In user-generated-content (UGC) applications, non-expert users often rely on image-to-3D generative models to create 3D assets. In this context, primitive-based shape abstraction offers a promising solution for UGC scenarios by compressing high-resolution meshes into compact, editable representations. Towards this end, effective shape abstraction must therefore be structure-aware, characterized by low overlap between primitives, part-aware alignment, and primitive compactness. We present Light-SQ, a novel superquadric-based optimization framework that explicitly emphasizes structure-awareness from three aspects. (a) We introduce SDF carving to iteratively udpate the target signed distance field, discouraging overlap between primitives. (b) We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition, enabling structural partitioning to drive primitive placement. (c) We implement adaptive residual pruning based on SDF update history to surpress over-segmentation and ensure compact results. In addition, Light-SQ supports multiscale fitting, enabling localized refinement to preserve fine geometric details. To evaluate our method, we introduce 3DGen-Prim, a benchmark extending 3DGen-Bench with new metrics for both reconstruction quality and primitive-level editability. Extensive experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics for complex generated geometry, advancing the feasibility of 3D UGC creation. Project Page: https://johann.wang/Light-SQ/ .

Recently, methods that utilize prompt tuning to rapidly transfer pretrained vision-language models (VLMs) to downstream tasks have been proposed. Although these models have produced reasonable results, they typically learn a single prompt, which limits their ability to capture more diverse information. This ability is crucial for addressing fine-grained classification challenges and intraclass visual variability (e.g., color, pose, and size variations within the same category). However, learning multiple prompts provides a larger optimization space, which further exacerbates the overfitting phenomenon. This makes it more challenging balance the performances acienved for base and new categories. To address these issues, we propose progressive multi-prompt (PMP) learning method.ecently, methods that utilize prompt tuning to rapidly transfer pretrained vision-language models (VLMs) to downstream tasks have been proposed. Although these models have produced reasonable results, they typically learn a single prompt, which limits their ability to capture more diverse information. This ability is crucial for addressing fine-grained classification challenges and intraclass visual variability (e.g., color, pose, and size variations within the same category). However, learning multiple prompts provides a larger optimization space, which further exacerbates the overfitting phenomenon. This makes it more challenging balance the performances acienved for base and new categories. To address these issues, we propose progressive multiprompt (PMP) learning method.R Specifically, we introduce multiple prompts in a step-by-step manner to focus on various information. To reduce overfitting, we utilize alate attachingmechanism to defer the interactions of prompts and features to a deeper encoding layer. Furthermore, we balance the prompts for different layers with learnable weights to guide the optimal optimization procedure. We compared our method with several state-of-the-art approaches in base-to-new task settings and demonstrate superior base-new tradeoff performance. Additionally, we conducted cross-dataset transfer, domain generalization, and few-shot experiments to further validate the effectiveness of our method. Our code is available at https://github.com/JunLGeek/PMP.git.

Face recognition has made significant advances with the development of deep learning and has begun to be deployed in some unrestricted scenarios. Many smartphones, for example, have infrared sensors that allow them to capture clear images even in low-light conditions. Face authentication under complex environmental conditions can thus be accomplished by matching NIR-VIS face images across modalities. However, existing NIR-VIS datasets lack enough variation in face attributes and are insufficient for real-world scenarios. To address the aforementioned issues, we first propose a 300-person NIR-VIS cross-modality face dataset with a variety of attributes. Based on modal information removal, we proposed a NIR-VIS cross-modal face recognition model. We can effectively extract modal information by constraining the similarity distribution of modalities and then using the orthogonal loss to remove modal information from identity features. The method achieves excellent results on our dataset and CASIA NIR-VIS 2.0 dataset.

Computational photo quality evaluation is a useful technique in many tasks of computer vision and graphics, for example, photo retaregeting, 3-D rendering, and fashion recommendation. The conventional photo quality models are designed by characterizing the pictures from all communities (e.g., "architecture" and "colorful") indiscriminately, wherein community-specific features are not exploited explicitly. In this article, we develop a new community-aware photo quality evaluation framework. It uncovers the latent community-specific topics by a regularized latent topic model (LTM) and captures human visual quality perception by exploring multiple attributes. More specifically, given massive-scale online photographs from multiple communities, a novel ranking algorithm is proposed to measure the visual/semantic attractiveness of regions inside each photograph. Meanwhile, three attributes, namely: 1) photo quality scores; weak semantic tags; and inter-region correlations, are seamlessly and collaboratively incorporated during ranking. Subsequently, we construct the gaze shifting path (GSP) for each photograph by sequentially linking the top-ranking regions from each photograph, and an aggregation-based CNN calculates the deep representation for each GSP. Based on this, an LTM is proposed to model the GSP distribution from multiple communities in the latent space. To mitigate the overfitting problem caused by communities with very few photographs, a regularizer is incorporated into our LTM. Finally, given a test photograph, we obtain its deep GSP representation and its quality score is determined by the posterior probability of the regularized LTM. Comparative studies on four image sets have shown the competitiveness of our method. Besides, the eye-tracking experiments have demonstrated that our ranking-based GSPs are highly consistent with real human gaze movements.

Internet-of-Things (IoT) devices are widely deployed nowadays. A large number of smart home IoT devices are hosted on a cloud server for easy management. Users can use their accounts to initiate operations and management on IoT devices through a cloud server, such as updating firmware and configuring devices. However, the cloud account may be hacked resulting in adversarial attacks to the hosted IoT devices. As a consequence, an adversary may perform malicious operations through the cloud remotely to the hosted IoT devices without user awareness. Motivated by this, in this article we propose gateway-based 2 factor authentication (G2F), a secure user authentication framework dedicated for a gateway based on the universal 2nd factor (U2F) protocol to enhance the security of IoT devices management. In G2F, the user authentication on the gateway is completed utilizing a hardware token that interacts with the local gateway node to guarantee the token owner’s presence. Furthermore, G2F can grant multiple simultaneous operations on IoT devices through just one user authentication. We implement a prototype to further evaluate the performance of G2F. Based on our realization on the commercial IoT server, i.e., Alibaba Cloud, G2F demonstrates the ability to protect against malicious attacks with high authentication efficiency.

While it is risky considering spacecraft constraints and unknown environment on asteroid, surface sampling is an important technique for asteroid exploration. One of the sample return missions is to seek an optimal landing site, which may be in hazardous terrain. Since autonomous landing is particularly challenging, it is necessary to simulate the effectiveness of this process and prove the onboard optical hazard avoidance is robust to various uncertainties. This paper aims to generate realistic surface images of asteroids for simulations of asteroid exploration. A SinGAN-based method is proposed, which only needs a single input image for training a pyramid of multi-scale patch generators. Various images with high fidelity can be generated, and manipulations such as shape variation, illumination direction variation, super resolution generation are well achieved. The method's applicability is validated by extensive experimental results and evaluations. At last, the proposed method has been used to help set up a test environment for landing site selection simulation.

This paper presents a speech information-hiding scheme that is integrated with the CELP (Coded Exited Linear Prediction) speech coding method. The G.729 codec (CS-ACELP) is used to test the efficiency of this scheme. The index-constrained method is applied for the secret information embedding. The selected bits of first-stage and residual vector indices during the Predictive Two-stage Vector Quantization procedure are modulated by the secret information bits. For the imperceptibility of this scheme, the quality of the watermarked speech signal can be controlled by adaptive embedding through referring to the original and watermarked speech. Experimental results show that this scheme can be effective and the distortion of the speech signal is trivial and imperceptible.

This paper proposes a scheme to hide some extra confidential data in transparencies during secret image encryption in visual cryptography. The secret image is multitoned into several levels first. An extended non-expansion visual secret sharing model is employed, i.e. size of transparencies is equal to that of the secret image. Thus less time and space are needed for transparencies transmission and storage.

This paper proposes two transparency authentication schemes used in visual cryptography, which are based on watermarking techniques. In the first scheme, a secret image can be perceptible when stacking two transparencies. In addition, another watermark image is visible when shifting one transparency to an appropriate position and stacking it with the other transparency. In the second scheme, both the secret image and the watermark are of the same size, while in the first scheme, the watermark is half of the size of the secret image. No computer aid is needed in decryption in the first scheme while simple computation is required in the second one. The secret image and the watermark are encrypted at the same time in the two schemes. Experimental results demonstrate the two schemes are effective and practical.