cs.CV · 2026-11-16 · No. 173

Computer Vision and Pattern Recognition, 2026-11-16.

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

01 — The papers

22 entries
  1. 01

    BAL: Bidirectional Autoregression in Latent Space for Learning Human Movement Representations

    Genki Kinoshita, Ko Nishino

    cs.CV · cs.LG

    Learning semantically meaningful human movement representations from 3D pose sequences is essential for human behavior modeling. Existing self-supervised methods derive supervision from artificial assumptions, e.g., invariance to augmentation within a certain range or recoverability of masked regions at a certain temporal scale, introducing heuristic hyperparameters that make the learned semantics sensitive to their settings. We propose BAL,...

    arxiv.org/abs/2611.18559 · PDF

  2. 02

    Understanding Contextual Bias in Agricultural CNNs Through Hidden-Neuron Concept Induction

    Abhilekha Dalal, Avishek Das, Samatha Ereshi Akkamahadevi

    cs.CV · cs.LG

    Convolutional Neural Networks (CNNs) can classify images using background-dominated patches that contain little or none of the target object, showing that they exploit contextual information. Previous studies detected this behavior through classification accuracy but say little about what CNN hidden layers represent. We investigate whether Concept Induction can reveal interpretable visual properties associated with hidden-neuron activations...

    arxiv.org/abs/2611.18530 · PDF

  3. 03

    StreamEmbed: Real-Time Indexing from Pixels for Screenshot Retrieval

    Dayoon Ko, Yichuan Wang, Soyeong Jeong, Joseph E. Gonzalez, Gunhee Kim, Sewon Min

    cs.CV · cs.IR · cs.LG

    Screen history can serve as searchable visual memory for people and agents, but unlike an offline corpus, it must be encoded and indexed as each screenshot arrives. OCR-based indexing is fast but loses visual information; visual encoding takes over two seconds. Yet screens change incrementally: most pixels repeat within and across screenshots. This raises a question: do visual encoders need to recompute their representations from scratch for...

    arxiv.org/abs/2611.18516 · PDF

  4. 04

    CoPre-MoE: Consolidating and Preserving MoE for Multimodal Continual Instruction Tuning

    Tao Hu, Ling-Xiang Zhang, Da-Wei Zhou

    cs.CV · cs.AI · cs.LG

    Multimodal continual instruction tuning requires multimodal large language models to sequentially acquire new capabilities without catastrophic forgetting. Mixture-of-experts (MoE) architectures offer a promising way to mitigate task interference through expert specialization and combination. However, while existing MoE-based methods avoid overwriting shared parameters by allocating separate experts for each task, this progressive expansion...

    arxiv.org/abs/2611.18417 · PDF

  5. 05

    AI-Based Multi-View Echocardiographic Image Synthesis using Dynamic Shape Control

    João Freitas, Anca Balinisteanu, Ahmed Youssef, Vitor Hugo Pereira, Jan D'hooge, Sandro Queirós

    cs.CV · cs.AI

    Although automated methods have improved echocardiographic workflows, progress remains constrained by the need for large, well-annotated datasets. As the development of clinical databases is often limited by ethical and logistical challenges, synthetic data generation has emerged as a promising alternative. However, existing approaches commonly rely on left ventricle shape-based supervision or are tailored to specific cardiac views, limiting...

    arxiv.org/abs/2611.18375 · PDF

  6. 06

    Adaptable Watermarking: Transforming Image Watermarking Models via Lightweight Adapters

    Mehrdad Saberi, Vishal Asnani, Shruti Agarwal, Soheil Feizi, John Collomosse

    cs.CV · cs.CR · cs.LG

    We explore the adaptability of neural image watermarking models; the extent to which one watermarking method can be transformed into another through lightweight adaptation. We introduce a framework that enables encoder-decoder watermarking architectures to become modular and upgradable, supporting multiple watermarking styles without re-training full models. Adaptation is performed by attaching a compact parameter-efficient adapter and...

    arxiv.org/abs/2611.18363 · PDF

  7. 07

    EcoVGGT: Pinned-Key Inference for Efficient and Streamable Feed-Forward 3D Reconstruction from Long Videos

    Hongsen Cao, Shanxin Yuan, Mona Jaber, Ahmed Sayed

    cs.CV · cs.AI

    Feed-forward multi-view transformers such as VGGT recover the cameras and geometry of a video in one pass, but the cost of their cross-frame attention grows quadratically with the frame count, and their accuracy drops on long videos. Most remedies approximate attention over all frames within a budget or select a few keys by their content. We hypothesize that the keys of a long video can be chosen without looking at its content, and our...

    arxiv.org/abs/2611.18099 · PDF

  8. 08

    AG-JEPA: Anatomically Guided Joint Embedding Predictive Architecture for Neurodegenerative Representation Learning

    Azad Singh, Ayantika Das, Amog Rao, Aiman Farooq, Anirban Porya, Ananya Shukla, Sowbhagya Suresh, Srinivasan...

    cs.CV · cs.AI

    Brain MRI can reveal early signs of Alzheimers disease (AD) before measurable cognitive decline becomes apparent. However, during the transition from cognitively normal (CN) to mild cognitive impairment (MCI), the disease-related signals are often subtle and confined to only a few brain regions. Existing Joint Embedding Predictive Architecture (JEPA) models learn general structural representations but do not explicitly capture the anatomical...

    arxiv.org/abs/2611.18097 · PDF

  9. 09

    TelePhysica: Agentic Reconstruction of Physically Interactive Scenes

    Ruiqi Shu, Xufeng Zhan, Yuanzhi Liang, Haibin Huang, Chi Zhang, Xuelong Li

    cs.CV · cs.AI

    Direct image-to-video diffusion models entangle pixel synthesis with implicit latent motion, precluding persistent 3D mechanical equilibrium, mid-rollout intervention, and counterfactual force control. Conversely, single-pass programmatic 3D reconstruction from an uncalibrated photograph leaves monocular depth and support clearance underconstrained, causing reconstructed scenes to interpenetrate or collapse under gravity. We present...

    arxiv.org/abs/2611.18078 · PDF

  10. 10

    JaRS: Contrast-Free Localization of Memorized Regions in Diffusion Models via Jacobian Row Sums

    Saisuchith Mahajan, Aditey Nandan, Rohit Singh, Nishanth Shetty, Chandra Sekhar Seelamantula

    cs.CV · cs.LG

    Diffusion models sometimes memorize and reproduce regions of their training images, raising privacy and copyright concerns. We aim to localize these regions. Existing contrast-based methods use the diagonal of the denoiser Jacobian, which reflects the posterior variance of each pixel. However, a small diagonal entry is ambiguous: it signals either memorization or averaging over many neighboring pixels in smooth or predictable regions. To...

    arxiv.org/abs/2611.18024 · PDF

  11. 11

    From Images to Grounded Edits: A Real-World Benchmark for Chinese Grammatical Error Correction in Handwritten Essays

    Weiru Zhang, Yuzhong Hong, Junwei Bao, Lemao Liu, Dejing Dou

    cs.CV · cs.AI

    Chinese Grammatical Error Correction (CGEC) is typically formulated as a text-to-text problem. While suitable for digital texts, this formulation falls short in real-world K-12 education, where AI-assisted corrections are expected directly on essay images, which are primarily handwritten and exhibit many irregularities. To bridge this gap, we introduce Grounded Chinese Grammatical Error Correction (G-CGEC), an image-to-grounded-edit task...

    arxiv.org/abs/2611.17966 · PDF

  12. 12

    Domain Adaptation Based Pipeline for Character Classification and Handwritten Text Recognition

    Florent Imbert, Simon Corbillé, Hui Han, Elisa H. Barney Smith

    cs.CV · cs.LG

    Character classification and handwritten text recognition, particularly in specialized tasks, often suffer from limited labeled data, while a large amount of unlabeled data remains unused. To address this challenge, we propose a novel unsupervised domain adaptation-based pipeline to reduce the distribution gap between source and target domains. Our pipeline follows three main steps. In the first step, we pretrained an expert model on source...

    arxiv.org/abs/2611.17952 · PDF

  13. 13

    More Genes, Faster Inference: Efficient Large-Panel Spatial Transcriptomics Prediction from Histology

    Songming Zhang, Yuxiao Luo, Shifu Luo, Siran Chen, Shuquan Su, Jinyan Li

    cs.CV · cs.AI · q-bio.QM

    Spatial transcriptomics (ST) prediction from histology aims to infer spatially resolved gene expression profiles directly from tissue images. This is a challenging problem that is currently often addressed with complicated model architectures, additional inputs, and complicated training procedures, while remaining limited to fixed, small gene panels. This raises a natural question: Is there an efficient method for large-panel ST prediction?...

    arxiv.org/abs/2611.17899 · PDF

  14. 14

    Photogrammetric 3D Model-Based Animal Behavior Classification

    Olaf Hellwich, Moritz Heine, Patrik Reiske, Sole Traverso, Katharina Hohlbaum, Henning Sprekeler, Christa...

    cs.CV · cs.AI

    Video-based behavior estimation is often implemented end-to-end from image sequences. We advocate a two-stage alternative: reconstruct 3D body and object geometry before classifying behavior. This makes ambiguities of the ill-posed 2D-to-3D inverse problem explicit and potentially correctable. We demonstrate the strategy with simulated interacting mice and extend it to real video.

    arxiv.org/abs/2611.17881 · PDF

  15. 15

    DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite Imagery

    Kailai Sun, Zijie Gao, Mingyi He, Can Rong, Alok Prakash, Baoshen Guo, Shenhao Wang, Jinhua Zhao

    cs.CV · cs.AI

    Cities account for over two-thirds of the world's energy and more than 70% of global carbon dioxide emissions. City energy is essential for achieving the 2050 net-zero target and the UN's Sustainable Development Goals 7 and 11. Although existing studies have made progress, they are limited by data and methodological gaps. Existing studies are largely predictive for existing cities rather than generative for future cities; fine-grained,...

    arxiv.org/abs/2611.17878 · PDF

  16. 16

    V-JEPA-LM: Video-Language Models That Read Dynamics Beyond Static, Text-Aligned Representations

    Keuntae Kim, Dongjun Kim, Yong Suk Choi

    cs.CV · cs.AI

    World-model video encoders such as V-JEPA learn how scenes change (direction, speed, order, state) from video alone. To answer questions, they are joined to a language model trained on captions and question-answer pairs. But each caption or question names only a few attributes of a clip, so the model learns to retrieve those attributes rather than to read the clip, and the dynamics the encoder carries go unused: on the same items, a linear...

    arxiv.org/abs/2611.17831 · PDF

  17. 17

    SceneAgent: A Multi-Agent Framework for Portable Game Scene Generation

    Xingyi Li, Jiahao Yang, Yiqin Zhu, Jingwen Ye, Yang Sun, Weidong Zhang

    cs.CV · cs.AI

    Moving a scene generator to a new game engine requires more than exporting its final output: planning, construction tools, and stored experience may also depend on the original backend. We present SceneAgent, a multi-agent framework for reusing the construction process and its experience across backends. A canonical SceneContext maintains the evolving world, while backend adapters isolate coordinate conventions, asset bindings, and export....

    arxiv.org/abs/2611.17821 · PDF

  18. 18

    Can Large Language Models Optimize Pretrained Neural Network Weights? A Multi-Phase Empirical Evaluation of Gradient-Free Editing in YOLO26 Object Detection

    Mohamed Abdallah Salem

    cs.CV · cs.AI

    Direct weight editing offers a gradient-free alternative to fine-tuning pretrained detectors, but its generalization and the value of large language model (LLM) guidance remain uncertain. We evaluate five experimental phases using YOLO26 models and MS COCO, comparing deterministic scaling, random perturbations, differential evolution, CMA-ES, structured interventions, real local-LLM proposals, failure-aware guidance, and hybrid LLM-CMA-ES...

    arxiv.org/abs/2611.17789 · PDF

  19. 19

    Towards Seconds-level Video Representation: Quadratically Gated Feature Grid with Adaptive, Prediction-free Sampling

    Tie-Yun Li, Hao-Ran Wang, Chao Wang, Zhiyong Yin, Yiming Xu, Zhenwei Cai, Li Li, Rongzhi Lin, Feng-Lei Fan

    cs.CV · cs.AI

    Implicit neural video representations are notoriously slow to build, which does not cross the basic practical threshold for most industrial applications. Here, we present Q-GAS, a coordinate-queryable video representation that couples multi-resolution explicit 3D feature grids with a compact SwiGLU-style quadratic-gating (QG) decoder and an error-aware, prediction-free sampler. The explicit grids avoid hash-collision coefficient sharing at...

    arxiv.org/abs/2611.17786 · PDF

  20. 20

    Learning Anisotropic Prediction Targets for Flow Models

    Rayhan Zirvi, Hansheng Chen, Gordon Wetzstein, Leonidas Guibas

    cs.CV · cs.LG

    Flow-based generative models are trained on a hand-chosen prediction target, such as the velocity, the noise, or the clean data. This choice strongly affects training and sample quality. We introduce Anisotropic Flow Models (AnisoFlow), which replaces a fixed prediction target with a fully learnable one. AnisoFlow learns to scale the noise component of the target anisotropically, assigning a separate nonnegative weight to each direction in a...

    arxiv.org/abs/2611.17767 · PDF

  21. 21

    Creative Product Design under Brand Image Constraints

    Takeshi Onishi, Hiroya Makino, Takahiro Yamaguchi, Hiroyuki Sakai

    cs.CV · cs.AI · cs.GR

    Industrial design requires creative visual exploration while satisfying constraints that are often product-specific and implicit. Existing text-to-image (T2I) approaches can generate creative designs through concept blending or multi-agent self-enhancement, but they provide limited mechanisms for ensuring that generated designs remain consistent with such constraints. We focus on brand image as a representative design constraint and propose a...

    arxiv.org/abs/2611.17762 · PDF

  22. 22

    Efficient Genotype Classification from 3D MRI in ADPKD via Density-Aware Point Sampling and E(3)-invariance

    Kwanghee Lee, Hyeongsub Lee, Youngwoo Kim, Hyunji Jeong

    cs.CV · cs.LG

    Early detection of genetic kidney diseases, especially autosomal dominant polycystic kidney disease (ADPKD), is crucial because certain genotypes such as truncating PKD1 mutations cause rapid kidney growth and early progression to end-stage kidney disease. MRI-based genotype inference is a potential low-cost complement to genetic testing. However, although many deep learning methods have been developed for classifying various MR images,...

    arxiv.org/abs/2611.17758 · 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.