Pub Date : 2026-02-12DOI: 10.1007/s11263-025-02676-0
Yi Chen, Yuying Ge, Yixiao Ge, Mingyu Ding, Bohao Li, Rui Wang, Ruifeng Xu, Ying Shan, Xihui Liu
The pursuit of artificial general intelligence (AGI) has been accelerated by Multimodal Large Language Models (MLLMs), which exhibit superior reasoning, generalization capabilities, and proficiency in processing multimodal inputs. A crucial milestone in the evolution of AGI is the attainment of human-level planning, a fundamental ability for making informed decisions in complex environments, and solving a wide range of real-world problems. Despite the impressive advancements in MLLMs, a question remains: How far are current MLLMs from achieving human-level planning? To shed light on this question, we introduce EgoPlan-Bench, a comprehensive benchmark to evaluate the planning abilities of MLLMs in real-world scenarios from an egocentric perspective, mirroring human perception. EgoPlan-Bench emphasizes the evaluation of planning capabilities of MLLMs, featuring realistic tasks, diverse action plans, and intricate visual observations. Our rigorous evaluation of a wide range of MLLMs reveals that EgoPlan-Bench poses significant challenges, highlighting a substantial scope for improvement in MLLMs to achieve human-level task planning. To facilitate this advancement, we further present EgoPlan-IT, a specialized instruction-tuning dataset that effectively enhances model performance on EgoPlan-Bench. We have made all the codes, data, and a maintained benchmark leaderboard available at https://chenyi99.github.io/ego_plan/ to advance future research.
{"title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","authors":"Yi Chen, Yuying Ge, Yixiao Ge, Mingyu Ding, Bohao Li, Rui Wang, Ruifeng Xu, Ying Shan, Xihui Liu","doi":"10.1007/s11263-025-02676-0","DOIUrl":"https://doi.org/10.1007/s11263-025-02676-0","url":null,"abstract":"The pursuit of artificial general intelligence (AGI) has been accelerated by Multimodal Large Language Models (MLLMs), which exhibit superior reasoning, generalization capabilities, and proficiency in processing multimodal inputs. A crucial milestone in the evolution of AGI is the attainment of human-level planning, a fundamental ability for making informed decisions in complex environments, and solving a wide range of real-world problems. Despite the impressive advancements in MLLMs, a question remains: How far are current MLLMs from achieving human-level planning? To shed light on this question, we introduce EgoPlan-Bench, a comprehensive benchmark to evaluate the planning abilities of MLLMs in real-world scenarios from an egocentric perspective, mirroring human perception. EgoPlan-Bench emphasizes the evaluation of planning capabilities of MLLMs, featuring realistic tasks, diverse action plans, and intricate visual observations. Our rigorous evaluation of a wide range of MLLMs reveals that EgoPlan-Bench poses significant challenges, highlighting a substantial scope for improvement in MLLMs to achieve human-level task planning. To facilitate this advancement, we further present EgoPlan-IT, a specialized instruction-tuning dataset that effectively enhances model performance on EgoPlan-Bench. We have made all the codes, data, and a maintained benchmark leaderboard available at <jats:ext-link xmlns:xlink=\"http://www.w3.org/1999/xlink\" xlink:href=\"https://chenyi99.github.io/ego_plan/\" ext-link-type=\"uri\">https://chenyi99.github.io/ego_plan/</jats:ext-link> to advance future research.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"96 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146196678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-11DOI: 10.1007/s11263-025-02596-z
Khurram Ashfaq, Muhammad Tariq Mahmood
{"title":"Robust Shape from Focus via Multiscale Directional Dilated Laplacian and Recurrent Network","authors":"Khurram Ashfaq, Muhammad Tariq Mahmood","doi":"10.1007/s11263-025-02596-z","DOIUrl":"https://doi.org/10.1007/s11263-025-02596-z","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"16 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146153644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-11DOI: 10.1007/s11263-025-02655-5
Sobhan K. Dhara, Mayukh Roy, Debashis Sen
{"title":"Haze Hue and Haze Saturation Priors for Single Image Dehazing","authors":"Sobhan K. Dhara, Mayukh Roy, Debashis Sen","doi":"10.1007/s11263-025-02655-5","DOIUrl":"https://doi.org/10.1007/s11263-025-02655-5","url":null,"abstract":"","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"230 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146196680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-06DOI: 10.1007/s11263-025-02709-8
Mitchell Rogers, Kobe Knowles, Gaël Gendron, Shahrokh Heidari, Isla Duporge, David Arturo Soriano Valdez, Mihailo Azhar, Padriac O’Leary, Simon Eyre, Michael Witbrock, Patrice Delmas
Recent advances in deep learning have greatly enhanced the accuracy and scalability of animal re-identification by automating the extraction of subtle distinguishing features from images and videos. This enables large-scale, non-invasive monitoring of animal populations. This article proposes a segmentation pipeline and a re-identification model to identify animals without ground-truth IDs. The segmentation pipeline isolates animals from the background using bounding boxes and leverages the DINOv2 and Segment Anything Model 2 (SAM2) foundation models. For re-identification, Recurrence over Video Frames (RoVF) is introduced, a novel approach that employs a recurrent component based on the Perceiver transformer atop a DINOv2 image model, iteratively refining embeddings from video frames. The proposed methods are evaluated on video datasets of meerkats and polar bears (PolarBearVidID). The proposed segmentation model achieved high accuracy (94.36% and 97.26%) and IoU (73.14% and 92.77%) for meerkats and polar bears, respectively. RoVF outperformed frame- and video-based re-identification baselines, achieving a top-1 accuracy of 46.5% and 55% on masked test sets for meerkats and polar bears, respectively, as well as higher top-3 accuracy. These results highlight the potential of the proposed approach to reduce annotation burdens in future individual-based ecological studies. The code is available at https://github.com/Strong-AI-Lab/RoVF-Meerkat-Reidentification .
深度学习的最新进展通过自动从图像和视频中提取细微的区分特征，大大提高了动物再识别的准确性和可扩展性。这使得对动物种群的大规模、非侵入性监测成为可能。本文提出了一个分割管道和一个重新识别模型来识别没有真实id的动物。分割管道使用边界框将动物从背景中分离出来，并利用DINOv2和Segment Anything Model 2 （SAM2）基础模型。为了重新识别，引入了视频帧上的递归（RoVF），这是一种新颖的方法，它采用基于DINOv2图像模型之上的感知器转换器的递归组件，迭代地从视频帧中细化嵌入。在猫鼬和北极熊的视频数据集（PolarBearVidID）上对所提出的方法进行了评估。该分割模型对猫鼬和北极熊的分割准确率分别为94.36%和97.26%，IoU分别为73.14%和92.77%。RoVF优于基于帧和视频的重新识别基线，在猫鼬和北极熊的蒙面测试集上分别实现了46.5%和55%的前1名准确率，以及更高的前3名准确率。这些结果突出了该方法在未来基于个体的生态学研究中减少注释负担的潜力。代码可在https://github.com/Strong-AI-Lab/RoVF-Meerkat-Reidentification上获得。
{"title":"Recurrence over Video Frames (RoVF) for Animal Re-identification","authors":"Mitchell Rogers, Kobe Knowles, Gaël Gendron, Shahrokh Heidari, Isla Duporge, David Arturo Soriano Valdez, Mihailo Azhar, Padriac O’Leary, Simon Eyre, Michael Witbrock, Patrice Delmas","doi":"10.1007/s11263-025-02709-8","DOIUrl":"https://doi.org/10.1007/s11263-025-02709-8","url":null,"abstract":"Recent advances in deep learning have greatly enhanced the accuracy and scalability of animal re-identification by automating the extraction of subtle distinguishing features from images and videos. This enables large-scale, non-invasive monitoring of animal populations. This article proposes a segmentation pipeline and a re-identification model to identify animals without ground-truth IDs. The segmentation pipeline isolates animals from the background using bounding boxes and leverages the DINOv2 and Segment Anything Model 2 (SAM2) foundation models. For re-identification, Recurrence over Video Frames (RoVF) is introduced, a novel approach that employs a recurrent component based on the Perceiver transformer atop a DINOv2 image model, iteratively refining embeddings from video frames. The proposed methods are evaluated on video datasets of meerkats and polar bears (PolarBearVidID). The proposed segmentation model achieved high accuracy (94.36% and 97.26%) and IoU (73.14% and 92.77%) for meerkats and polar bears, respectively. RoVF outperformed frame- and video-based re-identification baselines, achieving a top-1 accuracy of 46.5% and 55% on masked test sets for meerkats and polar bears, respectively, as well as higher top-3 accuracy. These results highlight the potential of the proposed approach to reduce annotation burdens in future individual-based ecological studies. The code is available at <jats:ext-link xmlns:xlink=\"http://www.w3.org/1999/xlink\" xlink:href=\"https://github.com/Strong-AI-Lab/RoVF-Meerkat-Reidentification\" ext-link-type=\"uri\">https://github.com/Strong-AI-Lab/RoVF-Meerkat-Reidentification</jats:ext-link> .","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"4 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146138687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：