3D teeth segmentation, involving the localization of tooth instances and their semantic categorization in 3D dental models, is a critical yet challenging task in digital dentistry due to the complexity of real-world dentition. In this paper, we propose 3DTeethSAM, an adaptation of the Segment Anything Model 2 (SAM2) for 3D teeth segmentation. SAM2 is a pretrained foundation model for image and video segmentation, demonstrating a strong backbone in various downstream scenarios. To adapt SAM2 for 3D teeth data, we render images of 3D teeth models from predefined views, apply SAM2 for 2D segmentation, and reconstruct 3D results using 2D-3D projections. Since SAM2's performance depends on input prompts and its initial outputs often have deficiencies, and given its class-agnostic nature, we introduce three light-weight learnable modules: (1) a prompt embedding generator to derive prompt embeddings from image embeddings for accurate mask decoding, (2) a mask refiner to enhance SAM2's initial segmentation results, and (3) a mask classifier to categorize the generated masks. Additionally, we incorporate Deformable Global Attention Plugins (DGAP) into SAM2's image encoder. The DGAP enhances both the segmentation accuracy and the speed of the training process. Our method has been validated on the 3DTeethSeg benchmark, achieving an IoU of 91.90% on high-resolution 3D teeth meshes, establishing a new state-of-the-art in the field.

Word embeddings, which map words into a unified vector space, capture rich semantic information. From a linguistic point of view, words have two carriers, speech and writing. Yet the most recent word embedding models focus on only the writing carrier and ignore the role of the speech carrier in semantic expressions. However, in the development of language, speech appears before writing and plays an important role in the development of writing. For phonetic language systems, the written forms are secondary symbols of spoken ones. Based on this idea, we carried out our work and proposed double-carrier word embedding (DCWE). We used DCWE to conduct a simulation of the generation order of speech and writing. We trained written embedding based on phonetic embedding. The final word embedding fuses writing and phonetic embedding. To illustrate that our model can be applied to most languages, we selected Chinese, English, and Spanish as examples and evaluated these models through word similarity and text classification experiments.

The Document Object Model (DOM) provides a tree structure called DOM tree for representing with objects in HTML. Many researchers have considered using leaf nodes of DOM tree as basic objects in extracting information from web pages. However, web pages are more of information blocks which each have a consistent visual format rather than individual DOM tree nodes. And those information blocks do not necessarily have a direct map to DOM tree nodes. In this paper, we propose a visual oriented extraction method that extracts news content by visual unit (vu, for short). Visual units are identified by a top-down approach based on visual features and text features. After that, page content is extracted according to domain characteristic. In experiments, the proposed approach achieves 94.86% accuracy over 700 news web pages from 7 different news sites. The result demonstrates that our method represents a promising approach for news content extraction with visual units and domain characteristic.

This paper deals with a method of locomotion selection based on Falling Risk and moving efficiency. The robot estimates information from sensors by solving state equation. The robot evaluates the Falling Risk as an indicator of uncertainty. Falling Risk is derived from measured information by using Bayesian Network. Locomotion selection during walking is modeled as a Semi-Markov Decision Process and the most appropriate locomotion is selected by using the greedy algorithm. As a result, the robot can move in the environment that is difficult to travel by single locomotion mode, maintaining the maximum moving efficiency.

For multi-contact robot motion, a closed chain is formed by robot links and the environment. This paper proposes a new methodology named “key joint method” for reducing the energy cost by adjusting an internal stress inside a closed chain. Firstly, we analyze the internal stress theoretically taking the degrees of freedom (DOF) and the number of position actuated joints into consideration, then a practical key joint method is proposed by changing a suitable redundant position controlled joint to be force control. After that, a parametric family is introduced for representing various of possible motions subjected to the robot dynamics and other constraints. Finally, a general optimization method is proposed for planning an energetically efficient multi-contact robot motion taking the motion trajectories and internal stress into consideration. As an example, the pace gait ladder decent motion is taken to explain the principle and realization of the proposed method. As experimental evaluation shows, the key joint method is effective for reducing the energy cost in the multi-contact motion.

We consider a 24-degrees-of-freedom monkey robot that is supposed to perform brachiation locomotion, i.e. swinging from one row of a horizontal ladder to the next one using the arms. The robot hand is constructed as a planar hook so that the contact point about which the robot swings is a passive hinge. We identify the 10 most relevant degrees of freedom for this underactuated mechanical system and formulate a tractable search: (a) introduce a family of coordination patterns to be enforced on the dynamics with respect to a path coordinate; (b) formulate geometric equality constraints that are necessary for periodic locomotion; (c) generate trajectories from integrable reduced dynamics associated with the passive hinge; (d) evaluate the energetic cost of transport. Moreover, we observe that a linear approximation of the reduced dynamics can be used for trajectory generation which allows us to incorporate the gradient of the cost function into the search algorithm.

This paper describes walk-to-brachiate transfer of a multi-locomotion robot (MLR). The MLR has multiple types of locomotion such as biped walking, quadruped walking and brachiation. This transfer is carried out through vertical ladder climbing as the robot must raise its body to start brachiating. As a result we have designed two stable transfer motions from walk to climb and from climb to brachiate, while contact situations and constraints of the robot are changing during the transfers. In addition, we have proposed a control algorithm by considering the reaction force from environment, and the setting of parameter is based on a kinetic model of the robot in order to tolerate relative position errors between the robot and its environments such as rungs of the ladder. The robustness of the designed motions with error corrections is experimentally verified.

With the flurry of research on P2P computing, many P2P technical challenges have emerged, one of which is how to efficiently locate desired resources. Advances have been made in this hot research field, where the pioneers are Pastry, CAN, Chord, and Tapestry. By using the functionality of a distributed hash table, they have achieved fair effectiveness. However they have many common limitations, such as ignoring the autonomous nature of peers, and just supporting weakly semantic functions. According to reality in the distributed network, we propose a content-based location mechanism, which not only keeps the autonomy of peers, but also supports approximate query and finer granularity of content sharing. Furthermore, this mechanism also facilitates P2P system to evolve dynamically. We have also used PeerIS, a P2P based information system used to verify it and obtained satisfactory results.