cs.CV · 2026-07-15 · No. 54

Computer Vision and Pattern Recognition, 2026-07-15.

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

01 — The papers

18 entries
  1. 01

    HSEmotion Team at the 11th ABAW Challenge: Multi-Task Learning and Ambivalence/Hesitancy Video Recognition

    Aleksei Bakin, Andrey V. Savchenko

    cs.CV · cs.AI

    This article presents our results for the 11th Affective Behavior Analysis in-the-Wild (ABAW) competition. For multi-task learning with simultaneous prediction of valence, arousal, facial expressions, and action units on s-Aff-Wild2 dataset, we use frozen lightweight facial extractors, MT-EmotiDDAMFN and MT-EmotiEffNet-B0, with separate heads and systematic post-processing: temporal Gaussian smoothing, per-class expression bias, AffectNet...

    arxiv.org/abs/2607.12774 · PDF

  2. 02

    Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation

    Hongbo Wang, Huaibo Huang, Jie Cao, Jin Liu, Haoyang Tong, Ran He

    cs.CV · cs.AI

    While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely on 2D diffusion supervision without explicit mechanisms for geometric consistency, leading to spatial hallucinations such as duplicated structures and misaligned geometry. These issues become more severe in 4D generation, where maintaining consistency across viewpoints and temporal evolution introduces additional challenges, including...

    arxiv.org/abs/2607.12752 · PDF

  3. 03

    Weakly Supervised Spatio-Temporal Candidate Discovery of Dairy Farm Sites from Seasonal Satellite Imagery

    Usman Haider, Fatima Khalid, Karl Mason

    cs.CV · cs.AI

    Farm site discovery from satellite imagery is a spatiotemporal candidate ranking problem because farm evidence is distributed across pasture, field boundaries, roads, buildings, and seasonal vegetation patterns. Direct farm labels are often incomplete, which makes fully supervised detection difficult. This paper proposes a weakly supervised pipeline for ranking dairy farm candidate clusters from seasonal Sentinel imagery and open map priors....

    arxiv.org/abs/2607.12748 · PDF

  4. 04

    Label-Decoupled Style Augmentation for Domain Generalization in Multi-Label Remote Sensing Scene Classification

    Alaa Almouradi, Erchan Aptoula

    cs.CV · cs.LG

    Multi-label classification assigns several co-occurring labels to each aerial scene, yet deployed models often encounter data distributions different from their training. Feature-statistics augmentation such as MixStyle, EFDMix, and correlated style uncertainty improves generalization at low cost but perturbs channel statistics globally, treating each image as a single style; one class can then contaminate the augmentation of another. Domain...

    arxiv.org/abs/2607.12704 · PDF

  5. 05

    Text-Aided Multi-Modal Panoptic Symbol Spotting for CAD Floor Plan Drawings

    Yan Gong, Bohao Li, Bowen Du, Junchen Ye

    cs.CV · cs.AI

    Computer-Aided Design (CAD) floor plan drawings contain both graphical primitives and textual annotations, which provide complementary geometric and semantic cues for intelligent design understanding. Among CAD analysis tasks, panoptic symbol spotting has become increasingly important with the growing demand for industrial digitalization and deep learning-based automation. However, most existing methods remain primarily primitive-centric and...

    arxiv.org/abs/2607.12678 · PDF

  6. 06

    Traceback Translators Against Forgetting in Continual Fake Speech Detection

    Enrico Gottardis, Mattia Tamiazzo, Simone Milani

    cs.CV · cs.AI · cs.MM · cs.SD

    Fake speech detectors are increasingly challenged by the development of new and more accurate generative models. To cope with this problem, continual learning techniques are nowadays widely considered feasible strategies for updating models to new datasets, but they also lead to decreased performance on previously seen samples (catastrophic forgetting). In this work, we propose a forgetting-resilient solution based on the adoption of domain...

    arxiv.org/abs/2607.12569 · PDF

  7. 07

    Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification

    Jeeyung Kim, Erfan Esmaeili, Qiang Qiu

    cs.CV · cs.LG

    When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful for the downstream task. Existing approaches largely improve synthetic data by increasing realism, diversity, or domain adaptation, while overlooking a more fundamental question: how should sample usefulness for classification be measured and optimized? We address...

    arxiv.org/abs/2607.12464 · PDF

  8. 08

    ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning

    Zijie Wang, Wei Zhang, Weiming Zhang, Xiao Tan, Weikai Chen, Xiaoxu Li, Guanbin Li

    cs.CV · cs.AI

    Diffusion models have recently become the dominant paradigm for monocular depth estimation (MDE). However, they implicitly assume that depth can be recovered as a globally smooth field through iterative denoising, which does not explicitly reflect the piecewise and scale-dependent organization of scene geometry. In practice, geometric structure emerges progressively across spatial scales, where coarse layout, surfaces, and boundaries are...

    arxiv.org/abs/2607.12433 · PDF

  9. 09

    Demonstration of the common dual-channel feature decoupling characteristic of front-door mediation causal inference methods in whole-slice image classification

    Zhirui Zhang, Tianhang Nan, Yong Ding, Zhuolun Song, Dayu Hu, Xiaoyu Cui

    cs.CV · cs.AI

    Causal inference using front door intervention and multi-instance learning (MIL) has advanced the analysis of Whole Slide Images (WSI) in digital pathology. These methods adjust feature distributions of subtle evidence sub-images to correctly associate them with WSI-level diagnoses. We propose and prove 2 hypotheses for evaluating such methods: 1) Causal inference MIL introduces an independent classification channel that effectively completes...

    arxiv.org/abs/2607.12376 · PDF

  10. 10

    IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment

    Jinjian Wu, Jiaqi Tang, Wei Wei, Yingying Yan, Jianmin Chen, Botong Geng, Lei Zhang, Qifeng Chen

    cs.CV · cs.AI · eess.IV

    Image Quality Assessment (IQA) in open-world environments remains challenging due to limited generalization and interpretability. Recent approaches based on multimodal large language models (MLLMs) introduce textual reasoning for quality prediction, yet their judgments rely heavily on semantically biased internal representations, making them insensitive to low-level perceptual degradations. We propose IQA-T1, a tool-based visual evidence...

    arxiv.org/abs/2607.12375 · PDF

  11. 11

    Lost in Visual Translation: A VLM-Assisted Perceptual-Semantic Coherence Framework for EEG-to-Image Reconstruction

    Sukriti Tiwari, BHVSP Subrahmanyam, Nidhi Goyal, Sai Amrit Patnaik

    cs.CV · cs.AI

    EEG-to-image evaluation should distinguish visual fidelity from recoverable meaning. Yet EEG-derived reconstructions are blurry, distorted, and low-detail, causing SSIM, LPIPS, and CLIP to penalize semantically recoverable outputs or reward plausible but incorrect ones. We analyze 6,855 ground-truth/reconstruction pairs from ATM, ENIGMA, BrainVis, and DreamDiffusion using semantic probes, caption harshness and blind-spot rates, and controlled...

    arxiv.org/abs/2607.12364 · PDF

  12. 12

    What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation

    Farrukh Rahman

    cs.CV · cs.LG

    A score on a temporal video question answering benchmark is meant to measure that a model has temporal understanding, but it conflates two questions. 1. The task question: is the question even temporal, does it need several frames and their order? and 2. The channel question, when it does, does the model recover the order from the pixels, or read it off the positional encoding (RoPE)? Most of a temporal score answers neither, a single frame...

    arxiv.org/abs/2607.12304 · PDF

  13. 13

    Auditing Data Leakage in Whole-Slide Image Multimodal Benchmarks

    Wenhao Zhang, Zhongliang Zhou, John Kang, Sheng Li

    cs.CV · cs.LG

    Recent vision-language models (VLMs) for computational pathology report striking zero-shot performance on whole-slide image (WSI) visual question answering (VQA) benchmarks. We audit these claims and find them fundamentally compromised by data leakage at two hierarchical levels: patient-level leakage, where slides from the same case appear in both training and test folds, and institutional-level leakage, where different cases nonetheless...

    arxiv.org/abs/2607.12278 · PDF

  14. 14

    Rough Path Signature-Guided Geometry Augmentation for Few-Shot Industrial Surface Defect Detection

    Jiaqi Kuang

    cs.CV · cs.LG · math.PR

    Few-shot industrial defect detection remains difficult for standard supervised detectors, which achieve poor performance on boundary-dominated industrial defects. This paper proposes rough path signature-guided geometry augmentation (RPS-GA), a geometry-aware approach in which Canny edge contours are treated as ordered planar paths whose truncated second-order signature responses, especially the antisymmetric Lévy-area term, are aggregated...

    arxiv.org/abs/2607.12245 · PDF

  15. 15

    From Reconstruction to Interpretation: Zero-Setup Multi-Phase Segmentation of X-ray Tomography Data

    Pradyumna Elavarthi, Arun J. Bhattacharjee, Harrison Lisabeth, Anca Ralescu, Petrus H. Zwart, Dilworth Parkinson,...

    cs.CV · cs.AI

    X-ray tomography enables nondestructive characterization of material microstructures, while advances in micro-CT imaging have accelerated volumetric data acquisition and reconstruction. However, rapid interpretation remains limited by image segmentation, which often requires manual thresholding, user prompting, or material-specific model training. We present a zero-setup framework for multi-phase segmentation of synchrotron X-ray tomography...

    arxiv.org/abs/2607.12175 · PDF

  16. 16

    Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models

    Xu Han, Jiajing Hu, Li-Ping Liu

    cs.CV · cs.AI · cs.LG

    In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising. Although prior work shows that these parameterizations lead to different empirical behaviors, the mechanisms underlying their respective advantages remain to be underexplored, and how to combine them effectively is still unclear. In this work, we analyze...

    arxiv.org/abs/2607.12171 · PDF

  17. 17

    Learning from Complementary Ultrasound Representations for Liver Disease Classification

    Sabahattin Mert Daloglu, Gokce Bekar, Ceren Coskun, Senanur Sahin, Harvey Castro, Soner Hacihaliloglu, Halley P....

    cs.CV · cs.LG

    Differentiating non-alcoholic steatohepatitis (NASH) from non-alcoholic fatty liver disease (NAFLD) using ultrasound remains challenging due to subtle tissue alterations and the limited information available in conventional B-mode imaging. In this work, we investigate whether complementary ultrasound representations derived from the same acquisition can improve NASH versus NAFLD classification. Specifically, we combine conventional B-mode...

    arxiv.org/abs/2607.12062 · PDF

  18. 18

    Representation and Reference Selection in Training-Free Synthetic Image Attribution

    Meiling Li, Pietro Bongini, Benedetta Tondi, Mauro Barni

    cs.CV · cs.AI · cs.CR

    Synthetic image attribution aims at identifying the generator responsible for a given AI-generated image. Training-free reference-based attribution methods are easily scalable, since newly emerging generators can be incorporated by adding source-specific references rather than retraining a task-specific classifier. Their performance depends on two coupled factors: the representation space used for comparison and the way source-specific...

    arxiv.org/abs/2607.12052 · 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.