cs.CV · 2026-11-04 · No. 163

Computer Vision and Pattern Recognition, 2026-11-04.

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

01 — The papers

17 entries
  1. 01

    DreamX: Video Diffusion Model is a Universal Latent Action Learner

    Jisoo Kim, Chaehyun Kim, Junsu Kim, Jiho Park, Seongchan Kim, Eunbeen Hong, Soowon Son, Fu-En Yang, Seungryong Kim

    cs.CV · cs.AI · cs.RO

    Learning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embodiment and appearance. Existing latent action models infer actions from visual transitions, but their representations often entangle the underlying action with irrelevant visual variations, limiting transfer across embodiments. We introduce DreamX, which repurposes...

    arxiv.org/abs/2611.05377 · PDF

  2. 02

    PLANTEUR: A Crop-Type Segmentation Benchmark for Tropical Regions

    Piper Wolters, Gabriel Tseng, Favyen Bastani, Joseph Redmon, Yawen Zhang, Hadrien Sablon, Ando Shah

    cs.CV · cs.LG

    We introduce PLANTEUR, a benchmark for crop-type mapping from satellite images in the French overseas territories. Building on the PASTIS design, PLANTEUR provides georeferenced and aligned Sentinel-2, Sentinel-1, and Landsat-8 sequences with parcel-derived labels spanning six tropical regions and an 8-class label space. We define both a standard test split and a leave-one-island-out protocol to measure cross-territory generalization, and...

    arxiv.org/abs/2611.05223 · PDF

  3. 03

    Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional Understanding

    Zijun Huang, Yingjun Du, Cees G. M. Snoek

    cs.CV · cs.LG

    Vision-language verifiers judge whether an image faithfully matches a textual description, yet existing training pipelines typically rely on static supervision from stronger external judges or curated hard-negative data. Such supervision requires external generation or annotation, is teacher-bounded, and is difficult to adapt as model failures evolve. We introduce PROVE (Perturb-and-Repair Optimization for Vision-Language Evaluation), a...

    arxiv.org/abs/2611.05158 · PDF

  4. 04

    VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models

    Junzhe Chen, Tian Qin, Eugenie Shi, Tianshu Zhang, Qiang Ju, Lijie Wen

    cs.CV · cs.AI

    Multimodal discrete diffusion language models (dLLMs) generate responses through iterative mask prediction and offer a promising alternative to autoregressive large vision-language models. However, they still suffer from hallucination, producing outputs that are plausible under language priors but insufficiently grounded in the image. We argue that hallucination in multimodal dLLMs is not only a token prediction problem, but also a premature...

    arxiv.org/abs/2611.05066 · PDF

  5. 05

    FloMo: 3D Scene Flow as a World Action Model Intermediate for Learning from Human Video

    Jeremy Collins, Namra Patel, Ayush Agarwal, Shitij Govil, Animesh Garg

    cs.CV · cs.AI

    Pretrained video generation models distill internet-scale motion priors into robot policies, but full video is a redundant signal for action prediction. We argue that dense 3D motion is the medium through which video pretraining best transfers to robot actions, and that predicting motion rather than video affords better sample-efficiency for action prediction. FloMo is a 5B video-generation model fine-tuned to predict 3D scene-flow and action...

    arxiv.org/abs/2611.05062 · PDF

  6. 06

    RGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge Report

    Andrey Ignatov, Georgy Perevozchikov, Radu Timofte, Dong Zhang, Zhao Ran, Yang Zhang, Xiaochen Li, Shichang Ju,...

    cs.CV · cs.AI

    On-device RGB photo enhancement is a popular task that is needed for quality improvement of photos captured with mobile devices as well as for retouching of images acquired through other sources. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose participants to design fast...

    arxiv.org/abs/2611.05024 · PDF

  7. 07

    Can saliency maps flag chest radiograph classifier errors at a new hospital? An external validation study

    Aashish Chapagai, Angad Singh Gurtatta, Erik Cambria

    cs.CV · cs.LG · eess.IV

    Saliency maps are offered as a safeguard for medical image classifiers, but whether they reveal individual errors at a new hospital remains largely untested. We trained a convolutional network and a vision transformer on NIH ChestX-ray14 and evaluated 303,768 decisions per model at the training hospital and at two external sites, in the USA and Vietnam, with radiologist-consensus labels. We scored each explanation by its anatomical...

    arxiv.org/abs/2611.05011 · PDF

  8. 08

    Learned Smartphone ISP on Mobile GPUs: Mobile AI 2026 Challenge Report

    Andrey Ignatov, Georgy Perevozchikov, Radu Timofte, Yuhong He, Yuxuan Qiu, Tianyu Hao, Ruoqi Li, Yueqi Yang, Chaoyu...

    cs.CV · cs.AI

    With the increasing importance of mobile camera quality in modern smartphones, growing attention has been directed toward computational photography and advanced image signal processing (ISP) algorithms aimed at enhancing various perceptual attributes of captured images. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI...

    arxiv.org/abs/2611.05008 · PDF

  9. 09

    MiCaDe: Online LiDAR-Camera Miscalibration Change Detection for Autonomous Driving

    Carlo Sgaravatti, Riccardo Pieroni, Matteo Corno, Sergio M. Savaresi, Luca Magri, Giacomo Boracchi

    cs.CV · cs.LG

    Reliable multi-sensor perception in autonomous vehicles requires accurate calibration between cameras and LiDAR. However, calibration drift is often unavoidable in long-term deployments: vibrations, thermal effects, and minor mechanical shocks may alter the relative pose between sensors, leading to systematic errors in downstream fusion tasks. We propose MiCaDe (Miscalibration Change Detection), an online solution detecting when the extrinsic...

    arxiv.org/abs/2611.04912 · PDF

  10. 10

    VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents

    ZhengXian Wu, Qianhao Nie, Zhuohong Chen, Junjie Gao, Yuyao Zhang, Yunyao Yu, Hangrui Xu, Cheng Cheng, Guiyu Ma, Jin...

    cs.CV · cs.AI

    Multimodal agents use web and image tools to answer questions beyond their internal knowledge. Some search tasks use images mainly to identify an initial entity, then rely on text retrieval. These tasks offer limited insight into how agents connect information across images, objects, and search steps. We therefore focus on visual context management. This involves organizing and using visual information and linking it to other findings during...

    arxiv.org/abs/2611.04894 · PDF

  11. 11

    Cycle WAM: Coupling Action and Video through Cycle Consistency

    Qinglin Yang, Jiepeng Wang, Yuxing Huang, Haibin Huang, Kai Xu, Chi Zhang, Ruizhen Hu, Xuelong Li

    cs.CV · cs.AI · cs.RO

    Recent advances in video modeling have driven substantial progress in world action models (WAMs). Existing approaches exploit pretrained video priors by decoding actions from latent representations or inferring them from generated videos. The underlying link is causal: robot actions produce changes in the scene, and video observations of these changes provide evidence for inferring the actions that produced them. However, existing training...

    arxiv.org/abs/2611.04711 · PDF

  12. 12

    DenseTwins: Dense Modality Decoupling for Multimodal Self-Supervision

    Carlo Sgaravatti, Daniele Kopyshevskiy, Davide Secco, Giacomo Boracchi

    cs.CV · cs.AI · cs.LG

    Multimodal perception is central to many computer vision applications, including robotics and autonomous driving, where different sensing modalities provide complementary cues. Self-supervised learning offers a scalable solution for exploiting large amounts of unlabeled multimodal data. However, existing methods either neglect modality-specific information by enforcing feature-space alignment between modalities or learn only global...

    arxiv.org/abs/2611.04710 · PDF

  13. 13

    Therapy-FIS: A Dataset for Assessing Facilitative Interpersonal Skills in Psychotherapeutic Setting

    Qijian Zheng, Wanqing Lin, Yuanfang Wang, Yijun Ge, Jordan Bate, Katie Aafjes-van Doorn, Feng Liu

    cs.CV · cs.AI · cs.CY

    Facilitative Interpersonal Skills (FIS) is a performance-based assessment method that provides a structured framework for evaluating the interpersonal competencies of mental health professionals. However, existing FIS assessment relies heavily on human observer ratings, making the evaluation process labor-intensive, costly, and difficult to scale. Progress toward automated FIS assessment has also been constrained by the lack of publicly...

    arxiv.org/abs/2611.04645 · PDF

  14. 14

    Polyp Matching Using Deep Learning

    Kristian Dalsbø Hindberg, Puneet Sharma, Benedicte Schelde-Olesen, Ulrik Deding, Jakob Frederik Frøkjær Justsen,...

    cs.CV · cs.AI

    A key challenge in colon capsule endoscopy (CCE) analysis is accurately identifying whether multiple images depict the same polyp, which is critical to avoid over-counting and unnecessary clinical interventions. Additionally, this prevents prolonged follow-up colonoscopies where endoscopists search for duplicate polyps without precise localization. This study presents a novel contrastive learning-based approach to polyp matching using a...

    arxiv.org/abs/2611.04624 · PDF

  15. 15

    BtsPruner: Role-Aware Visual Token Pruning for Large Vision-Language Models

    Zihao Qi, Zhibo Zhang, Miaoxin Zhang, Jincheng Cai, Zengqiang Yan

    cs.CV · cs.AI

    Large Vision-Language Models (LVLMs) often process hundreds or thousands of visual tokens, resulting in substantial computational and memory overhead during inference. Existing training-free pruning methods typically estimate token importance using language-model attention, visual attention, or feature similarity. However, these methods treat visual tokens with uniform criteria and overlook that tokens may serve different roles during visual...

    arxiv.org/abs/2611.04537 · PDF

  16. 16

    A Universal Raw-IQ Radar Encoder for Cross-Sensor Human Sensing

    Jonas Leo Mueller, Dario Zanca, Sebastian Hoefler, Jan Petermann, Thomas Altstidl, Naga Venkata Sai Jitin Jami,...

    cs.CV · cs.LG

    Radar-based human sensing typically relies on end-to-end task-specific models trained on hand-chosen signal projections, which generalize poorly across unseen users, tasks, and hardware. We argue that the dominant signal processing choice, the micro-Doppler spectrogram, is a poor starting point for transfer because it keeps the Doppler axis, which carrier frequency rescales, and discards the angular axis, which carrier frequency leaves...

    arxiv.org/abs/2611.04534 · PDF

  17. 17

    E2I-Flow: EEG-to-Image Reconstruction via Wavelet-Temporal Cross-Attention and Conditional Flow Matching

    Haowei Pan, Hwa Hui Tew, Junn Yong Loo, Fuad Noman, Hernando Ombao, Chee-Ming Ting

    cs.CV · cs.LG

    Electroencephalography (EEG)-based visual decoding and reconstruction aims to recover visual information from non-invasive brain signals. But there are challenges due to the complex temporal-frequency characteristics of EEG signals and the difficulty of discrete denoising framework in mapping neural activity to meaningful visual representations. Here, we propose E2I-Flow, an EEG-to-image decoding and reconstruction framework that combines a...

    arxiv.org/abs/2611.04524 · 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.