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.
By Sara Pieri, Evangelos Kazakos, Shizhe Chen, Josef Sivic, Cordelia Schmid
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
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...
arXiv:2607. 00684v1 Announce Type: new Abstract: The classification accuracy of pretrained Vision-Language Models (VLMs) relies on the quality of the text prompts.
By Seokhee Jin, Changhwan Sung, Sunung Mun, Hoyoung Kim, Jungseul Ok
arXiv:2609.13228v1 Announce Type: new
Abstract: Vision Language Models (VLMs) should rely on visual evidence that directly determines the correct answer, but supervision for grounding visual reasonin...
By Marko Jojic, Zhaonan Li, Ben Zhou
arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.
By Sangin Lee, Yukyung Choi
The paper introduces CFM, a language‑aligned concept foundation model for vision that generates fine‑grained, human‑interpretable concepts with spatial grounding. By pairing CFM with a strong semantic foundation model, it provides explanations for downstream tasks such as classification, segmentation, and captioning. The authors also analyze local co‑occurrence of concepts to define relationships, improving concept naming and yielding richer explanations while maintaining competitive performance.
By Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi, Bernt Schiele, Jonas Fischer
ProCAP introduces a probabilistic cross-attentive prompt learning framework for vision-language models like CLIP, enabling improved cross-modal interaction without updating the backbone. It jointly learns visual and textual prompt tokens, linking them via stacked bidirectional multi-head cross-attention to refine each branch across prompt depth. The method incorporates Gaussian parameterization of prompt tokens, lightweight KL and L2 regularization, and a compact symmetric InfoNCE head to align image features with class-level text representations, achieving strong few-shot base-to-novel performance and competitive transfer results across multiple datasets and benchmarks.
By Hiwa Azeez Abbas, Fatemeh Daneshfar, Moloud Abdar
arXiv:2606. 26994v1 Announce Type: cross Abstract: Existing referring video segmentation methods often treat a video as a single event consisting of multiple images, overlooking the fact that a video typically contains multiple distinct events.
By Jinyu Liu, Henghui Ding, Shuting He, Yu-Gang Jiang
arXiv:2509. 23876v3 Announce Type: replace-cross Abstract: Autoregressive (AR) models based on next-scale prediction have emerged as a powerful tool for image generation, but they face a critical weakness: information inconsistencies between patches across timesteps introduced by progressive resolution scaling.
By Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh, Daochang Liu, Weidong Cai, Xiuying Wang, Chang Xu
Pixels to Tokens introduces TEAL, a token‑space efficient active learning framework that operates at the pixel level for semantic segmentation using a frozen Vision Transformer backbone. TEAL selects diverse candidate pixels via a two‑level MaxHerding strategy on multi‑layer token descriptors and refines uncertainty on a finer decoder grid, avoiding interpolation artifacts. Across multiple datasets, TEAL outperforms prior baselines under extreme label scarcity, achieving up to +24.36 mIoU with a single labeled pixel per image and reaching 97% of fully supervised performance with only ten pixels.
By Utku Cicek, Mahip Singh, Ziyao Shang, Kimathi Kaai, C Thomas, Pedro Pablo Guerrero Vela, Alexander Wong, Sirisha Rambhatla
arXiv:2509.22650v3 Announce Type: replace
Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,...
By Anna Kukleva, Enis Simsar, Alessio Tonioni, Muhammad Ferjad Naeem, Federico Tombari, Jan Eric Lenssen, Bernt Schiele