Aspect Graph Research Articles

Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models

Recommendation systems harness user-item interactions like clicks and reviews to learn their representations. Previous studies improve recommendation accuracy and interpretability by modeling user preferences across various aspects and intents. However, the aspects and intents are inferred directly from user reviews or behavior patterns, suffering from the data noise and the data sparsity problem. Furthermore, it is difficult to understand the reasons behind recommendations due to the challenges of interpreting implicit aspects and intents. To address these constraints, we harness the sentiment analysis capabilities of Large Language Models (LLMs) to enhance the accuracy and interpretability of the conventional recommendation methods. Specifically, inspired by the deep semantic understanding offered by LLMs, we introduce a chain-based prompting strategy to uncover semantic aspect-aware interactions, which provide clearer insights into user behaviors at a fine-grained semantic level. To incorporate the rich interactions of various aspects, we propose the simple yet effective Semantic Aspect-based Graph Convolution Network (short for SAGCN). By performing graph convolutions on multiple semantic aspect graphs, SAGCN efficiently combines embeddings across multiple semantic aspects for final user and item representations. The effectiveness of the SAGCN was evaluated on four publicly available datasets through extensive experiments, which revealed that it outperforms all other competitors. Furthermore, interpretability analysis experiments were conducted to demonstrate the interpretability of incorporating semantic aspects into the model.

Facial augmented reality based on hierarchical optimization of similarity aspect graph

BackgroundThe existing face matching method requires a point cloud to be drawn on the real face for registration, which results in low registration accuracy due to the irregular deformation of the patient's skin that makes the point cloud have many outlier points. MethodsThis work proposes a non-contact pose estimation method based on similarity aspect graph hierarchical optimization. The proposed method constructs a distance-weighted and triangular-constrained similarity measure to describe the similarity between views by automatically identifying the 2D and 3D feature points of the face. A mutual similarity clustering method is proposed to construct a hierarchical aspect graph with 3D pose as nodes. A Monte Carlo tree search strategy is used to search the hierarchical aspect graph for determining the optimal pose of the facial 3D model, so as to realize the accurate registration of the facial 3D model and the real face. ResultsThe proposed method was used to conduct accuracy verification experiments on the phantoms and volunteers, which were compared with four advanced pose calibration methods. The proposed method obtained average fusion errors of 1.13 ± 0.20 mm and 0.92 ± 0.08 mm in head phantom and volunteer experiments, respectively, which exhibits the best fusion performance among all comparison methods. ConclusionsOur experiments proved the effectiveness of the proposed pose estimation method in facial augmented reality.

Aspect-Based Sentiment Analysis With Heterogeneous Graph Neural Network

Aspect-based sentiment analysis aims to predict sentiment polarities of given aspects in text. Most current approaches employ attention-based neural methods to capture semantic relationships between aspects and words in one sentence. However, these methods ignore the fact that sentences with the same aspect and sentiment polarity often share the structure and semantic information in a domain, which leads to lower model performance. To mitigate this problem, we propose a heterogeneous aspect graph neural network (HAGNN) to learn the structure and semantic knowledge from intersentence relationships. Our model is a heterogeneous graph neural network since it contains three different kinds of nodes: word nodes, aspect nodes, and sentence nodes. These nodes can pass structure and semantic information between each other and update their embeddings to improve the performance of our model. To the best of our knowledge, we are the first to use a heterogeneous graph to capture relationships between sentences and aspects. The experimental results on five public datasets show the effectiveness of our model outperforming some state-of-the-art models.

DualGCN: An Aspect-Aware Dual Graph Convolutional Network for review-based recommender

Recently, a variety of review-based recommendation systems that incorporate the valuable information extracted from user-generated textual reviews into user and item modeling have been proposed. However, the existing recommendations normally model reviews at the sentence level. They ignore the modeling of aspect words in reviews, which fails to capture user preferences and item attributes in a fine-grained way. In addition, few studies consider constructing user–item interaction based on review information extracted from the aspect level. In this paper, we are motivated to propose an Aspect-Aware Dual Graph Convolutional Network (DualGCN). Specifically, we first design an Aspect-GCN layer to model the message diffusion of an aspect graph constructed from reviews, capturing the overall description of an aspect in all reviews. We then propose a UI-GCN layer to model a user’s fine-grained preferences toward interacted items at the aspect level. Finally, we adopt a Factorization Machine model to accomplish the recommendation task. The experimental results demonstrate that our model significantly outperforms the related approaches w.r.t. the accuracy of both rating prediction and top-K ranking on Amazon and Yelp datasets.

Knowledge empowered prominent aspect extraction from product reviews

Many existing systems for analyzing and summarizing customer reviews about products or service are based on a number of prominent review aspects. Conventionally, the prominent review aspects of a product type are determined manually. This costly approach cannot scale to large and cross-domain services such as Amazon.com, Taobao.com or Yelp.com where there are a large number of product types and new products emerge almost everyday. In this paper, we propose a novel method empowered by knowledge sources such as Probase and WordNet, for extracting the most prominent aspects of a given product type from textual reviews. The proposed method, ExtRA (Extraction of Prominent Review Aspects), (i) extracts the aspect candidates from text reviews based on a data-driven approach, (ii) builds an aspect graph utilizing the Probase to narrow the aspect space, (iii) separates the space into reasonable aspect clusters by employing a set ofproposed algorithms and finally (iv) generates K most prominent aspect terms or phrases which do not overlap semantically automatically without supervision from those aspect clusters. ExtRA extracts high-quality prominent aspects as well as aspect clusters with little semantic overlap by exploring knowledge sources. ExtRA can extract not only words but also phrases as prominent aspects. Furthermore, it is general-purpose and can be applied to almost any type of product and service. Extensive experiments show that ExtRA is effective and achieves the state-of-the-art performance on a dataset consisting of different product types.

A 3D reconstruction method for pipeline inspection based on multi-vision

Abstract A fast and precise 3D reconstruction method for complex pipeline inspection is presented. The reconstruction process is divided into three phases based on multi-vision. A centerline matching and registration algorithm is proposed to achieve the branched and bended pipes’ reconstruction. The projected centerline of each pipe is split into several NURBS curves, and these curves are taken as the primitives of matching to be reconstructed and registered precisely. A pose estimation algorithm based on shape aspect graphs is proposed to achieve the joint’s reconstruction. The CAD model of each joint is used to obtain its shape aspect graphs as the templates which its edges image matches with. A pipeline multi-camera reconstruction system is established, and validation experiments are carried out. The results show that the proposed method completes a pipeline’s reconstruction within 5 min. The reconstruction errors of its pipes and joints are 0.24 mm and 0.496 mm respectively.

3-D Object Recognition via Aspect Graph Aware 3-D Object Representation

This letter addresses the problem of 3-D object recognition, whose aim is to recognize and estimate the pose of user-defined 3-D object when given an image. One difficult problem for 3-D object recognition is false correspondences between input image and 3-D model. To overcome this problem, we propose a novel aspect graph aware 3-D object representation method which enable us to output continuous pose and deal with self-occlusion problem. We also propose a two-stage 2-D to 3-D false correspondence filter based on proposed 3-D representation to achieve more consistent 2-D to 3-D matching pairs. We evaluate our proposed algorithm on Weizman Cars Viewpoint dataset and it demonstrates obvious improvement on localization and pose estimation accuracy compared with traditional methods. Besides, our proposed method accelerates computation time.

Seamless Fusion of LiDAR and Aerial Imagery for Building Extraction

Although many efforts have been made on the fusion of Light Detection and Ranging (LiDAR) and aerial imagery for the extraction of houses, little research on taking advantage of a building's geometric features, properties, and structures for assisting the further fusion of the two types of data has been made. For this reason, this paper develops a seamless fusion between LiDAR and aerial imagery on the basis of aspect graphs, which utilize the features of houses, such as geometry, structures, and shapes. First, 3-D primitives, standing for houses, are chosen, and their projections are represented by the aspects. A hierarchical aspect graph is then constructed using aerial image processing in combination with the results of LiDAR data processing. In the aspect graph, the note represents the face aspect and the arc is described by attributes obtained by the formulated coding regulations, and the coregistration between the aspect and LiDAR data is implemented. As a consequence, the aspects and/or the aspect graph are interpreted for the extraction of houses, and then the houses are fitted using a planar equation for creating a digital building model (DBM). The experimental field, which is located in Wytheville, VA, is used to evaluate the proposed method. The experimental results demonstrated that the proposed method is capable of effectively extracting houses at a successful rate of 93%, as compared with another method, which is 82% effective when LiDAR spacing is approximately 7.3 by 7.3 ft $^{2}$ . The accuracy of 3-D DBM is higher than the method using only single LiDAR data.

Combining Scale-Space and Similarity-Based Aspect Graphs for Fast 3D Object Recognition

This paper describes an approach for recognizing instances of a 3D object in a single camera image and for determining their 3D poses. A hierarchical model is generated solely based on the geometry information of a 3D CAD model of the object. The approach does not rely on texture or reflectance information of the object's surface, making it useful for a wide range of industrial and robotic applications, e.g., bin-picking. A hierarchical view-based approach that addresses typical problems of previous methods is applied: It handles true perspective, is robust to noise, occlusions, and clutter to an extent that is sufficient for many practical applications, and is invariant to contrast changes. For the generation of this hierarchical model, a new model image generation technique by which scale-space effects can be taken into account is presented. The necessary object views are derived using a similarity-based aspect graph. The high robustness of an exhaustive search is combined with an efficient hierarchical search. The 3D pose is refined by using a least-squares adjustment that minimizes geometric distances in the image, yielding a position accuracy of up to 0.12 percent with respect to the object distance, and an orientation accuracy of up to 0.35 degree in our tests. The recognition time is largely independent of the complexity of the object, but depends mainly on the range of poses within which the object may appear in front of the camera. For efficiency reasons, the approach allows the restriction of the pose range depending on the application. Typical runtimes are in the range of a few hundred ms.

Learning Combinatorial Map Information from Permutations of Landmarks

This paper considers a robot that moves in the plane and that is able to sense only the cyclic order of landmarks with respect to its current position. No metric information is available regarding the robot or landmark positions; moreover, the robot does not have a compass or odometers (i.e., knowledge of coordinates). We carefully study the information space of the robot, and establish its capabilities in terms of mapping the environment and accomplishing tasks, such as navigation and patrolling. When the robot moves exclusively inside the perimeter of the set of landmarks, the information space may be succinctly characterized as an order type that provides information powerful enough to determine which points lie inside the convex hulls of subsets of landmarks. In addition, if the robot is allowed to move outside the perimeter of the set of landmarks, the information space is described with a swap cell decomposition, that is, an aspect graph in which each aspect is a cyclic permutation of landmarks. Finally, we show how to construct such decomposition through its dual, using two kinds of feedback motion commands based on the landmarks sensed.

Multi-resolution recognition of 3D objects based on visual resolution limits

This paper presents a multi-resolution recognition method for 3D objects, based on the human visual model. In the first part of this paper, we propose a new visual resolution limit (VRL) calculation method that considers lens size, the scale of imaging cells and the distance, orientation and velocity of the object. In addition, we simplify 3D models with a novel mesh simplification method based on edge collapse, which controls the simplification degree with VRL. After applying viewpoint space partitioning to the simplified models at different resolutions, we develop a multi-resolution aspect graph library indexed by observation distance. Finally, we propose a 3D object recognition method based on multi-resolution aspect graphs and implement a real-time gradual multi-resolution recognition system that imitates human vision. We design and execute a set of experiments based on plane, car and ship models. Our results demonstrate that our recognition method is effective.

Computation of Edge-Edge-Edge Events Based on Conicoid Theory for 3-D Object Recognition

The availability of a good viewpoint space partition is crucial in three dimensional (3-D) object recognition on the approach of aspect graph. There are two important events depicted by the aspect graph approach, edge-edge-edge (EEE) events and edge-vertex (EV) events. This paper presents an algorithm to compute EEE events by characteristic analysis based on conicoid theory, in contrast to current algorithms that focus too much on EV events and often overlook the importance of EEE events. Also, the paper provides a standard flowchart for the viewpoint space partitioning based on aspect graph theory that makes it suitable for perspective models. The partitioning result best demonstrates the algorithm's efficiency with more valuable viewpoints found with the help of EEE events, which can definitely help to achieve high recognition rate for 3-D object recognition.

House co-registration between imagery and GIS data using aspect interpretation matching

A relational matching approach for imagery-to-GIS data is presented. This method applies image aspect interpretation and geospatial data mining techniques to realize their integration. Three-dimensional (3D) primitives, standing for houses, are chosen and their projections are represented by these aspects. The hierarchy aspect graphs are constructed to represent their interconnected relations. In this connection arcs are described by attribute data via formulated coding regulations. The nodes of the graph represent image features and their attributes can contain measurements on these features. The arcs of the graph represent relations between features and their attributes can contain measurements on spatial relations. Data mining is used to discover the semantic relationship of these primitives. Aerial images are interpreted via these aspects and geospatial data mining. Our experimental results demonstrate that the method presented is capable of effectively interpreting aerial images and extracting high accuracy from the DBM (digital building model) at a rate of 87%.

Aspect graphs for three-dimensional object recognition machine vision systems

The purpose of this research is to seek evidence for viewer-centered (especially aspect-graph-based) visual processing in the elementary task of object understanding. Two homologous, bilaterally symmetrical three-dimensional (3-D) objects have been employed that differ in that one is based on parts with flat surfaces and the other on parts with curved surfaces. The following procedure has been followed, separately for each object. In the training (saturated free inspection and manipulation) phase, a location (identical for both objects) of the object is marked with a red strip and the subjects' task is to memorize the object structure as well as the position of the strip. In the test phase, two-dimensional views of the object without the strip are presented and the subjects' task is to determine whether the previously marked location should be visible or invisible in the particular view. Findings have been found consistent with an aspect-graph-based 3-D object representation: (a) the reaction times and errors show characteristic dependencies on viewpoint; (b) a number of views (corresponding to certain aspects and aspect transitions of the aspect graph) consistently produce faster and more accurate recognition; (c) the differences in the aspect graphs of the two objects are reflected in differing patterns of reaction times and errors; furthermore; (d) the subjects impose a standard orientation on the objects, whereby a strong inversion effect is observed; and (e) performance varies in a similar way for both objects as a function of tilt. It is concluded that object understanding is viewpoint dependent, that is, based on a number of views. The characteristics of the views found to be most important for object understanding can be employed for creating efficient 3-D object recognition machine vision systems. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 47–72, 2005.

Mold Accessibility via Gauss Map Analysis

Abstract In manufacturing processes like injection molding or die casting, a two-piece mold is required to be separable, that is, be able to have both pieces of the mold removed in opposite directions while interfering neither with the mold nor with each other. The fundamental problem is to find a viewing (i.e., separating) direction, from which a valid partition line (i.e., the contact curves of the two mold pieces) exists. While previous research work on this problem exists for polyhedral models, verifying and finding such a partition line for general freeform shapes, represented by NURBS surfaces, is still an open question. This paper shows that such a valid partition exists for a compact surface of genus g, if and only if there is a viewing direction from which the silhouette consists of exactly g+1 nonsingular disjoint loops. Hence, the two-piece mold separability problem is essentially reduced to the topological analysis of silhouettes. In addition, we deal with removing almost vertical surface regions from the mold so that the form can more easily be extracted from the mold. It follows that the aspect graph, which gives all topologically distinct silhouettes, allows one to determine the existence of a valid partition as well as to find such a partition when it exists. In this paper, we present an aspect graph computation technique for compact free-form objects represented as NURBS surfaces. All the vision event curves (parabolic curves, flecnodal curves, and bitangency curves) relevant to mold separability are computed by symbolic techniques based on the NURBS representation, combined with numerical processing. An image dilation technique is then used for robust aspect graph cell decomposition on the sphere of viewing directions. Thus, an exact solution to the two-piece mold separability problem is given for such models.

Aspect graphs for three-dimensional object recognition machine vision systems

The purpose of this research is to seek evidence for viewer-centered (especially aspect-graph-based) visual processing in the elementary task of object understanding. Two homologous, bilaterally symmetrical three-dimensional (3-D) objects have been employed that differ in that one is based on parts with flat surfaces and the other on parts with curved surfaces. The following procedure has been followed, separately for each object. In the training (saturated free inspection and manipulation) phase, a location (identical for both objects) of the object is marked with a red strip and the subjects' task is to memorize the object structure as well as the position of the strip. In the test phase, two-dimensional views of the object without the strip are presented and the subjects' task is to determine whether the previously marked location should be visible or invisible in the particular view. Findings have been found consistent with an aspect-graph-based 3-D object representation: (a) the reaction times and errors show characteristic dependencies on viewpoint; (b) a number of views (corresponding to certain aspects and aspect transitions of the aspect graph) consistently produce faster and more accurate recognition; (c) the differences in the aspect graphs of the two objects are reflected in differing patterns of reaction times and errors; furthermore; (d) the subjects impose a standard orientation on the objects, whereby a strong inversion effect is observed; and (e) performance varies in a similar way for both objects as a function of tilt. It is concluded that object understanding is viewpoint dependent, that is, based on a number of views. The characteristics of the views found to be most important for object understanding can be employed for creating efficient 3-D object recognition machine vision systems. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 47–72, 2005.

The visual hull of smooth curved objects

The visual hull is a geometric entity that relates the shape of an object to its silhouettes or shadows. This paper develops the theory of the visual hull of generic smooth objects. We show that the visual hull can be constructed using surfaces which partition the viewpoint space of the aspect graph of the object. The surfaces are those generated by the visual events tangent crossing and triple point. An analysis based on the shape of the object at the tangency points of these surfaces allows pruning away many surfaces and patches not relevant to the construction. An algorithm for computing the visual hull is outlined.

A Similarity-Based Aspect-Graph Approach to 3D Object Recognition

This paper describes a view-based method for recognizing 3D objects from 2D images. We employ an aspect-graph structure, where the aspects are not based on the singularities of visual mapping but are instead formed using a notion of shape similarity between views. Specifically, the viewing sphere is endowed with a metric of dis-similarity for each pair of views and the problem of aspect generation is viewed as a “segmentation” of the viewing sphere into homogeneous regions. The viewing sphere is sampled at regular (5 degree) intervals and the similarity metric is used in an iterative procedure to combine views into aspects with a prototype representing each aspect. This is done in a “region-growing” regime which stands in contrast to the usual “edge detection” styles to computing the aspect graph. The aspect growth is constrained such that two aspects of an object remain distinct under the given similarity metric. Once the database of 3D objects is organized as a set of aspects, and prototypes for these aspects for each object, unknown views of database objects are compared with the prototypes and the results are ordered by similarity. We use two similarity metrics for shape, one based on curve matching and the other based on matching shock graphs, which for a database of 64 objects and unknown views of objects from the database give a recall rate of (90.3%, 74.2%, 59.7%) and (95.2%, 69.0%, 57.5%), respectively, for the top three matchess cumulative recall rate based on the top three matches is 98% and 100%, respectively. The result of indexing unknown views of objects not in the database also produce intuitive matches. We also develop a hierarchical indexing scheme to prune unlikely objects at an early stage to improve the efficiency of indexing, resulting in savings of 35% at the top level and of 55% at the next level, cumulatively.

Aspect graph construction with noisy feature detectors

Many three-dimensional (3D) object recognition strategies use aspect graphs to represent objects in the model base. A crucial factor in the success of these object recognition strategies is the accurate construction of the aspect graph, its ease of creation, and the extent to which it can represent all views of the object for a given setup. Factors such as noise and nonadaptive thresholds may introduce errors in the feature detection process. This paper presents a characterization of errors in aspect graphs, as well as an algorithm for estimating aspect graphs, given noisy sensor data. We present extensive results of our strategies applied on a reasonably complex experimental set, and demonstrate applications to a robust 3D object recognition problem.

The Expected Number of 3D Visibility Events Is Linear

In this paper, we show that, amongst n uniformly distributed unit balls in $\mathbb{R}^3$, the expected number of maximal nonoccluded line segments tangent to four balls is linear. Using our techniques we show a linear bound on the expected size of the visibility complex, a data structure encoding the visibility information of a scene, providing evidence that the storage requirement for this data structure is not necessarily prohibitive. These results significantly improve the best previously known bounds of $O(n^{8/3})$ [F. Durand, G. Drettakis, and C. Puech, {ACM Transactions on Graphics}, 21 (2002), pp. 176-206]. Our results generalize in various directions. We show that the linear bound on the expected number of maximal nonoccluded line segments that are not too close to the boundary of the scene and tangent to four unit balls extends to balls of various but bounded radii, to polyhedra of bounded aspect ratio, and even to nonfat three-dimensional objects such as polygons of bounded aspect ratio. We also prove that our results extend to other distributions such as the Poisson distribution. Finally, we indicate how our probabilistic analysis provides new insight on the expected size of other global visibility data structures, notably the aspect graph.