cs.CV · 2026-10-15 · No. 144
Computer Vision and Pattern Recognition, 2026-10-15.
13 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
13 entries-
01
Player-1: Learning to Play from Synthetic Experience
Mingyu Ouyang, Yiran Wang, Siyuan Hu, Xingyilang Yin, Huiqiang Sun, Guangzhi Wang, Junfu Pu, Cheng Cheng, Honghao...
cs.CV · cs.AI · cs.HC
Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their visually rich worlds and diverse mechanics, remain challenging and offer a demanding next step toward general digital control. Current game-agent learning pipelines often rely on large-scale demonstrations with limited coverage of dynamic game states, while scalable environments for interactive...
-
02
VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution
Hairong Ni, Jiahe Huang, Minghao Guo, Wojciech Matusik, Rose Yu
cs.CV · cs.AI · cs.LG
Generative super-resolution (SR) can recover sharp detail in computed tomography (CT) images from severely downsampled observations, but the missing high-frequency content is not uniquely determined by the low-resolution input. Consequently, visually plausible reconstructions may contain anatomically unsupported vascular detail, such as missing, spurious, or incorrectly connected vessels. To overcome this challenge, we introduce VascuSR, an...
-
03
Quantifying privacy risks in foundation model representations of brain MRI
Imen Bajar, Héber Hwang Arcolezi, Antoine Boutet, Carole Frindel, Mohamed Maouche
cs.CV · cs.AI
Pretrained representations are increasingly used to share and reuse information from medical images without exposing the original scans, but it is unclear how much patient-specific information these representations retain. We investigate this question for brain magnetic resonance imaging (MRI) by evaluating five frozen pretrained encoders spanning different architectures, pretraining objectives, and training domains on two longitudinal...
-
04
Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation
Yuheng Chen, Yufan Chen, Zhuojun Cai, Ruiping Liu, Junwei Zheng, Jiale Wei, Di Wen, Weijia Fan, Kunyu Peng, Jiaming...
cs.CV · cs.AI
Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction, and image captioning. This separation leaves scientific figures, captions, and visual semantics weakly connected, and fails to measure whether a model can produce a single page-level parse that is both structurally faithful and semantically accessible. We introduce Read-Parse-Describe, a...
-
05
Beyond Static Cues: Unified Dynamic Detection of MLLM Backdoors via Dual-Flow Trajectory Analysis
Yinzhen Huang, Jiahe Xie, Yitong Sun, Ruochen Zhang, Xingxing Wei
cs.CV · cs.AI
Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, yet their susceptibility to backdoor attacks remains a formidable challenge. While existing defenses have evolved from visual-centric patch cues to unsupervised internal attention statistics, they are fundamentally constrained by a reliance on static snapshots and attack-specific heuristics. Given the intricate interplay between dual modalities, the...
-
06
Contrastive uncertainty learning for robust multi-structure segmentation in lower-pelvic MR
Bilal Sidiqi, Yipei Wang, Wen Yan, Shaheer U. Saeed, Daniel C. Alexander, Yipeng Hu
cs.CV · cs.LG
Boundary delineation of anatomical structures in prostate MRI is often compromised by regional ambiguity. Automated segmentation methods relying on global overlap loss functions tend to be insensitive to surface deviations, leading to significant errors in ambiguous regions. Most existing uncertainty-aware methods treat uncertainty as a post-hoc quality indicator or prediction filter. We propose Contrastive Uncertainty Learning (CUL), a...
-
07
PAWA: Panoramic Action-conditioned World Modeling for Multiple Agents
Siqi Yang, Yimu Wang, Ziqi Cai, Chengxuan Zhu, Shuchen Weng, Erwin Wu, Zhaofei Yu, Kaipeng Zhang, Boxin Shi
cs.CV · cs.AI
A multiplayer world model must predict how the independent actions of several players change a shared environment, including changes outside a player's current field of view. A point-of-view (POV) video captures such changes only after they enter its field of view, whereas panoramic video records the surroundings in every viewing direction and has served as an intermediate representation of the world state in recent world models. Learning...
-
08
Continual pretraining Prostate MRI ViT Encoder for task alignment
Bilal A. Sidiqi, Yipei Wang, Shaheer U. Saeed, Shiqi Huang, Daniel C. Alexander, Yipeng Hu
cs.CV · cs.LG
Building foundation models for MRI has emerged as a promising direction for advancing medical image analysis and improving accessibility of task specific models. Existing approaches primarily focus on effective pretraining strategies and evaluating their performance across diverse downstream tasks. While these methods show performance gains, limited attention has been given to understanding task alignment between pretraining and downstream...
-
09
DreamHMR: From Video Generation to Human Motion Modeling via Structural Focusing
Zhengjie Xu, Ruihao Gong, Xianglong Liu
cs.CV · cs.AI
Human mesh recovery (HMR) provides a geometric foundation for understanding human motion, but accurately reconstructing both body motion and fine hand articulation from videos remains challenging, especially in real-world scenes where occlusion and partial visibility are common. Video generation pretraining offers rich spatial and temporal priors for this task, but its focus on visual synthesis leaves a gap between these representations and...
-
10
GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation
Yixin Wu, Mingjie Li, Yun Shen, Michael Backes, Yang Zhang
cs.CV · cs.AI · cs.CR
The rapid advancement of large vision language models (LVLMs) has made geolocation inference from images highly accurate and accessible. This poses serious privacy risks: a passive adversary with black-box LVLM access can infer a user's location from a single photo with no metadata. Existing protection methods rely almost exclusively on adversarial perturbation, which introduces perceptible visual artifacts and utility degradation. We...
-
11
SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking
Tomáš Čížek, Matej Straka, Illia Volkov, Matěj Kripner, Ervin Macić, Jiri Matas, Klara Janouskova, Martin Schmid
cs.CV · cs.LG
Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking. Its tracker, inherited from SAM 2, stores information from past frames in a memory bank, managed by a simple First-In-First-Out rule, allowing temporal consistency in complex videos. Several recent methods improve SAM 2 with hand-crafted memory update rules, each targeting a specific failure mode,...
-
12
Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters
Taha Sabir, Alberto Montero Molina, Thinh Quang Ly, Veronika Dmitrenko, Mohammad Yaqub, Tausifa Jan Saleem
cs.CV · cs.AI · cs.LG
Adapting a single vision-language model to medical image parsing requires training choices that reflect the demands of each task. We study task-specific adaptation with Qwen3.5-9B for FLARE 2026 Task 3, covering six task families and seven imaging modalities. Our system couples a shared, frozen 4-bit backbone with LoRA adapters selected from the input question. We customize adapter ranks and prompts, rebalance rare classification targets, and...
-
13
DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding
Boyuan Sun, Deshui Miao, Wenzhao Gao, Shaoyong Jia, Shaohui Jiao, Chi Liu, Yan Shu, Derek Li, Bryan Dai, Shengsheng...
cs.CV · cs.AI · cs.HC
We propose DeltaStreamer, a novel agentic framework for streaming video understanding inspired by how humans observe, remember, and investigate. Streaming video understanding requires a system to retain evidence before knowing which details future queries will need. Existing approaches often obscure event transitions and omit relevant details when compressing video history, and cannot recover missing visual evidence. DeltaStreamer addresses...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.