Computer-Aided Design (CAD) sketches, composed of geometric primitives and constraints, are fundamental to CAD models and play a critical role in industrial design and manufacturing. Leveraging artificial intelligence to convert hand-drawn sketches and rendered images into CAD sketches has the potential to streamline and accelerate the design process. Existing approaches predominantly focus on separately learning primitives and constraints, often employing two-stage methods or learnable tokens to model these elements independently. However, such methods fail to fully exploit the intrinsic relationships between primitives and constraints. In this paper, we propose LuBan, a lightweight, end-to-end model for CAD sketch generation that eliminates the need for separate constraint models or tokens. LuBan leverages the DEtection TRansformer (DETR) architecture for primitive modeling and distinguishes between parametric and non-parametric features. By deriving sub-primitive features from the intermediate outputs of the primitive model, LuBan facilitates constraint prediction, effectively capturing the inherent relationships between primitives and constraints. This enables the generation of CAD sketches as hierarchical graphs. Qualitative and quantitative experiments on both precise and hand-drawn renderings demonstrate that LuBan achieves state-of-the-art performance. Ablation studies further confirm its superiority over independently trained primitive models, validating its effectiveness. Additionally, LuBan embodies the principle of "what you draw is what you get," offering significant enhancements to the design process for designers.

Image hashing has been widely used in large-scale image retrieval due to its enhancement of storage space and retrieval speed. Recently, methods based on hash centers have achieved impressive retrieval performance, aiming to assign mutually separated hash codes as center points for each category and learn compact binary codes by minimizing intra-class variance. However, current methods tend to generate codebooks in advance, which are then used as pre-defined hash centers, leading to compromised quality of hash centers in instance-level datasets with excessive categories. To address this problem, we designed a training strategy that learns hash centers by constraining the margin of category clusters in Hamming space, during which the Gilbert-Varshamov bound and the upper bound of Hamming ball packing from coding theory are utilized to determine the range of margins. Finally, we jointly optimize hash encoder and hash centers to improve retrieval performance. Extensive experiments on more challenging large-scale instance-level datasets demonstrate that our method effectively overcomes the limitation of retrieval performance imposed by the number of categories. Code is at: https://github.com/GrimmAI/Hamming-Ball-Hashing.git.

Real-time matching between customer demands and product information via text-image retrieval remains a fundamental problem in intelligent retailing. However, this process involves challenges covering data quality, multi-modal retrieval strategies and performing efficiency. To alleviate the case, we propose a cross-modality retrieval pipeline leveraging contrastive loss and a novel sampling strategy. We also address text-image retrieval as a two-stage process, involving unsupervised clustering and contrastive feature representation. Additionally, we create an image-caption matching dataset by expanding the Grocery Store Dataset using a fundamental visual-language model. Our experiments demonstrate the effectiveness of our method on both an expanded new dataset and the well-known cross-modality retrieval benchmark, Flicker30k.

Multimodal representation aims to integrate information from multiple modalities to improve overall performance. Recent works utilizing pairwise interactions have been proposed to deal with the long-range inter-modal and intra-modal dependencies in modeling multimodal data. However, these works usually feature high model complexity, and they are not robust to noisy multimodal data. To address these problems, we propose a novel multimodal representation method that learns private and hub representations of modalities. These representations and their connections form a star graph, a basis for Star Graph-based Interaction (SGI). SGI not only captures the long-range dependencies in multimodal data but also has two natural properties. Firstly, the number of modal interactions increases linearly with the number of modalities, which is computationally efficient compared with the square increase rate of pairwise interactions in previous works. Secondly, the indirect modal interactions through the hub representation in SGI (rather than the direct pairwise interactions between modalities) ensure the model's robustness to noisy modalities. Experiments on five benchmark datasets demonstrate that our new SGI representation (SGIR) achieves state-of-the-art performance on various multimodal tasks, and our qualitative and quantitative analyses show the excellent generalization ability of SGIR. Further experiments reveal that SGIR still outperforms widely used baseline models when modalities are corrupted by low levels of noise.