Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at global image-text alignment, they often struggle with fine-grained alignment between image regions and specific phrases. In this work, we present ObjEmbed, a novel MLLM embedding model that decomposes the input image into multiple regional embeddings, each corresponding to an individual object, along with global embeddings. It supports a wide range of visual understanding tasks like visual grounding, local image retrieval, and global image retrieval. ObjEmbed enjoys three key properties: (1) Object-Oriented Representation: It captures both semantic and spatial aspects of objects by generating two complementary embeddings for each region: an object embedding for semantic matching and an IoU embedding that predicts localization quality. The final object matching score combines semantic similarity with the predicted IoU, enabling more accurate retrieval. (2) Versatility: It seamlessly handles both region-level and image-level tasks. (3) Efficient Encoding: All objects in an image, along with the full image, are encoded in a single forward pass for high efficiency. Superior performance on 18 diverse benchmarks demonstrates its strong semantic discrimination.
V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval
Tsinghua University（清华大学）；University of Central Florida（中央佛罗里达大学）；Fudan University（复旦大学）；The Australian National University（澳大利亚国立大学）；The University of Hong Kong（香港大学）；Pengcheng Laboratory（鹏城实验室）；Central South University（中南大学）
Hierarchical Refinement of Universal Multimodal Attacks on Vision-Language Models
School of Electrical Engineering and Computer Science, the University of Queensland（电气工程与计算机科学学院，昆士兰大学）；Department of Computer Science, City University of Hong Kong（计算机科学系，香港城市大学）
UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagery
School of Automation, Northwestern Polytechnical University（自动化学院，西北工业大学）；College of Missile Engineering, Rocket Force University of Engineering（导弹工程学院，火箭兵工程大学）；School of Artificial Intelligence, Chongqing University of Posts and Telecommunications（人工智能学院，重庆邮电大学）
School of Traffic and Transportation, Beijing Jiaotong University（交通与运输学院，北京交通大学）；Foundation Modal Research Center, Institute of Automation, Chinese Academy of Sciences（基础模态研究中心，自动化研究所）；Queen Mary School Hainan, Beijing University of Posts and Telecommunications（海南女王学院，北京邮电大学）；Department of Computer Science, NUS School of Computing（计算机科学系，国立大学计算机学院）
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；The Hong Kong Polytechnic University（香港理工大学）；University of Science and Technology of China（中国科学技术大学）；Shanghai Jiaotong University（上海交通大学）
Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity
School of AI Convergence, Soongsil University（顺斯利大学人工智能融合学院）；MAUM AI Inc.（MAUM人工智能公司）；Department of Intelligent Semiconductors, Soongsil University（顺斯利大学智能半导体系）
Zhejiang University-University of Illinois at Urbana-Champaign Institute（浙江大学-伊利诺伊大学厄巴纳香槟分校联合学院）；Zhejiang University（浙江大学）
Multimodal sentiment analysis (MSA) is an important way of observing mental activities with the help of data captured from multiple modalities. However, due to the recording or transmission error, some modalities may include incomplete data. Most existing works that address missing modalities usually assume a particular modality is completely missing and seldom consider a mixture of missing across multiple modalities. In this paper, we propose a simple yet effective meta-sampling approach for multimodal sentiment analysis with missing modalities, namely Missing Modality-based Meta Sampling (M3…
Microsoft Dynamics 365 AI Research（微软 Dynamics 365 AI 研究院）
Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets (COCO, Visual Genome, Conceptual Captions, and SBU Captions), which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. We design four pre-training tasks: Masked Language Modeling (MLM), Masked Region Modeling (MRM, with three variants), Image…
University of Helsinki（赫尔辛基大学）；Artificial Intelligence Research Institute（人工智能研究院）
Supporting the current trend in the AI community, we present the AI Journey 2021 Challenge called Fusion Brain, the first competition which is targeted to make the universal architecture which could process different modalities (in this case, images, texts, and code) and solve multiple tasks for vision and language. The Fusion Brain Challenge combines the following specific tasks: Code2code Translation, Handwritten Text recognition, Zero-shot Object Detection, and Visual Question Answering. We have created datasets for each task to test the participants' submissions on it. Moreover, we have co…
Harbin Institute of Technology（哈尔滨工业大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft（微软）；Microsoft Research Redmond（微软研究院（雷德蒙德））
We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-swi…
mChartQA: A universal benchmark for multimodal Chart Question Answer based on Vision-Language Alignment and Reasoning
Shenyang Institute of Computing Technology, Chinese Academy of Sciences（中国科学院沈阳计算技术研究所）；Beijing Wenge Technology Co., Ltd（北京文格科技有限公司）；University of Chinese Academy of Sciences（中国科学院大学）
Existing vision-language methods typically support two languages at a time at most. In this paper, we present a modular approach which can easily be incorporated into existing vision-language methods in order to support many languages. We accomplish this by learning a single shared Multimodal Universal Language Embedding (MULE) which has been visually-semantically aligned across all languages. Then we learn to relate MULE to visual data as if it were a single language. Our method is not architecture specific, unlike prior work which typically learned separate branches for each language, enabli…
UniIR: Training and Benchmarking Universal Multimodal Information Retrievers
University of Waterloo（滑铁卢大学）；Georgia Institute of Technology（佐治亚理工学院）；Hong Kong University of Science and Technology（香港科技大学）；Google DeepMind（谷歌DeepMind）
Universally Unfiltered and Unseen:Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards
Information Engineering University Zhengzhou China；School of Computer Science, \ University Wuhan China；Xi’an Jiaotong University Xi’an China；Wuhan University Wuhan China；Information Engineering University；School of Computer Science, \ University；Xi’an Jiaotong University；Wuhan University
Autoregressive Retriever: Improving Query Understanding from Item Feedback for Universal Multimodal Retrieval
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Zhongguancun Academy（中关村实验室）；Xiaohongshu（小红书）；Southeast Academy of Information Technology, Beijing Institute of Technology（北京理工大学东南信息科学研究院）；Zhongguancun Laboratory（中关村实验室）
