中文
相关论文

相关论文: MASR: Self-Reflective Reasoning through Multimodal…

200 篇论文

Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-date knowledge beyond their training data. We introduce MARS…

Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied to long-form video understanding scenarios, they exhibit clear limitations. The fundamental…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Jiaze Li , Hao Yin , Wenhui Tan , Jingyang Chen , Boshen Xu , Yuxun Qu , Yijing Chen , Jianzhong Ju , Zhenbo Luo , Jian Luan

Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Yufei Yin , Qianke Meng , Minghao Chen , Jiajun Ding , Zhenwei Shao , Zhou Yu

Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required. In this work, we propose an agent-based approach to enhance both the efficiency and…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Sullam Jeoung , Goeric Huybrechts , Bhavana Ganesh , Aram Galstyan , Sravan Bodapati

Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leaving the inference-time approach relatively underexplored. In…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Tingshu Mou , Jiabo He , Renying Wang , Ce Liu , Hao Yang , Tiehua Zhang , Jingjing Chen , Xingjun Ma

Recent advances in video large language models have demonstrated strong capabilities in understanding short clips. However, scaling them to hours- or days-long videos remains highly challenging due to limited context capacity and the loss…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Woongyeong Yeo , Kangsan Kim , Jaehong Yoon , Sung Ju Hwang

Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding tasks. However, they continue to struggle with long-form videos because of an inefficient perception of temporal intervals. Unlike humans, who can…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Chenglin Li , Qianglong Chen , fengtao , Yin Zhang

Reference Audio-Visual Segmentation (Ref-AVS) aims to segment objects in audible videos based on multimodal cues in reference expressions. Previous methods overlook the explicit recognition of expression difficulty and dominant modality in…

多媒体 · 计算机科学 2026-03-31 Yuan Zhao , Zhenqi Jia , Yongqiang Zhang

Successfully handling context is essential for any dialog understanding task. This context maybe be conversational (relying on previous user queries or system responses), visual (relying on what the user sees, for example, on their screen),…

Intelligent sports video analysis demands a comprehensive understanding of temporal context, from micro-level actions to macro-level game strategies. Existing end-to-end models often struggle with this temporal hierarchy, offering solutions…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Tsz-To Wong , Ching-Chun Huang , Hong-Han Shuai

The rise of short-form video platforms and the emergence of multimodal large language models (MLLMs) have amplified the need for scalable, effective, zero-shot text-to-video retrieval systems. While recent advances in large-scale…

信息检索 · 计算机科学 2026-02-24 Jiaxin Wu , Xiao-Yong Wei , Qing Li

Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Yiyang Zhou , Yangfan He , Yaofeng Su , Siwei Han , Joel Jang , Gedas Bertasius , Mohit Bansal , Huaxiu Yao

Large Vision-Language Models (LVLMs) demonstrate remarkable performance in short-video tasks such as video question answering, but struggle in long-video understanding. The linear frame sampling strategy, conventionally used by LVLMs, fails…

计算机视觉与模式识别 · 计算机科学 2025-06-30 Joao Pereira , Vasco Lopes , David Semedo , Joao Neves

Spatial reasoning has emerged as a critical capability for Multimodal Large Language Models (MLLMs), drawing increasing attention and rapid advancement. However, existing benchmarks primarily focus on single-step perception-to-judgment…

计算机视觉与模式识别 · 计算机科学 2026-01-15 Rui Zhu , Xin Shen , Shuchen Wu , Chenxi Miao , Xin Yu , Yang Li , Weikang Li , Deguo Xia , Jizhou Huang

To effectively engage in human society, the ability to adapt, filter information, and make informed decisions in ever-changing situations is critical. As robots and intelligent agents become more integrated into human life, there is a…

With the increasing prevalence of video content, effectively understanding and answering questions about long form videos has become essential for numerous applications. Although large vision language models (LVLMs) have enhanced…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Urjitkumar Patel , Fang-Chun Yeh , Chinmay Gondhalekar

Human drivers focus only on a handful of agents at any one time. On the other hand, autonomous driving systems process complex scenes with numerous agents, regardless of whether they are pedestrians on a crosswalk or vehicles parked on the…

机器学习 · 计算机科学 2025-09-25 Carlo Bosio , Greg Woelki , Noureldin Hendy , Nicholas Roy , Byungsoo Kim

Despite their popularity and success, Multimodal Large Language Models (MLLMs) often struggle to interpret images accurately, which limits their reasoning capability in complex scenarios (e.g., high object density and complex background…

计算机视觉与模式识别 · 计算机科学 2026-05-28 Xuanzhao Dong , Wenhui Zhu , Peijie Qiu , Xiwen Chen , Xiaobing Yu , Xin Li , Zhipeng Wang , Shao Tang , Gen Li , Yujian Xiong , Hao Wang , Yanxi Chen , Prayag Tiwari , Yalin Wang

Hateful videos pose serious risks by amplifying discrimination, inciting violence, and undermining online safety. Existing training-based hateful video detection methods are constrained by limited training data and lack of interpretability,…

计算机视觉与模式识别 · 计算机科学 2026-01-22 Shuonan Yang , Yuchen Zhang , Zeyu Fu

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
‹ 上一页 1 2 3 10 下一页 ›