cs.CV · 2026-08-17 · No. 87

Computer Vision and Pattern Recognition, 2026-08-17.

18 new papers in cs.CV. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

18 entries
  1. 01

    Decoding the Past: An Uncertainty-Aware Deep Learning Framework for Sex Attribution in Prehistoric Hand Stencils

    Karel Becerra, Boris Mederos, Dean Snow, Ramón A. Mollineda

    cs.CV · cs.AI · cs.LG

    Determining the biological sex of the individuals who created Upper Paleolithic hand stencils remains a challenging problem due to the absence of ground truth, population differences between contemporary and prehistoric groups, and the uncertainty introduced by image degradation. Traditional morphometric methods suffer from high structural overlap across sexes, poor cross-population generalizability, and subjective feature engineering. This...

    arxiv.org/abs/2608.14539 · PDF

  2. 02

    Marionette: Predicting World States, Rendering Geometry, Painting Appearance

    Zian Meng, Zhen Li, Chuanhao Li, Qiang Li, Kaipeng Zhang

    cs.CV · cs.AI

    Interactive game world models typically autoregress visual observations directly in pixel or latent space, forcing structured properties such as pose, geometry, and occlusion to be implicitly maintained by the same generative sequence. Over long horizons, errors in these latent world properties accumulate, making consistency and controllability fragile. We explicitly model the evolving world state, delegate exact geometric computation to a...

    arxiv.org/abs/2608.14530 · PDF

  3. 03

    Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings

    Rory Ashton

    cs.CV · cs.LG

    Frozen image embeddings from models such as CLIP are increasingly used to classify paintings by art-historical style, with high reported accuracy. We ask whether this accuracy reflects an understanding of style or the recognition of individual artists. Standard evaluation uses random splits in which works by the same artist appear on both sides, so a classifier can succeed by recognising the painter rather than the movement. We re-evaluate...

    arxiv.org/abs/2608.14435 · PDF

  4. 04

    Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

    Shuo Liang, Yixing Ma, Pengfei Zhou, Xingyan Chen, Zihan Mei, Manting Li, Feihan Chen, Zhiwen Wang, Bin Xu, Haotian...

    cs.CV · cs.AI

    Recent video generators can fabricate realistic depictions of wars, disasters, public emergencies, and other real-world crises, creating substantial risks of misinformation. Existing benchmarks, however, provide limited evidence on detector and generator behavior in such settings, including how detectability varies with generation conditions, how people perceive generated videos, and whether detectors remain reliable during social...

    arxiv.org/abs/2608.14391 · PDF

  5. 05

    GBU-Palm: A Multimodal Video Dataset and Benchmark for Palm Presentation Attack Detection

    Yingjie Ma, Zitong Yu, Wei Jia, Ajay Kumar, Linlin Shen

    cs.CV · cs.AI

    Existing palm presentation attack detection (PAD) datasets are often limited by static imagery, restricted acquisition conditions, or insufficient multimodal video data, hindering systematic evaluation across environments, modalities, and attack types. We present GBU-Palm, a large-scale multimodal video dataset and benchmark containing 21,326 videos from 105 subjects and 210 palms across six acquisition environments, including bona fide,...

    arxiv.org/abs/2608.14389 · PDF

  6. 06

    Intelligent Detection of Mechanical, Electrical, and Plumbing (MEP) Metrics Based on 2D Floor Plans

    Tarandeep Singh Mandhiratta, ANK Zaman, Abdul-Rahman Mawlood-Yunis

    cs.CV · cs.AI · cs.HC · cs.LG

    This research developed a neural network-based model to extract various information from 2D floor plans. We detect lighting symbols, identify the appropriate type of light, and extract the associated texts with lights. The study aims to enable efficient floor designing and determining the number and type of lights needed per floor, i.e., allow efficient design and estimate the power requirement of the floor plan. The model was developed using...

    arxiv.org/abs/2608.14317 · PDF

  7. 07

    Conditional Neural Optimal Transport for Predicting Cellular Phenotypes from Molecular Structure

    Gauthier Avité, Maxime Sanchez-Renauld, Nicolas Bourriez, Auguste Genovesio

    cs.CV · cs.LG

    High-content microscopy enables systematic profiling of cellular responses to chemical perturbations, but the scale of the chemical space makes exhaustive phenotypic characterization experimentally infeasible. This motivates computational models that can predict image-derived phenotypes without acquiring the corresponding treated cells. We formulate molecule-induced phenotype prediction as an inductive conditional transport problem in image...

    arxiv.org/abs/2608.14293 · PDF

  8. 08

    Seeing Red, Thinking Bad: Color Bias in Vision Language Models

    Kohsuke Ide, Ryousuke Yamada, Yoshihiro Fukuhara, Hirokatsu Kataoka, Yutaka Satoh

    cs.CV · cs.AI · cs.CL

    Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation. This motivates careful analysis of how VLMs process visual and textual information. In this work, we study how VLMs interpret text rendered as an image, and investigate the influence of visual styling biases. To this end, we introduce Stealth Visual Prompts, which subtly change visual styling of text, such...

    arxiv.org/abs/2608.14286 · PDF

  9. 09

    Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation

    Nikolai Röhrich, Isabell Hans, Felix Krause, Björn Ommer

    cs.CV · cs.AI · cs.LG

    Text-to-image diffusion models have two major drawbacks that severely limit their practical utility: (1) standard models lack an intrinsic mechanism for continuous, concept-specific guidance (e.g., for precisely controlling how aesthetically pleasing an image looks), and (2) they lack reliability for tasks requiring high local coherence (e.g., generating text or human hands). To tackle these issues, we introduce a novel notion of concept-wise...

    arxiv.org/abs/2608.14172 · PDF

  10. 10

    Self-Supervised Visual On-Policy Distillation

    Yijiang Li, Yijun Liang, Yunjie Tian, Bingyang Wang, Ke Zhang, Zhenfei Yin, Di Fu, Philip Torr, Nuno Vasconcelos

    cs.CV · cs.AI

    Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either a larger, stronger teacher or privileged supervision, such as reference answers or ground-truth regions of interest. This raises a fundamental question: where can informative asymmetry come from when nothing privileged is available? We answer this by inverting where the asymmetry comes from. Rather than adding privileged information to the...

    arxiv.org/abs/2608.14144 · PDF

  11. 11

    SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation

    Jinsheng Quan, Jianhua Li, Siyi Xie, Xuanke Shi, Kewang Deng, Zukai Chen, Feifei Shao, Lei Yang, Quan Wang, Yawei Luo

    cs.CV · cs.AI

    Spatial perception and reasoning from visual observations require recovering geometric structure, establishing correspondences, and understanding spatial relations. Existing approaches typically address these capabilities separately using task-specific architectures or external geometric modules, limiting knowledge transfer among complementary representations of the same physical scene. We introduce SPARGen, a unified multimodal framework...

    arxiv.org/abs/2608.14138 · PDF

  12. 12

    HiCo-GS: Hierarchical Context Aggregation and Geometric Consistency for Octree Gaussian Splatting

    Wei Zhang, Shengkai Yu, Shiqiang Gong, Qi Zhang, Qiang Li, Qi Wang

    cs.CV · cs.AI

    Octree-based anchor Gaussian Splatting has emerged as a scalable representation for city-scale novel view synthesis, where multi-level anchors adaptively capture scene content from coarse building structures to fine architectural details. However, we identify a fundamental limitation in existing methods: cross-level feature isolation, where each level's anchor features are optimized independently with no inter-level communication, causing...

    arxiv.org/abs/2608.14136 · PDF

  13. 13

    Fixed-Budget Gaussian Volume Encoding with Structure-Aware Allocation

    Michael R. Martin, Joseph Insley, Victor A. Mateevitsi, Silvio Rizzi, Kwan-Liu Ma

    cs.CV · cs.AI · cs.CE · cs.GR · cs.LG

    Scientific simulations often produce scalar volumes faster than they can be stored, transferred, and loaded, while in situ reduction must use only a limited share of simulation resources. This work encodes scalar fields as anisotropic Gaussian primitives under a fixed budget. The complete primitive set is allocated analytically from local field structure, including position, orientation, and shape, then refined directly against the scalar...

    arxiv.org/abs/2608.14112 · PDF

  14. 14

    Voxel-based 3D Facies Segmentation from Seismic Data: A Comparative Study

    Duc-Thanh Pham, Minh-Tan Pham, Anh Nguyen, Van Nguyen

    cs.CV · cs.AI

    Seismic facies segmentation has emerged as a significant challenge in geophysics, requiring robust methods and systems to effectively identify geologically analogous facies with limited labeled data. Although existing studies have shown promising results in 2D facies segmentation, they often preprocess the original 3D seismic volumes into sets of 2D slices, typically the inline and crossline directions, and treat this problem as a purely 2D...

    arxiv.org/abs/2608.14058 · PDF

  15. 15

    ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models

    Xinye Li, Lingshuai Lin, Lei Wang, Liuzhou Zhang, Jialin Cui, Qingshan Li, Guanchu Wang, Qingbin Liu, Xi Chen, Jiang...

    cs.CV · cs.AI

    Action-conditioned video world models require low-latency causal generation and reliable responses to game-native controls. Although causal distillation enables one- or few-step video synthesis, extending it to interactive world models remains challenging, as discrete keyboard states and continuous mouse motion must remain aligned with temporally compressed latent chunks during causal training and autoregressive rollout. We introduce ForgeWM,...

    arxiv.org/abs/2608.14022 · PDF

  16. 16

    Content Based Video Narration of Gameplay with Vision Language Models

    Mathew Varghese

    cs.CV · cs.AI · cs.GR

    Live game commentary is scarce: it exists for professional esports broadcasts and almost nowhere else. We present a content-based video narration system that produces spoken, esports-style commentary for arbitrary gameplay recordings using a general-purpose vision-language model (VLM) and a text-to-speech back end, with no game-specific instrumentation, no engine telemetry, and no task-specific training. Three mechanisms carry the system....

    arxiv.org/abs/2608.14016 · PDF

  17. 17

    MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning

    Yingying Fan, Penghui Du, Leyan Zhu, Runze He, Zimeng Wu, Yuxuan Zhang, Liang Chen, Jiahao Xie, Jiangtang Wang,...

    cs.CV · cs.AI

    Understanding tens-of-minutes surgical videos requires long-horizon temporal reasoning, answering what happens before, after, or across stages of a procedure by grounding the question in visual evidence spread across time. Existing approaches handle this poorly: a one-shot vision-language model (VLM) compresses the whole procedure to fit its context window and loses the detail a "before" or "after" question depends on, while video agents that...

    arxiv.org/abs/2608.14015 · PDF

  18. 18

    CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification

    Bingxin Yu, Xueli Wang, Jerry Zhou, Wenyan Wang, Li Wen, Lan Huang, Xin Feng, Fengfeng Zhou, Kewei Li

    cs.CV · cs.AI

    Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound feature categories that are aggregated into five risk levels (TR1-TR5). Although widely adopted in clinical practice, most deep learning approaches focus on binary malignancy classification, while multi-class prediction and explicit utilization of feature-level supervision remain underexplored,...

    arxiv.org/abs/2608.13939 · PDF

This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.