arXiv Computation and Language September 17, 2026 By Sara Pieri, Evangelos Kazakos, Shizhe Chen, Josef Sivic, Cordelia Schmid

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

Read the original on arXiv Computation and Language →

PANORAMA introduces a new panoptic grounded captioning framework that jointly generates detailed image captions and associates each phrase with precise pixel-level masks. The authors create PanoCaps, a human‑annotated benchmark with dense captions and near‑complete pixel coverage, and propose a phrase‑mask matching protocol with a generalized Panoptic Quality metric. PANORAMA conditions a pretrained segmenter on contextualized phrase representations, learns to select appropriate masks, and achieves state‑of‑the‑art grounding performance on PanoCaps and other pixel‑level tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers

Sep 16

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language models (VLMs) can generate fluent and detailed image ca...

llms computer-vision multimodal benchmarks

arXiv AI

Aug 11

Vision-Language Grounding as Bidirectional Concept Correspondence

arXiv:2608. 07886v1 Announce Type: cross Abstract: Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization problem: given a prespecified text phrase or category name, identify the corresponding image region.

By Jieyu Zhang, Ziqi Gao, Luke Zettlemoyer, Ranjay Krishna

llms computer-vision multimodal safety

arXiv Computer Vision

Oct 26

SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction

SetCon reformulates open-ended referring segmentation as set-level concept prediction, using LVLM-generated natural-language concepts instead of segmentation-specific tokens. It employs a hierarchical semantic decomposition that first predicts a shared set-level concept and then refines it into fine-grained concept groups aligned with target subsets. The method, supported by a two-stage annotation pipeline adding hierarchical semantic supervision, achieves state-of-the-art results on multiple image and video benchmarks, with performance gains increasing as the number of referred targets grows.

By Zhixiong Zhang, Yizhuo Li, Shuangrui Ding, Yuhang Zang, Shengyuan Ding, Long Xing, Yibin Wang, Qiaosheng Zhang, Jiaqi Wang

llms computer-vision benchmarks

arXiv Computer Vision

Aug 25

Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos

arXiv:2501.04001v4 Announce Type: replace Abstract: This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-...

By Haobo Yuan, Xiangtai Li, Tao Zhang, Yueyi Sun, Zilong Huang, Shilin Xu, Shunping Ji, Yunhai Tong, Lu Qi, Jiashi Feng, Ming-Hsuan Yang

llms computer-vision fine-tuning multimodal benchmarks

arXiv Computer Vision

Oct 27

PixFoundation: Are We Heading in the Right Direction with Pixel-level Vision Foundation Models?

arXiv:2502.04192v5 Announce Type: replace Abstract: Multiple works have emerged to push the boundaries of multi-modal large language models (MLLMs) towards pixel-level understanding. The current tren...

By Mennatullah Siam

llms computer-vision nlp multimodal benchmarks safety

arXiv AI

Jul 8

PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet

arXiv:2607. 06097v1 Announce Type: cross Abstract: 3D dense captioning, an emerging vision-language task, aims to generate descriptive sentences for each object in the 3D scene.

By Xiaopei Wu, Chenshu Hou, Liang Peng, Dan Xu, Binbin Lin, Xiaoshui Huang, Yuenan Hou, Yu Li, Wenxiao Wang, Haifeng Liu, Deng Cai, Wanli Ouyang

multimodal benchmarks

One email a morning, machine-written

Related stories

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

Vision-Language Grounding as Bidirectional Concept Correspondence

SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction

Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos

PixFoundation: Are We Heading in the Right Direction with Pixel-level Vision Foundation Models?

PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet