Traditional 3D garment creation requires extensive manual operations, resulting in time and labor costs. Recently, 3D Gaussian Splatting has achieved breakthrough progress in 3D scene reconstruction and rendering, attracting widespread attention and opening new pathways for 3D garment reconstruction. However, due to the unstructured and irregular nature of Gaussian primitives, it is difficult to reconstruct high-fidelity, non-watertight 3D garments. In this paper, we present GarmentGS, a dense point cloud-guided method that can reconstruct high-fidelity garment surfaces with high geometric accuracy and generate non-watertight, single-layer meshes. Our method introduces a fast dense point cloud reconstruction module that can complete garment point cloud reconstruction in 10 minutes, compared to traditional methods that require several hours. Furthermore, we use dense point clouds to guide the movement, flattening, and rotation of Gaussian primitives, enabling better distribution on the garment surface to achieve superior rendering effects and geometric accuracy. Through numerical and visual comparisons, our method achieves fast training and real-time rendering while maintaining competitive quality.

Recent advances in single image super-resolution (SISR) have achieved remarkable performance through deep learning. However, the high computational cost hinders the deployment of SISR models on edge devices. Instead of proposing new SISR models, a new trend is emerging to improve network efficiency by reducing parameters, FLOPs, and inference time through slight modifications to the original models. However, recent methods usually focus on reducing only one of three metrics, i.e., FLOPs, parameters and inference time, which inevitably increases the other two metrics. In this paper, we propose a novel Adaptive Student Inference Network (ASIN) on popular SISR models, which aims at reducing FLOPs and inference time while maintaining the number of parameters and restoring clearer high-resolution images. Specifically, our ASIN divides a SISR model into three components (head, body and tail) and adopts various strategies for each part. For head and tail parts, to ensure the restored images contain more detailed information, a novel auxiliary Enhanced Teacher Network (ETNet) is designed, which is trained with the ground-truth images to obtain more prior knowledge to guide student network to extract more accurate textures using a new knowledge distillation method. For the body part, owing to the varying difficulties of the reconstructions in different regions, we propose an Adaptive Depth Predicted Module (ADPM) to dynamically shorten average depth of network to reduce the computational cost of overall network. Extensive experiments on two datasets demonstrate the effectiveness and state-of-the-art performance of our ASIN compared to its counterparts.

Clothes attribution prediction is the key technology for users to automatically describe clothing characteristics. Most current methods are first to detect the multiple clothes, and then crop out the clothes and feed to a certain network for clothes attribution prediction. But this two-stage approach is time- and resource- consuming; on the other hand, one-stage approach can provide an effective and efficient solution by integrating clothes detection and attribution prediction into an end-to-end framework. But the one-stage approach tends to explore anchor-based detectors causing high sensitivity to the hyperparameters and high computational complexity from dense anchors. In addition, it may also confront with optimization contradiction problem in the training procedure, as the clothes detection and attribution prediction branches demand diverse optimization. In this work, to handle the above problems, we aim to develop an end-to-end anchor-free framework by involving an additional branch for joint clothes detection and attribution prediction. To handle the optimization contradiction in two branches, we encode the backbone feature map as pixel-level dense queries and decode them via deformable transformer as the output features that are fed into detection and prediction branches, respectively. In this way, the features of detection and prediction branches can be decoupled and the optimization contradiction can be naturally solved. To further enhance the prediction accuracy, we in the prediction branch also develop a special attention strategy and loss function to adaptively integrate the peer attribution relationships into feature learning as well as to avoid mutual suppression for hierarchical attributions. Extensive simulation results verify the effectiveness of the proposed work.

Image captioning is still a challenging task aiming at describing the contents of image by words. Current image caption methods usually assume the object relation to be important if the semantic and spatial geometric relationships between objects are close and large, but the relations meeting this assumption are not necessarily important to describe the contents of image in a fine-grained way. That is, the importance of fine-grained object relations is not properly taken into account. Besides, current Transformer based image caption models also fail to consider the importance of fine-grained objects, since they generate all the words of a sentence at one time, which cannot Figure out which objects are more important and vice versa. In this paper, we propose a novel Fine-grained Adaptive Object Transformer (FineFormer) network, which can jointly discover the importance of fine-grained objects and object relations for image captioning. Specifically, a new concept of adaptive soft-foreground attention is proposed to highlight the fine-grained objects dominating the descriptive contents. To characterize and calculate the important relations between fine-grained objects, we also propose an adaptive object relation attention to refine the object relation from the generation process of relation. As such, FineFormer can describe the contents of image more accurately, by reducing the interference of unimportant objects in the background. Extensive experiments on the highly-competitive MS-COCO dataset demonstrated the superiority of our FineFormer.

Clothes image search is the key technique to effectively search the clothes items that are most relevant to the query clothes given by the customer. In this work, we propose an Anchor-free framework for clothes image search by adopting an additional Re-ID branch for similarity learning and global mask branch for instance segmentation. The Re-ID branch is to extract richer feature of target clothes, where we develop a mask pooling layer to aggregate the feature by utilizing the mask of target clothes as the guidance. In this way, the extracted feature will involve more information covered by the mask area of targets instead of only the center point; the global mask branch is to be trained with detection and Re-ID branches simultaneously, where the estimated mask of target clothes can be utilized in reference procedure to guide the feature extraction. Finally, to further enhance the performance of retrieval, we have introduced a match loss to further fine-tune the Re-ID embedding branch in the framework, so that the clothes target can be closer to the same one, while be farther away from different clothes targets. Extensive simulations have been conducted and the results verify the effectiveness of the proposed work.

Deep neural network (DNN) compression can reduce the memory footprint of deep networks effectively, so that the deep model can be deployed on the portable devices. However, most of the existing model compression methods cost lots of time, e.g., vector quantization or pruning, which makes them inept to the real-world applications that need fast online computation. In this paper, we therefore explore how to accelerate the model compression process by reducing the computation cost. Then, we propose a new deep model compression method, termed Dictionary Pair-based Data-Free Fast DNN Compression, which aims at reducing the memory consumption of DNNs without extra training and can greatly improve the compression efficiency. Specifically, our proposed method performs tensor decomposition on the DNN model with a fast dictionary pair learning-based reconstruction approach, which can be deployed on different layers (e.g., convolution and fully-connection layers). Given a pre-trained DNN model, we first divide the parameters (i.e., weights) of each layer into a series of partitions for dictionary pair-based fast reconstruction, which can potentially discover more fine-grained information and provide the possibility for parallel model compression. Then, dictionaries of less memory occupation are learned to reconstruct the weights. Extensive experiments on popular DNNs (i.e., VGG-16, ResNet-18 and ResNet-50) showed that our proposed weight compression method can significantly reduce the memory footprint and speed up the compression process, with less performance loss.

Real-world data in emerging applications may suffer from highly-skewed class imbalanced distribution, however how to deal with this kind of problem appropriately through deep learning needs further investigation. In this paper, we mainly propose a novel cross-entropy based loss function, referred to as Additive Scale Loss (ASL), for deep representation learning and imbalanced classification. To deal with the class imbalanced problem, ASL aims at increasing the loss in case of misclassification, which can avoid the superimposed loss values caused by the large amount of easily classified data in the unbalanced database to dominate the loss value of misclassified data. Moreover, in real-world applications, one data source may be used for multiple scenarios, such as classification and embedding learning, however training two separable models to handle these problems is costly, especially in deep learning area. To tackle this issue, we present and integrate a discriminative inter-class separation term into ASL, and propose a discriminative ASL (D-ASL), which can not only improve the classification performance, but also obtain discriminative representations simultaneously. The discriminative inter-class separation term is general, and can be easily integrated to other loss functions, such as CE and FL, as the byproducts. Finally, a new deep convolutional neural network equipped with D-ASL and a fully-connected (FC) layer is proposed, which can classify the imbalanced image data and obtain the discriminative representations at the same time. Extensive experimental results verified the superior performance of our method.

In this paper, we technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features. To improve the representation and clustering abilities, DSCF-Net explicitly considers discovering hidden deep semantic features, enhancing the robustness properties of the deep factorization to noise and preserving the local manifold structures of deep features. Specifically, DSCF-Net integrates the robust deep concept factorization, deep self-expressive representation and adaptive locality preserving feature learning into a unified framework. To discover hidden deep representations, DSCF-Net designs a hierarchical factorization architecture using multiple layers of linear transformations, where the hierarchical representation is performed by formulating the problem as optimizing the basis concepts in each layer to improve the representation indirectly. DSCF-Net also improves robustness by subspace recovery for sparse error correction firstly and then performs deep factorization in the recovered visual subspace. To obtain localitypreserving representations, we also present an adaptive deep self-representative weighting strategy by using the coefficient matrix as adaptive weights to keep the locality of representations. Extensive results show that DSCF-Net delivers state-of-the-art performance on several public databases.

Books, as a representative of lengthy documents, convey rich semantics. Traditional document modeling methods, such as bag-of-words models, have difficulty capturing such rich semantics when only considering term-frequency features. In order to explore term spatial distributions over a book, a tree-structured book representation is investigated in this paper. Moreover, an efficient learning framework, Tree2Vector, is introduced for mapping tree-structured book data into vectorial space. In particular, we present two types of locality reconstruction (LR) models: Euclidean-type and cosine-type, during the transformation process of tree structures into vectorial representations. The LR is used for modeling the reconstruction process, in which each parent node in a tree is supposed to be reconstructed by its child nodes. The prominent advantage of this Tree2Vector framework is that it solely utilizes the local information within a single book tree. In addition, extensive experimental results demonstrate that Tree2Vector is able to deliver comparable or better performance in comparison to methods that consider the information of all trees in a database globally. Experimental results also suggest that cosine-type LR consistently performs better than Euclidean-type LR in applications of book and author recommendations.

We propose a new transductive label propagation method, termed Adaptive Neighborhood Propagation (Adaptive-NP) by joint L2,1-norm regularized sparse coding, for semi-supervised classification. To make the predicted soft labels more accurate for predicting the labels of samples and to avoid the tricky process of choosing the optimal neighborhood size or kernel width for graph construction, Adaptive-NP seamlessly integrates sparse coding and neighborhood propagation into a unified framework. That is, the sparse reconstruction error and classification error are combined for joint minimization, which clearly differs from traditional methods that explicitly separate graph construction and label propagation into independent steps, which may result in inaccurate predictions. Note that our Adaptive-NP alternately optimize the sparse codes and soft labels matrices, where the sparse codes are used as adaptive weights for neighborhood propagation at each iteration, so the tricky process of determining neighborhood size or kernel width is avoided. Besides, for enhancing sparse coding, we use the L2,1-norm constraint on the sparse coding coefficients and the reconstruction error at the same time for delivering more accurate and robust representations. Extensive simulations show that our model can deliver state-of-the-art performances on several public datasets for classification.

This paper proposes an enhanced semi-supervised classification approach termed Nonnegative Sparse Neighborhood Propagation (SparseNP) that is an improvement to the existing neighborhood propagation due to the fact that the outputted soft labels of points cannot be ensured to be sufficiently sparse, discriminative, robust to noise and be probabilistic values. Note that the sparse property and strong discriminating ability of predicted labels is important, since ideally the soft label of each sample should have only one or few positive elements (that is, less unfavorable mixed signs are included) deciding its class assignment. To reduce the negative effects of unfavorable mixed signs on the learning performance, we regularize the l2,1-norm on the soft labels during optimization for enhancing the prediction results. The non-negativity and sum-to-one constraints are also included to ensure the outputted labels are probabilistic values. The proposed framework is solved in an alternative manner for delivering a more reliable solution so that the accuracy can be improved. Simulations show that satisfactory results can be obtained by the proposed SparseNP compared with other related approaches.

In this article, we consider the problem of simultaneous low-rank recovery and sparse projection. More specifically, a new Robust Principal Component Analysis (RPCA)-based framework called Sparse Projection and Low-Rank Recovery (SPLRR) is proposed for handwriting representation and salient stroke feature extraction. In addition to achieving a low-rank component encoding principal features and identify errors or missing values from a given data matrix as RPCA, SPLRR also learns a similarity-preserving sparse projection for extracting salient stroke features and embedding new inputs for classification. These properties make SPLRR applicable for handwriting recognition and stroke correction and enable online computation. A cosine-similarity-style regularization term is incorporated into the SPLRR formulation for encoding the similarities of local handwriting features. The sparse projection and low-rank recovery are calculated from a convex minimization problem that can be efficiently solved in polynomial time. Besides, the supervised extension of SPLRR is also elaborated. The effectiveness of our SPLRR is examined by extensive handwritten digital repairing, stroke correction, and recognition based on benchmark problems. Compared with other related techniques, SPLRR delivers strong generalization capability and state-of-the-art performance for handwriting representation and recognition.

A new graph based constrained semi-supervised learning (G-CSSL) framework is proposed. Pairwise constraints (PC) are used to specify the types (intra- or inter-class) of points with labels. Since the number of labeled data is typically small in SSL setting, the core idea of this framework is to create and enrich the PC sets using the propagated soft labels from both labeled and unlabeled data by special label propagation (SLP), and hence obtaining more supervised information for delivering enhanced performance. We also propose a Two-stage Sparse Coding, termed TSC, for achieving adaptive neighborhood for SLP. The first stage aims at correcting the possible corruptions in data and training an informative dictionary, and the second stage focuses on sparse coding. To deliver enhanced inter-class separation and intra-class compactness, we also present a mixed soft-similarity measure to evaluate the similarity/dissimilarity of constrained pairs using the sparse codes and outputted probabilistic values by SLP. Simulations on the synthetic and real datasets demonstrated the validity of our algorithms for data representation and image recognition, compared with other related state-of-the-art graph based semi-supervised techniques.

Visualizing similarity data of different objects by exhibiting more separate organizations with local and multimodal characteristics preserved is important in multivariate data analysis. Laplacian Eigenmaps (LAE) and Locally Linear Embedding (LLE) aim at preserving the embeddings of all similarity pairs in the close vicinity of the reduced output space, but they are unable to identify and separate interclass neighbors. This paper considers the semi-supervised manifold learning problems. We apply the pairwise Cannot-Link and Must-Link constraints induced by the neighborhood graph to specify the types of neighboring pairs. More flexible regulation on supervised information is provided. Two novel multimodal nonlinear techniques, which we call trace ratio (TR) criterion-based semi-supervised LAE (S2LAE) and LLE (S2LLE), are then proposed for marginal manifold visualization. We also present the kernelized S2LAE and S2LLE. We verify the feasibility of S2LAE and S2LLE through extensive simulations over benchmark real-world MIT CBCL, CMU PIE, MNIST, and USPS data sets. Manifold visualizations show that S2LAE and S2LLE are able to deliver large margins between different clusters or classes with multimodal distributions preserved. Clustering evaluations show they can achieve comparable to or even better results than some widely used methods.

This paper incorporates the group sparse representation into the well-known canonical correlation analysis (CCA) framework and proposes a novel discriminant feature extraction technique named group sparse canonical correlation analysis (GSCCA). GSCCA uses two sets of variables and aims at preserving the group sparse (GS) characteristics of data within each set in addition to maximize the global interset covariance. With GS weights computed prior to feature extraction, the locality, sparsity and discriminant information of data can be adaptively determined. The GS weights are obtained from an NP-hard group-sparsity promoting problem that considers all highly correlated data within a group. By defining one of the two variable sets as the class label matrix, GSCCA is effectively extended to multiclass scenarios. Then GSCCA is theoretically formulated as a least-squares problem as CCA does. Comparative analysis between this work and the related studies demonstrate that our algorithm is more general exhibiting attractive properties. The projection matrix of GSCCA is analytically solved by applying eigen-decomposition and trace ratio (TR) optimization. Extensive benchmark simulations are conducted to examine GSCCA. Results show that our approach delivers promising results, compared with other related algorithms.