cs.CV · 2026-11-06 · No. 165
Computer Vision and Pattern Recognition, 2026-11-06.
16 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
16 entries-
01
USB Gym: A Gymnasium Testbed for Closed-Loop Ultrasound View Matching
Thanapong Intharah, Zhichao Gao, Yiliang Liu, Hao Dong
cs.CV · cs.LG · cs.RO
Background and Objective: Our main goal is ultrasound guidance: moving a probe until its image matches a target view. Published methods for each part of a guide are evaluated in separate simulators. We asked whether these methods, combined into one guide, are good enough. Methods: We built USB Gym, a testbed whose standard engine simulates ultrasound from public patient CT, with a network drawing organ textures from CT labels. Its guide has...
-
02
4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering
Adnan Armouti, Guanyue Qian, Rajalakshmi Nandakumar
cs.CV · cs.GR · cs.LG · eess.SP
Millimeter-wave radar resolves the micrometer displacements of a moving body as micro-Doppler, enabling gait, gesture, activity, pose and vital-sign sensing. Each task relies on a downstream model trained on real data, yet radar datasets lag orders of magnitude behind vision and language. Brute-force collection will not close that gap, and existing synthesis methods (forward-only simulators, learned generators and static-scene inverse...
-
03
DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection
Muhammad Aqeel, Maham Nazir, Marco Cristani, Francesco Setti
cs.CV · cs.AI · cs.LG
Generalist Anomaly Detection (GAD) aims to detect anomalies in unseen domains using only a few reference samples. Recent normal-abnormal guided methods improve this setting by exploiting abnormal references, but their residuals often mix transferable anomaly cues with domain-specific appearance factors such as texture, geometry, and acquisition conditions. This residual domain entanglement limits cross-domain transfer and may produce spurious...
-
04
Improving Context-Shift Robustness of Convolutional Networks via Context-Regularized Cross-Entropy
Jinen Setpal, Chaoyue Liu
cs.CV · cs.LG
Image classification models often encounter objects in diverse and unpredictable contexts at test time, which may differ substantially from those seen during training. This phenomenon, termed context shift, exposes a key fragility in neural networks: when models rely on non-causal contextual cues for prediction, shifts in context can lead to significant performance degradation. In this paper, we propose a novel training framework to improve...
-
05
NutriVisRAG: Multimodal Exemplar Grounding for Nutrient Estimation with Vision-Language Models
Lubnaa Abdur Rahman, Ioannis Papathanail, Maria Panagiotou, Nefeli Dimitropoulou, Margret Harðardóttir, Elisabeth J....
cs.CV · cs.AI
Diet is a major determinant of health, yet accurate dietary assessment from free-living meal images remains challenging. Existing retrieval-based Vision-Language Model (VLM) approaches to nutrient estimation typically rely on textual food representations, while, to our knowledge, direct grounding on visually similar annotated meals has not been investigated. We present NutriVisRAG, a retrieval-augmented generation framework that uses a vision...
-
06
Towards Scalable Diagnostic-Driven Whole-Slide Image Retrieval for Pathology Archives
Jingsong Liu, Youssef Wally Han Li, Weiwei Zhou, Jing Dai, Elisabeth Wetzer, Peter J. Schüffler
cs.CV · cs.AI
The growing adoption of digital pathology has rapidly expanded collections of hematoxylin-and-eosin whole-slide images, yet efficient navigation through these archives remains challenging, as metadata is often inconsistent or unavailable. Content-based image retrieval addresses this challenge by identifying similar cases directly from visual representations instead of manual annotations or metadata. Existing retrieval systems have...
-
07
Structure from Collision via Hypothesis-Space Reasoning
Takuhiro Kaneko
cs.CV · cs.AI · cs.GR · cs.LG · cs.RO
Knowledge of the hidden interior structure of an object, including the presence and location of cavities, is essential for predictive simulation, robotic manipulation, and nondestructive inspection. However, such cavities leave no direct signature on the static visible surface, making collision-induced deformation one of the few cues used to infer their presence. Structure from Collision (SfC) addresses this problem by recovering the hidden...
-
08
InnerLogic-Surg: An Open Surgical Foundation Model via Continual Pretraining
Kun Yuan, Hao Ding, Yiqing Shen, Gasper Podobnik, Benjamin Killeen, Tito Porras, Axel Krieger, Mathias Unberath
cs.CV · cs.AI
Vision foundation models are the backbone of modern surgical image analysis, yet most surgical systems still rely on encoders pretrained on natural images or on specialist models trained from scratch on comparatively small datasets. Pretraining encoders on large amounts of surgery-specific data has the potential to generally enhance the performance of surgical image analysis methods simply by providing stronger backbones. Here we present...
-
09
PlayGen2: Learning Real-Time Playable Worlds with Explicit 3D State
Jihai Zhang, Yuhan Zhou, Junyou Li, Deheng Ye, Qi Dou, Yu Cheng
cs.CV · cs.LG
Building a playable world requires more than generating plausible video: it demands responsive control, persistent spatial structure, and coherent interactions with dynamic entities. Using generated frames as the sole recurrent world representation ties these requirements to view-dependent appearance synthesis, making it difficult to maintain long-term spatial and temporal consistency in generation and interaction. We present PlayGen2, a...
-
10
Enhanced MRI brain tumor detection using deep learning in conjunction with explainable AI SHAP based diverse and multi feature analysis
Asif Rahman, Maqsood Hayat, Nadeem Iqbal, Fawaz Khaled Alarfaj, Salem Alkhalaf, Fahad Alturise
cs.CV · cs.LG
Recent innovations in medical imaging have markedly improved brain tumor identification, surpassing conventional diagnostic approaches that suffer from low resolution, radiation exposure, and limited contrast. Magnetic Resonance Imaging (MRI) is pivotal in precise and accurate tumor characterization owing to its high-resolution, non-invasive nature. This study investigates the synergy among multiple feature representation schemes such as...
-
11
THG-Omni: Traceable Human-Centric Graph Supervision for Video Reasoning
Jisheng Dang, Kai Wei, Ronghao Lin, Bimei Wang, Hong Peng, Wei-Shi Zheng, Bin Hu, Qi Tian, Tat-Seng Chua
cs.CV · cs.AI
Omni-modal models can answer questions about video, but their predictions rarely show which participant, event, or interval supports an answer. Moreover, answer-level supervision alone does not teach a model to interpret structured video evidence. To systematically mitigate this issue, we present THG-Omni, a human-centric graph-supervision framework that links Segment Anything Model~3 participant tracks with temporally grounded Qwen3-VL...
-
12
STAG-Net: Structure-Aware Attention over Landmark Groups for Lightweight Head Pose Estimation
Asiri Gawesha Lindamulage, Sanka Mohottala, Dharshana Kasthurirathna, Nuwan Kodagoda
cs.CV · cs.AI · cs.HC
Head pose estimation is important for human computer interaction and driver monitoring, but many image based methods remain too costly for resource constrained deployment. We propose STAG-Net, a structure-aware attention over landmark groups for lightweight head Pose estimation that estimates head pose from facial landmarks using movement aware selection, spatial clustering, compact DeepSet encoders, self attention, and a global geometry...
-
13
Multimodal Information Interactions Bottleneck for Multimodal Self-Supervised Learning
Liangjian Wen, Jiangtao Zheng, Jiang Duan, Qun Dai, Yong Dai, Jianzhuang Liu, Jun Wang, Shu-Dong Huang, Xinwang Liu,...
cs.CV · cs.LG
Multimodal self-supervised learning is challenged by heterogeneity, unequal informativeness, and complex information interactions across multimodal data sources such as images, text, audio, and tabular data. While contrastive methods effectively align shared semantics, they typically rely on strong multi-view redundancy assumptions, overlooking modality-specific and synergistic information, thus leading to suboptimal representations. We...
-
14
InfMasking: A Unified Variational Framework for Synergistic Multimodal Learning
Liangjian Wen, Qun Dai, Jiang Duan, Yong Dai, Jianzhuang Liu, Dongkai Wang, Jun Wang, Fuyuan Cao, Zenglin Xu, Zhao Kang
cs.CV · cs.AI · cs.LG
Multimodal models are expected to exploit synergistic information, that is, information available only when multiple modalities are observed together. In practice, however, a fusion module can fit the training objective by relying on a dominant modality or on information that modalities share, and the synergy between modalities is often left unused. We propose InfMasking, a unified multimodal learning framework based on Infinite Masking....
-
15
ReferClaw: Disambiguating User Intent for Egocentric Assistance
Hangyu Qin, Junbin Xiao, Angela Yao
cs.CV · cs.AI · cs.MA
Users of egocentric AI assistants often ask short, ambiguous questions whose intended referents cannot be uniquely resolved from video and dialogue history. For example, "Where did I leave it?" may refer to several previously handled objects. Existing VideoQA systems typically commit to a single interpretation, risking plausible but intention-misaligned answers. We introduce ReferClaw, an agentic framework that formulates egocentric streaming...
-
16
UniGADD: Universal Generator-Agnostic Deepfake Detector
Bernard Tomczyk, Agil Aghasanli, Plamen Angelov
cs.CV · cs.AI
In this paper, we introduce Universal Generator-Agnostic Deepfake Detector (UniGADD), a novel method that employs supervised learning to achieve high accuracy on known deepfake generators, while maintaining robust performance on previously unseen ones. The proposed approach follows a two-stage optimisation process. In the first stage, a contrastive loss encourages the model to learn discriminative feature embeddings from real and known fake...
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.