cs.CV · 2026-08-01 · No. 71
Computer Vision and Pattern Recognition, 2026-08-01.
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-
01
ReToken: One Token to Improve Vision-Language Models for Visual Retrieval
Yao Xiao, Reuben Tan, Zhen Zhu, Yuqun Wu, Jianfeng Gao, Derek Hoiem
cs.CV · cs.AI · cs.LG
Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once is computationally infeasible under GPU memory constraints. We present ReToken, a single learnable embedding trained as an explicit retrieval target that selects a sparse set of query-relevant visual tokens from a pre-filled visual KV cache. Trained on only a small image-QA dataset,...
-
02
MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers
Md. Mehrab Hossain Opi, Robiul Islam Ryad, Md. Umar Faruk
cs.CV · cs.LG
Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices. However, existing PTQ methods typically employ uniform bit-widths across transformer components, overlooking their heterogeneous sensitivity to quantization and leading to inefficient precision allocation. In this paper, we propose {MixFrag, a fragility-guided mixed-precision PTQ framework for Vision...
-
03
ScaFE: Data-Efficient Scar Classification with LLM-Generated Clinical Feature Programs
Ruman Wang, Hangting Ye
cs.CV · cs.LG
Classifying pathological scars from clinical photographs requires distinguishing keloids from hypertrophic scars despite limited expert-labeled data and substantial acquisition variation across hospitals. End-to-end image models remain data-dependent, whereas sending photographs to a hosted vision-language model (VLM) may conflict with local data-governance requirements and yields decisions that are difficult to reproduce and audit. We...
-
04
What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration
Cencen Liu, Wen Yin, Dongyang Zhang, Dongmin Li, Shan Zhao, Bing Su, Tao He, Jielei Wang, Guoming Lu
cs.CV · cs.AI
All-in-one image restoration aims to handle diverse degradations within a unified framework. Existing methods commonly encode heterogeneous degradation conditions in a shared latent space, where degradation-related cues and scene content can remain entangled. We characterize the resulting challenge as dual ambiguity: semantic ambiguity in channel-wise modulation and spatial ambiguity in restoration responses, which can lead to content...
-
05
Negative controls reveal volume-driven confounding in radiomics and imaging foundation model features
Katy L. Scott, Sejin Kim, Joshua Siraj, Caryn Geady, Matthew Boccalon, Mattea Welch, Mogtaba Alim, Andrew J. Hope,...
cs.CV · cs.LG
Radiomics and imaging foundation models promise non-invasive biomarkers of tumour biology, yet predictive signatures may reflect tumour volume or acquisition artifacts rather than meaningful image structure. We introduce READII-2-ROQC, an open-source framework that uses volume-preserving negative controls to assess whether radiomic and deep imaging features capture independent spatial signals. READII-2-ROQC generates voxel-perturbed images...
-
06
ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow
Jin Cao, Zian Meng, Kaipeng Zhang
cs.CV · cs.AI · cs.LG
We present ShadowDancer, a novel approach to any-action, frame-level control of interactive video world models. The obstacle is representational: existing interfaces either encode an action loosely, leaving how it unfolds for the model to improvise, or encode it exactly through structured signals that serve one family and are hard to acquire, so precise control across diverse dynamics remains impractical. Demonstration videos are the natural...
-
07
ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding
Mingkang Dong, Muxin Pu, Jie Li, Bohan Guo, Songruo Chen, Bin Ren, Xu Zheng, Chen Zhao, Tianwen Qian, Mohamed...
cs.CV · cs.AI
Streaming video understanding requires models to continuously retain useful visual evidence before future questions are known. Existing approaches primarily manage the growing visual context according to token importance, temporal redundancy, or segment-level relevance, but rarely organize evidence around objects that persist and evolve over time. Thus, in this paper, we introduce ObjectStream, a training-free framework that treats latent...
-
08
MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
Pouya Ardekhani, Zahra Dehghanian, Morteza Abolghasemi, Hamid R. Rabiee
cs.CV · cs.AI
Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using natural language. However, current 3D Gaussian frameworks are often bottlenecked by restrictive multiview capture requirements, costly scene-specific optimization, and the massive memory overhead of storing dense language features. We present a novel, training-free...
-
09
Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras
Edoardo Ragusa, Giovanni Paolo Canuti, Simone Lugani, Rodolfo Zunino, Paolo Gastaldo
cs.CV · cs.LG · cs.RO
While depth sensors have the potential to complement RGB data for affordance segmentation in wearable robots, their usage seems to remain underexplored. The paper proposes two approaches: a reformulated version of hardware-aware neural architecture search, endowed with a newly designed search space to integrate depth (D) information into small-sized deep networks, and a dedicated fine-tuning approach, including a preprocessing layer to merge...
-
10
Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation
Simone Giano, Lorenzo Severini, Alessandro Galdelli, Adriano Mancini
cs.CV · cs.AI · cs.MM
The deployment of Vision-Language Models (VLMs) in critical domains like disaster management requires high-quality multimodal datasets, especially for transferring knowledge via Data-Free Knowledge Distillation (DFKD). However, existing datasets in this domain either entirely lack descriptive text, such as Incidents1M, or suffer from severe text-image semantic misalignment, such as CrisisMMD. In this work, we present a novel methodology to...
-
11
EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPE
Zexuan Yan, Yuzhou Wu, Yue Ma, Zonghang He, Kaibo Yin, Xiaobing Tu, Yinggui Wang, Jinkui Ren, Xiantao Zhang, Shijian...
cs.CV · cs.AI
Egocentric video offers rich manipulation experience for embodied AI, yet collecting diverse egocentric data across scenes, objects, motions, and embodiments remains costly. We present \method, an egocentric world-action simulator that synthesizes controllable, high-quality manipulation videos to expand scarce real-world training data. \method{} builds on a pretrained video generation prior and introduces two geometry-aware conditioning...
-
12
OPLD: On-Policy Latent Distillation for Multimodal Reasoning
Shoutai Zhu, Tianyang Xu, Bin Sun, Mingyuan Xu, Yu Liu, Qinzhen Guo
cs.CV · cs.AI
Interleaved multimodal Chain-of-Thought (CoT) improves visual reasoning by incorporating auxiliary visual evidence into intermediate reasoning. However, existing approaches remain constrained by externally defined reasoning traces and visual operations, limiting their ability to develop flexible and abstract visual thinking. Reasoning with latent has recently offered a promising direction by internalizing intermediate computation into...
-
13
What Makes Deep Learning Work for Traditional Chinese Medicine Tongue Diagnosis? A Comprehensive Ablation Study
Longxia Gao, Linan Wang, Yuhe Han, Junze Geng, Meng Zhang, Hanqing Zhao
cs.CV · cs.LG
Deep learning has shown promise for automated tongue diagnosis in traditional Chinese medicine (TCM), yet the design space remains underexplored. We conducted a systematic ablation study spanning 20+ model versions under rigorous 5-fold cross-validation on TongueDx2 (5,109 images, 976 expert-annotated) and a merged dataset of 11,101 samples. We compared six backbone architectures, four loss functions, five augmentation strategies, and six...
-
14
Towards Practical Algorithm Selection for Unsupervised Domain Adaptation in Medical Imaging
Yiheng Xiong, Luisa Gallée, Daniel Santak Wolf, Heiko Hillenhagen, Michael Götz
cs.CV · cs.AI
Numerous unsupervised domain adaptation (UDA) algori-thms exist, but for clinical practice, selecting the best-suited one along with proper hyperparameters often remains unclear, as the unlabeled deployment (target) domain prevents direct evaluation. We propose a label-free criterion that jointly selects the algorithm and hyperparameters for UDA. Given a pool of candidate models from multiple algorithms trained with different hyperparameters,...
-
15
Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures
Sweta Banerjee, Alireza Teimoury, Nils Porsche, Alexandra K. Stoll, Viktoria Weiss, Niklas Hargarter, Jonas...
cs.CV · cs.AI
Pathology foundation models (FMs) are models trained on vast amounts of typically unlabeled data and have been shown to yield regularized latent spaces that can be used effectively in downstream classification tasks. This is also true for the classification of mitotic figures vs. other cells. However, it is so far unclear if the latent space of current FMs provides features that are discriminant and spatially suitably resolved to also serve...
-
16
LAST: The Last Query Token Guides Visual Token Pruning for Edge-Cloud Collaborative MLLM Inference
Feng Yang, Xinrui Ju, Keyang Zhang, Xiandong Meng, Rongqun Lin, Howard Leung, Shiqi Wang, Haoliang Li, Chris Xing Tian
cs.CV · cs.AI
Multimodal foundation models are reshaping edge-cloud visual intelligence from task-specific feature pipelines into token-based interfaces, where edge devices encode visual inputs into tokens for a general-purpose cloud MLLM. However, dense visual-token sequences increase cloud-side inference costs. Existing pruning methods mainly target centralized inference: vision-driven methods can operate before cloud execution but are typically...
-
17
ARD-REFSM: Enhancing Reflection Symmetry Detection with Asymmetric Denoising and Rotation Equivariance
Dongfu Yin, Rourou Su, Cong Zhao, Fei Yu
cs.CV · cs.AI
Reflection symmetry detection remains challenging due to interference from asymmetric regions and arbitrary orientations of symmetric patterns. Asymmetric regions introduce background clutter that disrupts symmetric pattern matching, whereas conventional convolutional neural networks lack rotation equivariance, leading to inconsistent feature representations under rotational transformations. To address these issues, we propose an Asymmetric...
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.