Affordance understanding, the task of identifying actionable regions on 3D objects, plays a vital role in allowing robotic systems to engage with and operate within the physical world. Although Visual Language Models (VLMs) have excelled in high-level reasoning and long-horizon planning for robotic manipulation, they still fall short in grasping the nuanced physical properties required for effective human-robot interaction. In this paper, we introduce PAVLM (Point cloud Affordance Vision-Language Model), an innovative framework that utilizes the extensive multimodal knowledge embedded in pre-trained language models to enhance 3D affordance understanding of point cloud. PAVLM is an approach to integrates a geometric-guided propagation module with hidden embeddings from large language models (LLMs) to enrich visual semantics. On the language side, we prompt Llama-3.1 models to generate refined context-aware text, augmenting the instructional input with deeper semantic cues. Experimental results on the 3D-AffordanceNet benchmark demonstrate that PAVLM outperforms baseline methods for both full and partial point clouds, particularly excelling in its generalization to novel open-world affordance tasks of 3D objects. For more information, visit our project site: pavlm-source.github.io.

Despite the abundance of literature in coordinated signal controls, effectively contending with excessive delay and lane blockage, caused by either turning-bay overflows or mutual impedance between through and turning queues, remains a critically challenging research issue, especially for commuting arterials experiencing near saturated traffic states and highly asymmetric volume distributions during peak hours. Such mutual queue blockages and resulting excessive delay will inevitably reduce the arterial’s capacity and even trigger gridlocks at its upstream intersections and neighboring networks. To address these issues, this study introduces an Event-based Dynamic Adaptive Signal Control System (E-DASCS), designed to detect, classify, and respond to evolving congestion patterns with customized signal control strategies. In real-time operations, E-DASCS will first monitor the spatial-temporal queue evolution over each intersection and classify the detected queue types as one of the four predefined congestion levels. One or a series of signal plans customized to tackle the identified congestion level will subsequently be selected and activated by the system. Performance evaluation with simulation-based experimental scenarios over a highly congested arterial in Bethesda, Maryland, has demonstrated the promising properties of E-DASCS, compared to non-adaptive systems with the same control objectives. For instance, it has yielded delay reductions of 7.39% and 5.46% per vehicle hour, respectively, in the commuting direction and at the network level, along with an increase in traffic throughput and prevention of potential queue spillbacks. The revealed effectiveness and computing efficiency from extensive experimental results demonstrate the potential for the proposed arterial signal system to be implement in practice.

Questionnaire is a conventional approach for fashion designers and educators to survey consumers’ general preferences of products’ appearances; however the precision of survey results remains questionable. The authors proposed an alternative in this pilot study in which five eye trackers were used to record 10 female participants’ eye movement data of gazing at 20 randomly displayed handbag pictures. Six types of Regions of Interest (ROI) of handbags were assigned to understand which regions were more attractive to the participants. The times and duration of fixations showed the degree of ROIs’ attractiveness to the participants. The findings provide persuasive eye-movement evidence of predicting potential female consumers’ gazing behaviors. Textbook editors of fashion design can also add eye-tracking approach to future books. And eye-tracking technology can also help fashion design educators to enhance teaching and students’ learning. Moreover gazing behavior can be broadly considered a form of reading, and the findings of this study further extend the existing knowledge of human reading process.

The scalable video coding (SVC), an extension of H.264/MPEG4-AVC (H.264), was standardized in 2007 by Joint Video Team (JVT). SVC provides spatial, temporal and SNR scalabilities. To achieve these scalabilities, SVC uses additional coding tools and coding modes based on H.264. The coding tools used by SVC and the variety coding modes decision make the corresponding coding complexity become extremely high, so real-time realization of SVC is nearly impossible by using software and single-core CPU only. One possible solution to generate SVC streams in real-time is to parallelize the whole encoding process. Currently, multi-core CPU and GPU are two popular kinds of parallel processing architectures. Not much research has been devoted to realize the parallel SVC encoders based on the co-work of these two architectures. In this paper, a scalable computation model for spatial SVC using multi-core CPU and GPGPU through NVIDIA CUDA is proposed. On the basis of the proposed computational model, a solution to solve the challenging data transition problem (will be detailed later) of this CPU-GPU co-work architecture is then provided. Simulation results show that, through our work, significant speed up gain in spatial SVC encoding can be achieved.

A novel data hiding scheme, denoted as unseen visible watermarking (UVW), is proposed. In UVW schemes, hidden information can be embedded covertly and then directly extracted using the human visual system as long as appropriate operations (e.g., gamma correction provided by almost all display devices or changes in viewing angles relative to LCD monitors) are performed. UVW eliminates the requirement of invisible watermarking that specific watermark extractors must be deployed to the receiving end in advance, and it can be integrated with 2-D barcodes to transmit machine-readable information that conventional visible watermarking schemes fail to deliver. We also adopt visual cryptographic techniques to guard the security of hidden information and, at the same time, increase the practical value of visual cryptography. Since UVW can be alternatively viewed as a mechanism for visualizing patterns hidden with least-significant-bit embedding, its security against statistical steganalysis is proved by empirical tests. Limitations and other potential extensions of UVW are also addressed.

BACKGROUND: Analysis of genomes evolving via block-interchange events leads to a combinatorial problem of sorting by block-interchanges, which has been studied recently to evaluate the evolutionary relationship in distance between two biological species since block-interchange can be considered as a generalization of transposition. However, for genomes consisting of multiple chromosomes, their evolutionary history should also include events of chromosome fusions and fissions, where fusion merges two chromosomes into one and fission splits a chromosome into two. RESULTS: In this paper, we study the problem of genome rearrangement between two genomes of circular and multiple chromosomes by considering fusion, fission and block-interchange events altogether. By use of permutation groups in algebra, we propose an O (n2) time algorithm to efficiently compute and obtain a minimum series of fusions, fissions and block-interchanges required to transform one circular multi-chromosomal genome into another, where n is the number of genes shared by the two studied genomes. In addition, we have implemented this algorithm as a web server, called FFBI, and have also applied it to analyzing by gene orders the whole genomes of three human Vibrio pathogens, each with multiple and circular chromosomes, to infer their evolutionary relationships. Consequently, our experimental results coincide well with our previous results obtained using the chromosome-by-chromosome comparisons by landmark orders between any two Vibrio chromosomal sequences as well as using the traditional comparative analysis of 16S rRNA sequences. ConclusionFFBI is a useful tool for the bioinformatics analysis of circular and multiple genome rearrangement by fusions, fissions and block-interchanges.

We present an optimal chain-code-like representation to code contour shapes; in addition, this representation can be easily extended to a scalable form which structures shape data as the base layer followed by two enhancement layers. A lossy coding scheme is also presented for low-bit-rate applications. Compared with the block-based CAE (context-based arithmetic encoding) method in MPEG-4 and DCC (differential chain coding) with an arithmetic coder, our method not only has a higher compression ratio with fewer computation steps, but also can be applied to layered transmission. The scalability achieved by our scheme can be recognized both spatially and quality-wise. Compared with other scalable shape coding methods, our scheme is simple but more efficient than progressive polygon encoding methods. In case of a base layer with distortion Dn=0.02, our scheme saves about 20-30% of the number of bits, that is, we have a smaller size base layer, which is important in layered transmission.