cs.CV · 2026-07-13 · No. 52
Computer Vision and Pattern Recognition, 2026-07-13.
29 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
29 entries-
01
Scalable Visual Pretraining for Language Intelligence
Yiming Zhang, Zhonghan Zhao, Wenwei Zhang, Haiteng Zhao, Tianyang Lin, Yunhua Zhou, Demin Song, Kuikun Liu, Haochen...
cs.CV · cs.AI · cs.MM
The rapid progress of large foundation models has been driven predominantly by pretraining on large-scale text corpora. However, many forms of knowledge are conveyed through visual representations, where figures, typeset equations, and page layouts carry rich information that cannot be faithfully or completely captured by text alone. Yet current pretraining approaches discard these visual cues by converting visually rich sources, such as...
-
02
Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models
Shravan Murlidaran, Miguel P. Eckstein
cs.CV · cs.AI
Vision language models (VLMs) have made remarkable progress in visual reasoning during the last decade. Most evaluations have used simple scenes (MS-COCO) that do not showcase complex human interactions or behaviors, only a handful of non-curated human descriptions as a benchmark, and have not focused on understanding the model's error types. Here, we introduce the Complex Social Behavior (CSB) dataset, containing 100 images depicting complex...
-
03
4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception
Xiaokai Bai, Lianqing Zheng, Runwei Guan, Songkai Wang, Siyuan Cao, Hui-liang Shen
cs.CV · cs.AI
Reliable autonomous driving requires full-scene perception that couples foreground objects with dense semantic layout. Recently, 4D millimeter-wave radar has emerged as a robust and affordable sensor, yet its sparse returns make radar-camera fusion necessary for comprehensive scene understanding. Existing radar-camera methods mainly optimize detection, while dual-task systems usually decode boxes and occupancy with limited interaction. To...
-
04
TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models
Tianyou Jiang, Ziyu Zhou
cs.CV · cs.AI
Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretraining. Existing few-shot adaptation methods typically introduce additional trainable components, which can be unstable in extremely low-data regimes (e.g., 1-shot), and lack robustness on different medical data. We present TCLA,...
-
05
The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs
Ahmed Oumar El-Shangiti, Abzal Nurgazy, Hilal AlQuabeh, Nikolai Rozanov, Kentaro Inui
cs.CV · cs.LG
Despite strong performance on many multimodal tasks, vision-language models (VLMs) still struggle with basic object counting. We investigate whether this reflects missing internal knowledge or a gap between internal representations and verbalized outputs. Training simple probes on activations from four VLMs across five counting datasets reveals that nonlinear probes can reliably detect counting errors, suggesting that VLMs often encode the...
-
06
ALICE: Learning a General-Purpose Pathology Foundation Model from Vision, Vision-Language, and Slide-Level Experts
Jiawen Li, Tian Guan, Huijuan Shi, Xitong Ling, Mingxi Fu, Anjia Han, Chao He, Yonghong He
cs.CV · cs.AI
Foundation models are reshaping computational pathology, yet their capabilities remain shaped by pretraining objectives, data sources, and spatial scales, fragmenting complementary expertise across separate backbones. Here we present ALICE, a unified foundation model trained through multi-stage agglomerative distillation that sequentially distills eight vision-only, vision-language, and slide-level teacher models into dedicated modules of a...
-
07
Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference
Junfei Zhan, Haoxun Shen, Mingang Guo, Zixuan Huang, Tengjiao He
cs.CV · cs.AI
Vision-Language Models (VLMs) are the perceptual backbone of embodied AI, but their energy footprint on edge hardware remains poorly understood. Existing efficiency efforts focus predominantly on reducing visual tokens, implicitly treating visual processing as the dominant energy cost. We overturn this implicit assumption through the first systematic energy profiling of on-device VLM inference, spanning five models across three architecture...
-
08
What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility
Filippo Ziliotto, Luciano Serafini, Lamberto Ballan, Tommaso Campari
cs.CV · cs.AI
A fundamental challenge in 3D reconstruction and robotic localization is co-visibility: determining which image pairs share overlapping visible surfaces, particularly in scenarios with minimal overlap. We demonstrate that VGGT implicitly encodes co-visibility as an emergent behavior: without any supervision for this task, its internal representations exhibit a clear hierarchical structure mirroring that of large language models, i.e. early...
-
09
Decoupling Language Guidance from Backbones for Text-Guided Medical Segmentation
Yungeng Liu, Xuanzi Fang, Haijin Zeng, Qi Dai, Yongyong Chen
cs.CV · cs.AI
Text-guided medical image segmentation leverages clinical semantics to improve lesion delineation, yet many existing models bind cross-modal fusion, supervision, and decoder design into a task-specific architecture. Such tight coupling makes it difficult to reuse language guidance modules across heterogeneous vision and text backbones, and often requires redesigning the network when the encoder pair changes. This paper presents BTHA, a...
-
10
Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers
Ibrahim Batuhan Akkaya, Kishaan Jeeveswaran, Bahram Zonooz, Elahe Arani
cs.CV · cs.LG · cs.NE
The human visual system (HVS) employs foveated sampling and eye movements to achieve efficient perception, conserving both metabolic energy and computational resources. Drawing inspiration from this robustness and adaptability, we introduce the Foveated Dynamic Transformer (FDT), a foveation-guided dynamic token-selection architecture that integrates these mechanisms into a vision transformer framework. The FDT exhibits strong resilience to...
-
11
Robustifying Vision-Language Models via Test-Time Prompt Adaptation
Xingyu Zhu, Huanshen Wu, Shuo Wang, Beier Zhu, Jiannan Ge, Jiaheng Zhang, Long Chen
cs.CV · cs.LG
Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations. Existing test-time adaptation methods typically rely on sample-level confidence heuristics, overlooking the intrinsic distributional structure of the data. This sample-centric approach limits robustness, as it fails to distinguish confident adversarial mispredictions from true...
-
12
Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification
Anil Osman Tur, Tonje Knutsen Sordalen, Kim Tallaksen Halvorsen, Cigdem Beyan
cs.CV · cs.AI
Long-term animal re-identification (ReID) must remain robust to gradual morphological evolution and seasonal appearance shifts. Although recent vision-language models provide strong pretrained visual representations, adapting them to longitudinal ecological settings remains challenging, particularly under identity and temporal distribution shifts. We present a parameter-efficient CLIP adaptation framework for animal ReID and introduce a...
-
13
Multimodal Scenario Similarity Search for Autonomous Driving
Tamás Matuszka, András Tamásy, Balázs Szolár
cs.CV · cs.LG
Large-scale autonomous-driving datasets contain vast numbers of recorded scenarios, creating a need for efficient retrieval methods that can identify situations similar to a given query. Existing approaches typically rely on either visual representations or motion-based descriptions, making it difficult to understand their relative strengths and limitations for scenario retrieval. In this work, we present a multimodal framework for...
-
14
SVF-CR: Synchronized Visual-Facial Cross-Refinement for Multimodal Ambivalence and Hesitancy Recognition
Hyein Park, Namho Kim, Junhwa Kim
cs.CV · cs.AI
Ambivalence and hesitancy are subtle behavioral states that are expressed through a combination of verbal content, facial behavior, visual context, and acoustic cues. Effective recognition therefore requires not only extracting informative unimodal representations, but also modeling how temporally aligned behavioral evidence interacts across modalities. In this paper, we propose a synchronized visual-facial cross-refinement framework (SVF-CR)...
-
15
CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation
Seungyong Lee, Hyun Jun Jang, Sangoh Kim, Sungjoon Park
cs.CV · cs.AI
Virtual try-on (VTO) has made significant progress in realistically transferring garments onto a target person. Yet most systems give the user little control over how a garment should be worn -- its size (loose or fitted), style (e.g., tucked in or untucked, open or closed), and spatial placement on the body. We address this gap with two complementary contributions. First, we define and solve Visual-Instance-Prompt Segmentation via VIP-SAM:...
-
16
From Classification to Localization and Clinical Validation: Large-Scale Development of a Deep Learning System for Thoracic Disease Detection on Chest Radiographs in Thailand
Isarun Chamveha, Tretap Promwiset, Napat Wanchaitanawong, Trongtum Tongdee, Pairash Saiviroonporn, Warasinee Chaisangmongkon
cs.CV · cs.LG
Chest radiography (CXR) remains the most widely used thoracic imaging modality, yet expert interpretation is constrained by a severe shortage of radiologists in Thailand and across Southeast Asia. Local adaptation of deep learning models to Thai data has been shown to substantially improve accuracy on Thai populations. Here we present the development and comprehensive validation of the chest radiograph analysis model in Inspectra CXR version...
-
17
IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation
Yiting Wang, Jingyi Zhang, Wenhu Zhang, Ke Chao, Yves Liang, Kun Cheng, Kang Zhao
cs.CV · cs.AI
While large-scale text-to-image generative models have achieved unprecedented visual performance, their inherent reliance on multi-step iterative solvers incurs severe inference latency. Few-step distillation targeting the Classifier-Free Guidance (CFG) trajectory has emerged as the prevalent dual-dimensional compression paradigm. However, existing frameworks remain subjugated by a coarse-grained blind injection paradigm that perpetually...
-
18
Event Stream based Multi-Modal Video Anomaly Detection: A Benchmark Dataset and Algorithms
Peipei Zhu, Yueqing Niu, Lin Zhu, Guanchong Niu, Yang Yu, Zheng Li
cs.CV · cs.AI · cs.MM
Video anomaly detection (VAD) is critical for automated surveillance but remains fragile under challenging conditions such as illumination variations, fast motion, and complex backgrounds when relying solely on visible light videos. To address these limitations, we propose EVAD, an event enhanced VAD framework that jointly exploits conventional video and event streams captured by bio inspired event cameras. Event sensors asynchronously...
-
19
Integrating Large Language Models and Graph Convolutional Networks for Semi-Supervised Image Classification
Camila Piscioneri Magalhães, Lucas Pascotti Valem
cs.CV · cs.AI
While the growing availability of image data has driven significant advances, labeling datasets remains costly and time-consuming. Therefore, semi-supervised approaches such as Graph Convolutional Networks (GCNs), which learn from both labeled and unlabeled data, have emerged as a promising solution. One of the primary challenges in applying GCNs to image classification is graph construction, since, unlike in citation networks or similar...
-
20
A Coreset Selection Framework with Ensemble Aggregation for Image Classification
Pedro Rocha Dantas, Lucas Pascotti Valem
cs.CV · cs.AI
The rapid growth of image data has produced large-scale datasets, raising concerns about the time and memory costs of model training. Selecting representative training subsets, however, remains challenging: individual sample contributions are unclear, and model behavior varies across datasets and runs. We address these challenges with a framework that combines coreset selection with an ensemble aggregation over multiple runs. For coreset...
-
21
OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents
Yang Chen, Yunwen Li, Yufan Shen, Minghao Liu, Tianyu Zheng, Bin Fu, Qunshu Lin, Zhi Yu, Botian Shi
cs.CV · cs.AI
Recent advancements in LVLMs necessitate robust benchmarks for complex, visually grounded reasoning. A critical limitation is identified in many document understanding benchmarks: visual content is often reducible to text, enabling high performance without genuine visual grounding. To address this limitation, OmniMapBench is introduced to foster visual-centric reasoning for map documents. The benchmark comprises 2,096 manually annotated...
-
22
On Locality and Length Generalization in Visual Reasoning
Pulkit Madan, Sanjay Haresh, Reza Ebrahimi, Sunny Panchal, Apratim Bhattacharyya, Roland Memisevic
cs.CV · cs.AI · cs.LG
A striking feature of the human visual system is that it ingests visual information through a series of local foveated glimpses, rather than a single global computation. This makes human vision distinctly different from most popular computer vision models in use today, which input images globally and in a single shot. A natural question therefore is whether local, sequential vision models may provide any fundamental computational benefits in...
-
23
Video Generation Models are General-Purpose Vision Learners
Letian Wang, Chuhan Zhang, Rishabh Kabra, Jasper Uijlings, Steven Waslander, Andrew Zisserman, Joao Carreira,...
cs.CV · cs.AI
Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models. What, then, is the equivalent catalyst needed to achieve a general-purpose model in computer vision? In this paper, we contend that large-scale text-to-video generation serves as a strong pre-training paradigm for computer vision, providing the necessary spatiotemporal priors, vision-language alignment, and scalability required...
-
24
MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs
Hantao Zhang, Jinru Sui, Ed Li, Dirk Bergemann, Zhuoran Yang
cs.CV · cs.AI
Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model. We introduce MultiView-Bench, a diagnostic benchmark expressly designed to evaluate multi-view integration for holistic 3D scene comprehension. Unlike existing datasets that focus on pixel-level mapping or...
-
25
Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling
Jason Rojas, Jiajie He, Yash Patel, Yuechun Gu, Zeyun Yu, Keke Chen
cs.CV · cs.LG
Cloud-based deep learning enables large-scale medical image analysis but raises significant privacy concerns when sensitive patient images are outsourced for model development. Image disguising has recently emerged as a promising privacy-enhancing technology (PET) that transforms images into visually unintelligible representations while preserving information for downstream learning. We established a unified framework to evaluate...
-
26
Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing
Dominick Reilly, Qiyu Wu, Hiromi Wakaki, Srijan Das, Yuki Mistufuji
cs.CV · cs.LG
Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference. However, many real-world settings violate this assumption, requiring models to operate under a privileged modality setting, where auxiliary modalities are available only during training. While these modalities contain valuable information, existing MLLMs largely fail to...
-
27
OpenCoF: Learning to Reason Through Video Generation
Xinyan Chen, Ziyu Guo, Renrui Zhang, Dongzhi Jiang, Hongsheng Li
cs.CV · cs.AI
Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reasoning path distinct from previous Chain-of-Thought (CoT): reasoning can unfold through temporally connected frames, known as Chain-of-Frame (CoF) reasoning. However, existing video generators are primarily trained on general video corpora, still lacking diverse...
-
28
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction
Ayda Eghbalian, Kevin Desai
cs.CV · cs.AI · cs.LG
Recent progress in 3D human pose estimation has made markerless recovery of skeletal motion increasingly accurate and scalable. However, most pose estimators remain optimized for geometric keypoint accuracy, while many real-world applications in rehabilitation, sports science, ergonomics, and clinical movement analysis require biomechanical quantities that describe how the body moves, loads, and activates. In this work, we propose BioModule,...
-
29
LTM: Large-scale Terrain Model for Wildfire-prone Landscapes
Xiao Fu, Yue Hu, Meida Chen, Peter Anthony Beerel, Barath Raghavan
cs.CV · cs.LG
Accurate 3D terrain maps are essential for emergency response when assessing wildfire hazards. However, wildfire-prone regions often span vast areas where conventional reconstruction methods underperform. Airborne LiDAR systems provide high-resolution terrain data, but they are expensive and infrequently updated. Image-based methods offer a lower-cost alternative, but struggle due to sparse visual features and limited image overlap. We...
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.