cs.CV · 2026-11-09 · No. 168

Computer Vision and Pattern Recognition, 2026-11-09.

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

01 — The papers

14 entries
  1. 01

    FlowMoP: Stochastic Multi-Person Motion Prediction

    Aadya Agrawal, Ho Kei Cheng, Alexander Schwing

    cs.CV · cs.LG

    Predicting the future motion of multiple people is inherently stochastic: the same observed history admits many plausible continuations depending on intent, coordination, and social context. Yet the dominant paradigm in multi-person 3D motion prediction remains deterministic, with existing methods producing a fixed number of outputs per agent. In contrast, we present a conditional flow matching framework that jointly generates diverse future...

    arxiv.org/abs/2611.09882 · PDF

  2. 02

    Graded convolutional networks: scale invariance without the scale and robustness to unknown blur

    Tanush Shaska

    cs.CV · cs.LG

    The Gaussian jet of an image is a graded vector space: a dilation by $λ$ multiplies derivatives of order $k$ by $λ^{-k}$. Local graded convolutions are exactly homogeneous differential operators, and a local feature is dilation-invariant if and only if it factors through the scale-normalized jet or, without the scale, through the retraction onto the weighted sphere of the grading. Under unknown Gaussian blur the retraction changes only by a...

    arxiv.org/abs/2611.09878 · PDF

  3. 03

    GRAC: Graph-Based Retrieval-Augmented Captioning for Surgical Scene Description

    Rochak Dhakal, Chen Zhao, Soup Cobb, Xin Qian, Xiaofeng Yang, Weihua Zhou

    cs.CV · cs.AI

    Purpose: Surgical operative reports support procedural documentation, surgical training, performance assessment, and workflow review. However, extracting meaningful information often requires extensive manual review and clinical expertise. Automated surgical scene descriptions could reduce this burden by leveraging recurring surgical activities and prior knowledge. Methods: We propose GRAC (Graph-Based Retrieval-Augmented Captioning), a...

    arxiv.org/abs/2611.09866 · PDF

  4. 04

    Breaking the Privacy Promise: Gradient Inversion Attacks on Federated Low-Rank Adapted Vision Transformers

    Ritik K. Badiya, Siladittya Manna, Ashmit Sinha, M Yashwanth, Anirban Chakraborty

    cs.CV · cs.AI · cs.CR · cs.DC · cs.LG

    Parameter-efficient fine-tuning (PEFT) has been increasingly adopted to fine-tune pretrained models with low computational cost and is therefore also preferred in the federated learning paradigm to reduce computational and communication overhead. In this work, we investigate the sparsely explored problem of the risk of private data leakage in LoRA-adapted Vision Transformers (ViTs), where low-rank updates weaken the gradient signal available...

    arxiv.org/abs/2611.09652 · PDF

  5. 05

    Multimodal Training with Knowledge Traction for Video Anomaly Detection

    Xiao Tan

    cs.CV · cs.AI

    The task of weakly supervised video anomaly detection is challenging. Existing approaches mainly model video frame features and determine whether anomalies are present based on their magnitudes. In this work, we propose a novel method that incorporates external knowledge into training to improve model performance, robustness, and generalization. We leverage textual prompts and a large language model (LLM) to establish prior information for...

    arxiv.org/abs/2611.09536 · PDF

  6. 06

    V-STORM: A Structure-Aware Grounded Chain of Thought Dataset for Faithful and Fine-Grained Spatio-Temporal Video Reasoning

    Dian Jiao, Yuqian Yuan, Jiaqi Zhu, Mingjian Gao, Siwen Tan, Yunqi Cao, Jinhui Li, Sijing Li, Zhenxuan Fan, Haoyang...

    cs.CV · cs.AI

    While MLLMs can often identify what happens in a video, they still struggle with fine-grained spatio-temporal reasoning, which requires precise grounding when and where the supporting evidence appears and composing such evidence into a coherent reasoning chain. This challenge is exacerbated by the lack of scalable data construction and evaluation pipelines that provide granular, verifiable supervision linking reasoning steps to explicit...

    arxiv.org/abs/2611.09511 · PDF

  7. 07

    BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression

    Gonçalo Gomes, Bruno Martins, Chrysoula Zerva

    cs.CV · cs.AI · cs.CL · cs.LG

    Reliable uncertainty estimation is important for deploying evaluation metrics in real-world settings, where both input ambiguity and domain shifts are common. In this work, we propose an uncertainty-aware extension of the BEiTScore image captioning metric, producing conformally calibrated confidence intervals alongside alignment scores. Our approach models predictive distributions over human judgments, enabling both accurate scoring and...

    arxiv.org/abs/2611.09505 · PDF

  8. 08

    FusionCLIP: Multimodal Contrastive Pretraining for Fusion Plasma Diagnostics

    Qiang Chen, Xiao Wang, Qingquan Yang, Hao Si, Zikang Yan, Guosheng Xu, Jin Tang

    cs.CV · cs.AI

    Visible-light videos and multivariate diagnostic signals provide complementary observations of tokamak discharges. However, existing fusion pretraining methods, primarily learn representations by reconstructing or predicting observations, leaving the correspondence between these modalities underexplored. Representation learning is further challenged by the fact that plasma-related regions occupy only part of each video frame and diagnostic...

    arxiv.org/abs/2611.09493 · PDF

  9. 09

    SPSC: Zero-Shot Cross-Subject EEG-to-Image Reconstruction via Semantic Preservation and Subspace Calibration

    Yutang Lu, Shuai Jiang, Fei Su, Zhicheng Zhao

    cs.CV · cs.AI

    Pretrained vision-language models and diffusion generators have driven rapid progress in brain-to-image generation, while EEG-based reconstruction is still constrained by low signal-to-noise ratio and cross-subject semantic shifts. Zero-shot cross-subject reconstruction poses even greater challenges: EEG semantic embeddings learned from source subjects deviate from the manifold of image embeddings of the unseen target subject, particularly...

    arxiv.org/abs/2611.09380 · PDF

  10. 10

    HiMEM: Hippocampus-Inspired Memory Consolidation, Pruning, and Composition for Vision-Language-Action Models in 3D Scenes

    Boran Zhao, Yanbin Hu, Jun Ye, Zhenxian Hu, Yuxin Zhai, Jin Cui, Pengju Ren

    cs.CV · cs.AI

    Memory plays a crucial role in long-horizon task execution and cross-task generalization for Vision-Language-Action (VLA) models operating in complex 3D scenes. However, existing VLA memory mechanisms suffer from memory noise, particularly in complex 3D scenes, as stored episodic memories contain extensive redundant details about scene layouts, object configurations, and robot-specific states, which obscure generalizable manipulation...

    arxiv.org/abs/2611.09355 · PDF

  11. 11

    Interpretable Context-Aware Multi-Label Retinal Classification with Dual-Hub Heterogeneous Graph Neural Network

    Proshanto Chanda, Munib Mesinovic, Tingting Zhu, Abhirup Banerjee

    cs.CV · cs.LG

    Multi-label retinal screening requires capturing co-occurring pathologies and clinical context, yet standard multimodal fusion remains opaque. We propose a dual-hub heterogeneous graph neural network (GNN) that couples spatial fundus features and structured clinical covariates through cross-modal message passing while providing inherent interpretability. Rather than relying on post-hoc saliency approximations, our architecture exposes...

    arxiv.org/abs/2611.09309 · PDF

  12. 12

    HMMF-Net: A Lightweight Hierarchical Multi-Frame Multimodal Fusion Network for Accurate Fish Feeding Intensity Assessment

    Phi-Hung Hoang, Van-Manh Tran, Nam-Thuan Trinh, Thi-Thu-Hong Phan

    cs.CV · cs.AI

    Automated fish feeding intensity assessment (FFIA) is important for precision aquaculture and feed cost optimization. However, unimodal methods are vulnerable to acoustic noise and visual disturbances, while existing multimodal frameworks often rely on computationally intensive 3D convolutions or Transformers, limiting their use on edge devices. To address these limitations, we propose HMMF-Net, a lightweight multimodal architecture that...

    arxiv.org/abs/2611.09224 · PDF

  13. 13

    FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection

    Dongxiao Li, Zixuan Hu, Ling-Yu Duan

    cs.CV · cs.AI

    LiDAR-based 3D Object Detection (L3OD) is a fundamental 3D perception task, yet its performance is often compromised by domain shifts arising from diverse sensor configurations and environmental conditions. Existing Test-Time Adaptation (TTA) methods primarily leverage self-supervision in the spatial domain, yet they frequently confound semantic content with domain style due to the sparse, non-Euclidean nature of point clouds. To overcome...

    arxiv.org/abs/2611.09170 · PDF

  14. 14

    Finite-sample Calibration Guarantees for Binary Segmentation

    Bruno Viti, Martin Holler

    cs.CV · cs.LG

    Machine learning based segmentation models are frequently miscalibrated, producing for each pixel a label prediction whose associated confidence does not accurately reflect the true underlying probability. This limitation is particularly critical in high-stakes applications such as medical image segmentation. Although several calibration methods have been proposed, only a small subset of them provides theoretical guarantees on the calibration...

    arxiv.org/abs/2611.09120 · 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.