During Painting Viewing

Emotion recognition during painting viewing remains difficult because aesthetic responses are dynamic, context-dependent, and only partly observable ...

Southwest University

Traditional wound closure methods often present several issues, including additional puncture wounds, adverse effects from anesthesia, and noticeable scarring. Inspired by embryonic wound healing, a Janus hydrogel (PG/Au-Asp@PCM) is designed to manipulate non-invasive wound closure by photothermal-responsive self-contraction of PG/Au-Asp@PCM, which is attributed to the shape memory behavior of PG/Au-Asp@PCM under near-infrared (NIR). Wherein, gelatin acts as a thermally reversible "switch" and polyacrylamide creates stable and cross-linked "net-points". The elongated PG/Au-Asp@PCM can be temporarily fixed at 4 °C, and subsequently self-contracts upon NIR irradiation, generating a recovery force of 10 kPa, adequate for the closure of wound spontaneously. The Janus hydrogel also incorporates a drug carrier loaded with phase change material (PCM) and aspirin. The PCM absorbs heat during its phase transition above 42 °C, offering the photothermal-responsive release of aspirin on-demand; additionally, it also reduces the risk of skin burn during NIR exposure. Animal studies confirm the effectiveness of PG/Au-Asp@PCM in wound closure. Moreover, wounds treated with PG/Au-Asp@PCM exhibit reduced inflammation, increased thickness of epidermal and dermal layers, and a smoother appearance without scarring. These findings reinforce the feasibility of the photothermal strategy utilizing PG/Au-Asp@PCM for non-invasive wound closure, resulting in enhanced cosmetic appearance and improved wound healing outcomes.

Photothermal-manipulatable shape memory polyacrylamide/gelatin Janus hydrogel with drug carrier array for invasive wound closure and responsive drug release.

Images captured by vision sensors in outdoor environments often suffer from haze-induced degradations, including blurred details, faded colors, and reduced visibility, which severely impair the performance of sensing and perception systems. To address this issue, we propose a haze-removal algorithm for hazy images using multiple variational constraints. Based on the classic atmospheric scattering model, a mixed variational framework is presented that incorporates three regularization terms for the transmission map and scene radiance. Concretely, an ℓp norm and an ℓ2 norm were constructed to jointly enforce the transmissions for smoothing the details and preserving the structures, and a weighted ℓ1 norm was devised to constrain the scene radiance for suppressing the noises. Furthermore, our devised weight function takes into account both the local variances and the gradients of the scene radiance, which adaptively perceives the textures and structures and controls the smoothness in the process of image restoration. To address the mixed variational model, a re-weighted least square strategy was employed to iteratively solve two separated subproblems. Finally, a gamma correction was applied to adjust the overall brightness, yielding the final recovered result. Extensive comparisons with state-of-the-art methods demonstrated that our proposed algorithm produces visually satisfactory results with a superior clarity and vibrant colors. In addition, our proposed algorithm demonstrated a superior generalization to diverse degradation scenarios, including low-light and remote sensing hazy images, and it effectively improved the performance of high-level vision tasks.

Article	Year
Photothermal-manipulatable shape memory polyacrylamide/gelatin Janus hydrogel with drug carrier array for invasive wound closure and responsive drug release. International journal of biological macromolecules\| PubMed ID: 39732225	2025
Single Image Haze Removal via Multiple Variational Constraints for Vision Sensor Enhancement. Sensors (Basel, Switzerland)\| PubMed ID: 41374572	2025

YuXue Feng

Biography

JoVE Journal Publications

Other Publications