Skeleton
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Topology-Aware Skeleton Detection via Lighthouse-Guided Structured Inference
arXiv:2604.20123v2 Announce Type: replace Abstract: In natural images, object skeletons are used to represent geometric shapes. However, even slight variations in pose or movement can cause noticeable changes in skeleton structure, increasing the difficulty of detecting the skeleton and often resulting in discontinuous skeletons. Existing methods primarily focus on point-level skeleton point detection and overlook the importance of structural continuity in recovering complete skeletons.
Headless skeletons offer new insights into farming societies 7,000 years ago
Headless skeletons offer new insights into farming societies 7,000 years ago Gaby Clark Scientific Editor Robert Egan Associate Editor Dozens of human skeletons, lying apparently randomly on and next to each other, with their skulls missing, present a terrifying sight at first glance. Since 2022, this is what researchers have been excavating in a 7,000-year-old settlement near the present-day town of Vráble in Slovakia. Are the headless skeletons the remains of a Neolithic massacre,...
Ditch full of 7,000-year-old headless human skeletons discovered in Slovakia, baffling archaeologists
Ditch full of 7,000-year-old headless human skeletons discovered in Slovakia, baffling archaeologists Archaeologists are unsure why people in Stone Age Slovakia removed corpses' heads before burying them in a neighborhood ditch. At the entrance to a Stone Age neighborhood in Slovakia, archaeologists have uncovered a ditch full of headless human skeletons. While the bones reveal cut marks that signal decapitation, researchers think the practice was not a violent mass killing but rather part...
Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition
arXiv:2604.09063v3 Announce Type: replace Abstract: Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiveness of supervised skeleton-based methods, their reliance on exhaustive annotation limits generalization to novel actions. Zero-Shot Skeleton Action Recognition (ZSAR) emerges as a promising paradigm, yet it faces challenges due to the spectral bias of diffusion models, which oversmooth...
SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition
arXiv:2606.03610v1 Announce Type: new Abstract: Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, where only a single labeled exemplar is available for each novel action. A key challenge is learning representations that capture the hierarchical and compositional structure of human motion while aligning effectively with high-level action semantics under extreme data scarcity. Existing...
800-year-old 'hugging skeletons' are genetically confirmed as Poland's only medieval same-sex double burial
The "hugging skeletons" in Opole, Poland, during excavation (top) and an unrelated burial (bottom).
Pompeii excavations reveal equid skeleton at House of the Chaste Lovers
The remains of an equid were discovered in a bakery area of Pompeii's House of the Chaste Lovers complex, offering new insights into the role of working animals in Roman daily life and during the eruption of Mount Vesuvius in AD 79. An equid skeleton has been uncovered during archaeological excavations in a bakery area of Pompeii's House of the Chaste Lovers complex. The Insula of the Chaste Lovers is one of the most important excavation sites in Pompeii because it preserves an entire...
SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code Generation
arXiv:2606.06826v1 Announce Type: new Abstract: With the remarkable progress of Code Large Language Models (Code LLMs) in achieving semantic correctness, execution efficiency has become an increasingly important dimension for evaluating their practical utility. However, existing approaches typically treat full programs as a single optimization target during training, without explicitly modeling the structural factors that influence efficiency. As a result, although these models can generate...
Chiseling Out Efficiency: Structured Skeleton Supervision for Efficient Code Generation
arXiv:2606.06821v1 Announce Type: new Abstract: Large Language Models (LLMs) are capable of generating syntactically correct and functionally complete programs, greatly streamlining software development. However, recent studies reveal that these programs typically execute substantially slower than human-optimized counterparts. Existing approaches to bridging this efficiency gap typically involve either iteratively optimizing code after generation or fine-tuning models on corpora of efficient...
Tensor Algebraic Property Skeletons: Amplifying Property-Based Testing for AI Compilers
Announce Type: new Abstract: Deep learning (DL) compilers such as TVM and ONNX-MLIR lower tensor computation graphs into optimized executables for target backends. Testing these AI compilers has made substantial progress in generating well-formed inputs in the context of fuzzing; however, such generation alone does not catch semantic drifts from algebraic invariants that graph transformations and optimizations are expected to preserve. While tensor algebra has been studied for decades, it...