Visual Question Answering (VQA)

Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world sc…

Language Modeling Language Modelling Optical Character Recognition (OCR)reinforcement-learning+2

MGFFD-VLM: Multi-Granularity Prompt Learning for Face Forgery Detection with VLM

2025-07-16 · Tao Chen, Jingyi Zhang, Decheng Liu, Chunlei Peng

Recent studies have utilized visual large language models (VLMs) to answer not only "Is this face a forgery?" but also "Why is the face a forgery?" These studies introduced forgery-related attributes, such as forgery loc…

Attribute Face Swapping Prompt Learning Visual Question Answering (VQA)

Describe Anything Model for Visual Question Answering on Text-rich Images

2025-07-16 · Yen-Linh Vu, Dinh-Thang Duong, Truong-Binh Duong, Anh-Khoi Nguyen 외

Recent progress has been made in region-aware vision-language modeling, particularly with the emergence of the Describe Anything Model (DAM). DAM is capable of generating detailed descriptions of any specific image areas…

Descriptive Language Modeling Language Modelling Question Answering+2

Evaluating Attribute Confusion in Fashion Text-to-Image Generation

2025-07-09 · Ziyue Liu, Federico Girella, Yiming Wang, Davide Talon

Despite the rapid advances in Text-to-Image (T2I) generation models, their evaluation remains challenging in domains like fashion, involving complex compositional generation. Recent automated T2I evaluation methods lever…

Attribute cross-modal alignment Image Generation Question Answering+5

LinguaMark: Do Multimodal Models Speak Fairly? A Benchmark-Based Evaluation

2025-07-09 · Ananya Raval, Aravind Narayanan, Vahid Reza Khazaie, Shaina Raza

Large Multimodal Models (LMMs) are typically trained on vast corpora of image-text data but are often limited in linguistic coverage, leading to biased and unfair outputs across languages. While prior work has explored m…

Question Answering Visual Question Answering Visual Question Answering (VQA)

Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder

2025-06-28 · Dang Jisheng, Wu Xudong, Wang Bimei, Lv Ning 외

Existing video segmenter and grounder approaches, exemplified by Sa2VA, directly fuse features within segmentation models. This often results in an undesirable entanglement of dynamic visual information and static semant…

Image Segmentation Large Language Model Question Answering Segmentation+5

전체 2,167편 보기 →