中文
相关论文

相关论文: iReason: Multimodal Commonsense Reasoning using Vi…

200 篇论文

The task of Visual Commonsense Reasoning is extremely challenging in the sense that the model has to not only be able to answer a question given an image, but also be able to learn to reason. The baselines introduced in this task are quite…

计算机视觉与模式识别 · 计算机科学 2019-12-30 Hammad A. Ayyubi , Md. Mehrab Tanjim , David J. Kriegman

Compositional learning, mastering the ability to combine basic concepts and construct more intricate ones, is crucial for human cognition, especially in human language comprehension and visual perception. This notion is tightly connected to…

人工智能 · 计算机科学 2024-11-22 Sania Sinha , Tanawan Premsri , Parisa Kordjamshidi

The recent advancements in Deep Learning models and techniques have led to significant strides in performance across diverse tasks and modalities. However, while the overall capabilities of models show promising growth, our understanding of…

人工智能 · 计算机科学 2025-04-04 Erik Arakelyan

Deep learning models perform poorly on tasks that require commonsense reasoning, which often necessitates some form of world-knowledge or reasoning over information not immediately present in the input. We collect human explanations for…

计算与语言 · 计算机科学 2019-06-07 Nazneen Fatema Rajani , Bryan McCann , Caiming Xiong , Richard Socher

Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal…

计算与语言 · 计算机科学 2025-09-09 Hao Liang , Ruitao Wu , Bohan Zeng , Junbo Niu , Wentao Zhang , Bin Dong

Prevalent in biomedical applications (e.g., human phenotype research), multimodal datasets can provide valuable insights into the underlying physiological mechanisms. However, current machine learning (ML) models designed to analyze these…

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Yifan Li , Yingda Yin , Lingting Zhu , Weikai Chen , Shengju Qian , Xin Wang , Yanwei Fu

Visual Navigation is a core task in Embodied AI, enabling agents to navigate complex environments toward given objectives. Across diverse settings within Navigation tasks, many necessitate the modelling of sequential data accumulated from…

人工智能 · 计算机科学 2025-06-19 Ruoyu Wang , Xinshu Li , Chen Wang , Lina Yao

Image captioning, which generates natural language descriptions of the visual information in an image, is a crucial task in vision-language research. Previous models have typically addressed this task by aligning the generative capabilities…

计算机视觉与模式识别 · 计算机科学 2024-09-02 Qian Cao , Xu Chen , Ruihua Song , Xiting Wang , Xinting Huang , Yuchen Ren

Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc. In spite of their great performance in…

机器学习 · 计算机科学 2021-09-20 Guandong Xu , Tri Dung Duong , Qian Li , Shaowu Liu , Xianzhi Wang

Multimodality Representation Learning, as a technique of learning to embed information from different modalities and their correlations, has achieved remarkable success on a variety of applications, such as Visual Question Answering (VQA),…

人工智能 · 计算机科学 2024-03-04 Muhammad Arslan Manzoor , Sarah Albarri , Ziting Xian , Zaiqiao Meng , Preslav Nakov , Shangsong Liang

When humans read or listen, they make implicit commonsense inferences that frame their understanding of what happened and why. As a step toward AI systems that can build similar mental models, we introduce GLUCOSE, a large-scale dataset of…

Visual Commonsense Reasoning, which is regarded as one challenging task to pursue advanced visual scene comprehension, has been used to diagnose the reasoning ability of AI systems. However, reliable reasoning requires a good grasp of the…

计算机视觉与模式识别 · 计算机科学 2025-01-17 Fan Yuan , Xiaoyuan Fang , Rong Quan , Jing Li , Wei Bi , Xiaogang Xu , Piji Li

Recent large vision-language models have achieved strong performance on short- and medium-length video understanding, yet they remain inadequate for ultra-long or even infinite video reasoning, where models must preserve coherent memory…

人工智能 · 计算机科学 2026-05-08 Peizheng Yan , Yu Zhao , Liang Xie , Juntong Qi , Mingming Wang , Erwei Yin

Effective and reliable evaluation is essential for advancing empirical machine learning. However, the increasing accessibility of generalist models and the progress towards ever more complex, high-level tasks make systematic evaluation more…

机器学习 · 计算机科学 2025-02-10 Felix Leeb , Zhijing Jin , Bernhard Schölkopf

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible…

计算机视觉与模式识别 · 计算机科学 2020-03-17 Andrea Zunino , Sarah Adel Bargal , Riccardo Volpi , Mehrnoosh Sameki , Jianming Zhang , Stan Sclaroff , Vittorio Murino , Kate Saenko

Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an indispensable cornerstone in building general AI systems. We propose a new commonsense reasoning dataset based on human's…

人工智能 · 计算机科学 2020-10-21 Mo Yu , Xiaoxiao Guo , Yufei Feng , Xiaodan Zhu , Michael Greenspan , Murray Campbell

Commonsense causality reasoning (CCR) aims at identifying plausible causes and effects in natural language descriptions that are deemed reasonable by an average person. Although being of great academic and practical interest, this problem…

计算与语言 · 计算机科学 2022-06-20 Jiayao Zhang , Hongming Zhang , Weijie J. Su , Dan Roth

Commonsense reasoning in multimodal contexts remains a foundational challenge in artificial intelligence. We introduce Multimodal UNcommonsense(MUN), a benchmark designed to evaluate models' ability to handle scenarios that deviate from…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Yejin Son , Saejin Kim , Dongjun Min , Younjae Yu

The ability to learn and act in novel situations is still a prerogative of animate intelligence, as current machine learning methods mostly fail when moving beyond the standard i.i.d. setting. What is the reason for this discrepancy? Most…

机器学习 · 计算机科学 2018-12-04 Niki Kilbertus , Giambattista Parascandolo , Bernhard Schölkopf
‹ 上一页 1 8 9 10 下一页 ›