activity
20242026
collaborators

8 papers

cs.CV2026

CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning

Ankan Deria, Komal Kumar, Xilin He +4

Recent vision-language models (VLMs) typically rely on a single vision encoder trained with contrastive image-text objectives, such as CLIP-style pretraining. While contrastive enc…

cs.CV2026

The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report

Bin Ren, Hang Guo, Yan Shu +60

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a…

cs.CV2025

RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion

Thao Nguyen, Jiaqi Ma, Fahad Shahbaz Khan +2

Precipitation nowcasting, predicting future radar echo sequences from current observations, is a critical yet challenging task due to the inherently chaotic and tightly coupled spa…

cs.CV2025

LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation

Xinyu Yan, Meijun Sun, Ge-Peng Ji +3

We present LawDIS, a language-window-based controllable dichotomous image segmentation (DIS) framework that produces high-quality object masks. Our framework recasts DIS as an imag…

cs.CV2025

Vocabulary-free Fine-grained Visual Recognition via Enriched Contextually Grounded Vision-Language Model

Dmitry Demidov, Zaigham Zaheer, Omkar Thawakar +2

Fine-grained image classification, the task of distinguishing between visually similar subcategories within a broader category (e.g., bird species, car models, flower types), is a…

cs.CV2025

Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model

Shiming Chen, Bowen Duan, Salman Khan +1

Large-scale vision-language models (VLMs), such as CLIP, have achieved remarkable success in zero-shot learning (ZSL) by leveraging large-scale visual-text pair datasets. However,…