cs.CV · 2026-11-05 · No. 164

Computer Vision and Pattern Recognition, 2026-11-05.

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

01 — The papers

24 entries
  1. 01

    Occlusion for Free: Detecting Occlusion from the Disagreement Between Two Monocular Distance Cues

    Chibueze Praise Onyenweaku, Toyibat Adele, Sikirulahi Opeyemi Abdulkareem, Obed Honour Eje

    cs.CV · cs.AI

    Knowing that a pedestrian is occluded is useful to a robot even when the detector cannot recover the hidden pixels, but occlusion estimators are normally trained on occlusion annotations that deployment settings rarely have. We show that occlusion can be read off two distance estimates a camera-only pipeline already computes. Apparent height is largely unchanged by occlusion, because the detected box still spans the whole person; monocular...

    arxiv.org/abs/2611.06899 · PDF

  2. 02

    CounterFactual Retrieval for Evidence-Aware Individual Animal Identification

    Ankit K. Upadhyay, Aleksandr Algasov, Ekaterina Nepovinnykh, Fedor Zolotarev, Tuomas Eerola, Heikki Kälviäinen,...

    cs.CV · cs.AI · cs.LG

    Automated identification of individual animals is moving from small curated studies toward shared benchmarks and reusable foundation models. This progress is useful, but current evaluation leaves the evidence behind a match unresolved, i.e., high retrieval accuracy does not show whether a model used animal features or identity-correlated shortcuts. We address this with Counterfactual Foreground Retrieval (CFR), an evidence-aware evaluation...

    arxiv.org/abs/2611.06864 · PDF

  3. 03

    Visual Token Routing: Learning to keep tokens that matter

    Pranjal Aggarwal, Sean Welleck

    cs.CV · cs.LG

    Computer-use agents (CUAs) have recently achieved superhuman performance on several long-horizon benchmarks. However, their computational cost limits their use in long-horizon tasks and real-time domains such as video games. A key bottleneck is representing each screenshot as thousands of visual tokens, which accumulate into long contexts as agents reason over extended interaction histories. We observe that most of these visual tokens are...

    arxiv.org/abs/2611.06854 · PDF

  4. 04

    Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models

    Liang Yue, Eric A. Vance

    cs.CV · cs.LG

    Ask SD3.5-Medium for twelve of an object and then, from the same starting noise, for twenty-five. The picture keeps its layout, but the count changes about as much as it would under a new random seed, and in no consistent direction. We study what number words do once a request passes about ten objects, in five open text-to-image models. Holding the object and the starting noise fixed, we change one thing at a time, and people who never see...

    arxiv.org/abs/2611.06840 · PDF

  5. 05

    Route First, See Later: Enabling Vision Agents to Reason Scientifically by Separating Routing Policy from Action Spaces

    Shubhabrata Mukherjee, Jeffrey Donatelli, Daniela Ushizima

    cs.CV · cs.AI

    Scientific image-analysis workflows require agents to select among diverse capabilities like description, detection, counting, and segmentation. Current multi-tool architectures conflate intent interpretation with visual execution, masking whether a failure arises from flawed reasoning (misrouting) or failed perception (invalid tool execution). This lack of auditability renders agents unreliable for high-stakes scientific automation. We...

    arxiv.org/abs/2611.06760 · PDF

  6. 06

    EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models

    Yequan Bie, Dengyang Jiang, Zhixuan Chen, Xiaozhuan Liang, Haoxuan Che, Quande Liu, Xi Chen, Hao Chen

    cs.CV · cs.AI

    Generative video models are increasingly used as visual world simulators, yet their primary strength lies in rendering plausible pixels rather than reasoning about how a world should evolve. Coherent world evolution requires more than visual fidelity: when an event occurs, a model must infer its consequences for the entities in the world and then render the resulting state. For example, after a wild beast appears, the model should not only...

    arxiv.org/abs/2611.06748 · PDF

  7. 07

    TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing

    Ruikang Li, Zixuan Chen, Jiarui Wu, Mingde Yao, Yiyuan Zhang, Yujin Wang, Hanming Deng, Lewei Lu, Tianfan Xue

    cs.CV · cs.AI

    Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. This long-term drift is often mitigated through training on multi-turn data or cross-turn rollouts, potentially altering pretrained priors, or through specialized inference-time mechanisms that are difficult to scale to foundation models. We...

    arxiv.org/abs/2611.06741 · PDF

  8. 08

    Coupled Scene Graph Anticipation: When With-Constraint Recall Hides Structural Inconsistency

    Zeno Nongmaithem, Anushttha Srivastava, Anshit Sinha, Apoorv Sisodia, Suman Chowdhury, Prerana Mukherjee, Rajesh P. Barnwal

    cs.CV · cs.LG

    Scene Graph Anticipation (SGA) predicts object relationships in future video frames. Continuous-time SGA models evolve each subject-object pair with an independent Neural ODE, so relationships sharing an entity cannot influence one another during integration, and nothing prevents mutually exclusive predictions, such as "sitting on" and "standing on", for the same pair. We introduce CoupledSGA, which links such relationships through a...

    arxiv.org/abs/2611.06738 · PDF

  9. 09

    Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

    Shuai Dong, Kanghui Tian, Linghan Chen, Wenqi Shao, Hongrui Wu, Haowen Hou, Yongfu Zhu, Xuehui Wang, Ziyue Wang,...

    cs.CV · cs.CL · cs.LG

    Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with existing approaches emphasizing reward design while retaining a single trajectory-level advantage across turns. Such shared credit can reinforce redundant replies after earlier successes and discourage useful follow-ups after earlier failures. We...

    arxiv.org/abs/2611.06728 · PDF

  10. 10

    Human Motion Prediction via Continual Prior Compensation

    Jianwei Tang, Jian-Fang Hu, Tianming Liang, Xiaotong Lin, Jiangxin Sun, Wei-Shi Zheng, Jianhuang Lai

    cs.CV · cs.AI

    Human Motion Prediction (HMP) aims to predict future human poses at different moments according to observed past motion sequences. Previous approaches mainly treated the prediction of different temporal moments as a single prediction task and learned the predictions of varied moments simultaneously, which would encounter a main limitation: the learning of short-term predictions (referring to ``near-future'' prediction) could be hindered by...

    arxiv.org/abs/2611.06637 · PDF

  11. 11

    Trick-or-Treat: Adversarial Evaluation of Multimodal Medical Reasoning with Synthetic Images

    Oishi Banerjee, Eujin Lee, Sung Eun Kim, Alexandra N. Willauer, Christine Y. Zhou, Zhizhou Yang, Pranav Rajpurkar

    cs.CV · cs.AI

    We used medical image synthesis to create a challenging multimodal evaluation framework that exposes hallucination behaviors in frontier models. Evaluating multimodal reasoning has historically been difficult because existing medical datasets rarely pair different image modalities, such as radiographs and external clinical photographs. To address this gap, we introduce Trick-or-Treat, an adversarial multimodal medical benchmark that pairs...

    arxiv.org/abs/2611.06631 · PDF

  12. 12

    EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

    Mingzhe Zheng, Yue Wu, Jing Tan, Chang Zou, Dengyang Jiang, Zeyue Tian, Xuanhua He, Ryan Xu, Yunyang Ge, Sihui Ji,...

    cs.CV · cs.AI

    Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression, often depends on subjective aesthetics and has no uniquely correct target. Existing approaches typically rely on fixed rewards for visual quality, motion quality, and text alignment that poorly capture emotional intent and can invite reward...

    arxiv.org/abs/2611.06518 · PDF

  13. 13

    Within-Family EfficientNet Scaling under Fixed-Resolution Transfer Learning for Spectral-Domain Optical Coherence Tomography Retinal Disease Classification

    Shkelqim Sherifi

    cs.CV · cs.AI · cs.LG

    Background/Objectives: CNNs perform well in retinal disease classification from spectral-domain optical coherence tomography (SD-OCT), but whether EfficientNet's natural-image scaling hierarchy transfers to medical-image transfer learning at fixed resolution remains unclear. This study evaluates EfficientNet-B0-B7 for four-class SD-OCT classification and accuracy-efficiency trade-offs. Methods: Eight ImageNet-pretrained variants (4.05-64.10M...

    arxiv.org/abs/2611.06452 · PDF

  14. 14

    A Bag of Tricks for Defending Deep Learning-based Face Recognition Pipelines against Backdoor Attacks

    Quentin Le Roux, Marti Jimenez, Yannick Teglia, Philippe Loubet Moundi

    cs.CV · cs.AI · cs.CR · cs.LG

    The protection of mature, multi-stage Face Recognition Systems is crucial to system providers. This technical report targets the threat model most relevant to industry practitioners: although model training is performed in-house, training data is sourced from possibly-compromised third parties. Given this setting, we present three practical defense "tricks" against data poisoning-based backdoor attacks. The first operates at training-time,...

    arxiv.org/abs/2611.06412 · PDF

  15. 15

    Traffic-VL: Reinforced Vision-Language Models for Generalizable End-to-End Traffic Signal Control

    Xingchen Zou, Maonan Wang, Kemou Jiang, Jie Li, Yiqi Chen, Xi Chen, Hai Yang, Yuxuan Liang

    cs.CV · cs.AI

    Existing traffic signal control methods typically rely on structured traffic states produced by dedicated perception pipelines. Emerging visual approaches often use idealized simulator images and convert them into intermediate representations before control, limiting their ability to directly exploit roadside visual observations. To bridge both the visual-domain and perception-to-decision gaps, we introduce SynTra-V and Traffic-VL. SynTra-V...

    arxiv.org/abs/2611.06353 · PDF

  16. 16

    Prism: Bidirectional Self-Teaching for Unified Multimodal Models

    Peng Zhang, Qian Chen, Xianyin Zhang, Yimin Tian, Ruite Fei, Dongyi Lv, Lifan Guo, Chi Zhang, Shuai Liu

    cs.CV · cs.AI

    Unified Multimodal Models (UMMs) aim to support visual understanding and generation within a single model. Existing post-training methods either use understanding as a fixed teacher to improve generation, or rely on ground-truth trajectories to supervise both understanding and generation. Prism instead derives bidirectional supervision from self-generated interleaved rollouts, constructing training targets according to the reliability of...

    arxiv.org/abs/2611.06343 · PDF

  17. 17

    MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection

    Kiet Dang Vu, Cao Le Minh Khoa, Nguyen Viet Tri Pham, An Nguyen Gia, Tam Le Thuc Ho, Duc Dung Nguyen

    cs.CV · cs.AI

    Monocular 3D object detection offers a low-cost route to 3D perception, but it remains fundamentally ill-posed, since depth must be inferred from a single view. Recent transformer-based detectors learn geometry purely from image features and 3D box annotations, lacking the high-level semantic priors that vision-language models (VLMs) acquire from large-scale pretraining. VLMs offer such priors, but deploying one directly as a detector is...

    arxiv.org/abs/2611.06282 · PDF

  18. 18

    Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification

    Dung Do Tien, Kien Nguyen Do Trung, Kiet Dang Vu, Trung Thai Tran, Duc Dung Nguyen

    cs.CV · cs.AI

    While recent feed-forward 3D Gaussian Splatting methods enable efficient driving-scene reconstruction from surround-view images, their reliance on a single observation fundamentally hinders novel-view synthesis. Regions occluded in the input can become visible from novel viewpoints, leaving the reconstructed Gaussians under-constrained and incomplete. Moving beyond image-space inpainting for rendered views, we introduce OccSplat, a...

    arxiv.org/abs/2611.06273 · PDF

  19. 19

    NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation

    Xinhao Lou, Dongye Xie, Peng Sun, Chenyi Zhuang, Kaicheng Yu, Tao Lin

    cs.CV · cs.AI

    Adversarial training enables one- and few-step image and video generation, but conventional adversarial losses supervise critic values without directly specifying the gradients used to update the generator. We present NEXTGAN, which trains a scalar critic by regressing its input gradient onto displacements between independently paired reference and generated features at interpolated locations in frozen representation spaces. For a fixed...

    arxiv.org/abs/2611.06270 · PDF

  20. 20

    Reasoning-Aware Cross-Modal Association Unlearning in Multimodal Large Reasoning Models

    Xinghao Li, Chenchen Tan, Youyang Qu, Shujie Cui, Xingliang Yuan, Cunjian Chen, Chi Liu, Longxiang Gao

    cs.CV · cs.AI

    Multimodal large reasoning models (MLRMs) integrate visual inputs with textual and parametric knowledge, allowing sensitive information to be accessed through cross-modal associations during reasoning. This raises privacy concerns when a visual input should no longer provide access to such information. Machine unlearning can remove this influence without retraining the model from scratch. However, multimodal unlearning methods mainly target...

    arxiv.org/abs/2611.06168 · PDF

  21. 21

    Grounding in the Dark: Text-Only Training for Zero-Shot Video Temporal Localization

    Divyanshu Mishra, Sabine Sternig, Rakshith Shetty, Erhan Gundogdu

    cs.CV · cs.AI

    Video-LLMs are typically trained on paired video-text data for temporal tasks, yet collecting precise temporal annotations and training on large-scale video datasets are both costly. We investigate whether a text-only LLM, with no vision-language pretraining, can be trained on textual video descriptions alone to perform temporal grounding and receive video only at inference time. This setting removes paired video data from training altogether...

    arxiv.org/abs/2611.06149 · PDF

  22. 22

    Many Pixels, One Composition: Self-Supervised Spectra for Specimen-Level Prediction

    Eleftheria Tetoula-Tsonga, George Arvanitakis, Theodoros Giannakas

    cs.CV · cs.LG

    Can hyperspectral (HS) imaging be used to predict the elemental composition of physical specimens found on the Earth's surface? We approach this problem as a supervised regression task, using an open dataset of specimens, each comprising a HS cube and elemental characterization. In particular, we train an encoder in a self-supervised fashion that operates on pixel-level; then freeze the encoder and train a lightweight attention-based...

    arxiv.org/abs/2611.06096 · PDF

  23. 23

    Drift-adaptive Representation Preservation for Domain-Incremental Learning

    Hyunmin Kong, Gyutae Oh, Jitae Shin

    cs.CV · cs.AI

    Pretrained vision models provide strong general-purpose representations, but in Domain-Incremental Learning (DIL), where the input distribution changes sequentially, adapting to new domains often degrades performance on previously learned ones. We observe that forgetting is not uniform across domains and classes and is not explained by training order alone. This motivates us to track each past domain-class concept individually. We use...

    arxiv.org/abs/2611.06093 · PDF

  24. 24

    TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds

    Jiaao Yu, Yanjian Zhang, Haoyang Jiang, Guillaume Wisniewski, Nadi Tomeh, Shijie Jia

    cs.CV · cs.AI

    Recent video world models allow users to explore generated environments through camera navigation. Continuous hand motion provides a fine-grained action channel for interacting with the people and objects encountered during exploration. We present TouchéWorld, a framework that integrates gesture-driven interaction into a camera-controlled video world model. Given an initial image and a scene-description prompt, the model generates video...

    arxiv.org/abs/2611.06061 · 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.