hackcv · 实时 AI 资讯聚合

计算机视觉 · 检测、分割与识别

全部生成式 AI Agent / 智能体多模态计算机视觉自然语言处理强化学习 AI 安全编程助手公司与产品政策与监管研究进展 AI 视频

论文精选 61

PanoWorld: Real-World Panoramic Generation

In this work, we aim to address the challenge of long-range memory in panoramic world mode…

领域：cs.CV作者：Haoyuan Li、Dizhe Zhang、Yuemei Zhou

#cs.CV

📎 arXiv🕒 07-11 01:59🔗 arxiv.org

论文精选 61

Scalable Visual Pretraining for Language Intelligence

The rapid progress of large foundation models has been driven predominantly by pretraining…

领域：cs.CV作者：Yiming Zhang、Zhonghan Zhao、Wenwei Zhang

#cs.CV

📎 arXiv🕒 07-11 01:57🔗 arxiv.org

论文精选 61

OpenLongTail: Generative Scaling of Long-Tail Driving Data

Scaling robust driving policies is fundamentally bottlenecked by the scarcity of edge case…

领域：cs.CV作者：Lulin Liu、Nuo Chen、Yan Wang

#cs.CV

📎 arXiv🕒 07-11 01:54🔗 arxiv.org

论文精选 61

Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models

Vision language models (VLMs) have made remarkable progress in visual reasoning during the…

领域：cs.CV作者：Shravan Murlidaran、Miguel P. Eckstein

#cs.CV

📎 arXiv🕒 07-11 01:53🔗 arxiv.org

论文精选 61

Revisiting Euler-Angle Regression with Kolmogorov-Arnold Networks

In many real-world systems, including articulated robots and biomechanical models, rotatio…

领域：cs.CV作者：Yangting Sun、Zijun Cui、Yufei Zhang

#cs.CV

📎 arXiv🕒 07-11 01:48🔗 arxiv.org

论文精选 61

The Effects of Synthetic Data and Label Distribution on Canola Branch Counting

Collecting annotated plant images for automated phenotyping is often slow and expensive. P…

领域：cs.CV作者：Amirsalar Darvishpour、Mikolaj Cieslak、Adam Runions

#cs.CV

📎 arXiv🕒 07-11 01:27🔗 arxiv.org

论文精选 61

4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception

Reliable autonomous driving requires full-scene perception that couples foreground objects…

领域：cs.CV作者：Xiaokai Bai、Lianqing Zheng、Runwei Guan

#cs.CV

📎 arXiv🕒 07-11 01:26🔗 arxiv.org

论文精选 61

Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing

The deployment of large-scale foundation models, such as the Segment Anything Model 3 (SAM…

领域：cs.CV作者：Mohammad Dabaja、Turgay Celik

#cs.CV

📎 arXiv🕒 07-11 00:33🔗 arxiv.org

论文精选 61

Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation

Generating long-duration, high-definition, and rhythmically synchronized dance videos dire…

领域：cs.CV作者：Mingyang Huang、Peng Zhang、Li Hu

#cs.CV

📎 arXiv🕒 07-11 00:30🔗 arxiv.org