中文
相关论文

相关论文: Video-STAR: Reinforcing Open-Vocabulary Action Rec…

200 篇论文

Human action recognition often struggles with deep semantic understanding, complex contextual information, and fine-grained distinction, limitations that traditional methods frequently encounter when dealing with diverse video data.…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Jingwei Peng , Zhixuan Qiu , Boyu Jin , Surasakdi Siripong

Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition. In this work, we extend this paradigm by leveraging motion and audio that…

计算机视觉与模式识别 · 计算机科学 2022-07-18 Rui Qian , Yeqing Li , Zheng Xu , Ming-Hsuan Yang , Serge Belongie , Yin Cui

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, yet they lag significantly behind humans in spatial reasoning. We investigate this gap through Transformation-Driven Visual Reasoning…

计算机视觉与模式识别 · 计算机科学 2025-07-11 Zongzhao Li , Zongyang Ma , Mingze Li , Songyou Li , Yu Rong , Tingyang Xu , Ziqi Zhang , Deli Zhao , Wenbing Huang

Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large…

计算机视觉与模式识别 · 计算机科学 2025-12-12 Sunqi Fan , Jiashuo Cui , Meng-Hao Guo , Shuojin Yang

Recent progress in reasoning capabilities of Multimodal Large Language Models(MLLMs) has highlighted their potential for performing complex video understanding tasks. However, in the domain of Video Anomaly Detection and Understanding…

计算机视觉与模式识别 · 计算机科学 2026-01-16 Chao Huang , Benfeng Wang , Wei Wang , Jie Wen , Li Shen , Wenqi Ren , Yong Xu , Xiaochun Cao

Human processes video reasoning in a sequential spatio-temporal reasoning logic, we first identify the relevant frames ("when") and then analyse the spatial relationships ("where") between key objects, and finally leverage these…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Zixu Cheng , Jian Hu , Ziquan Liu , Chenyang Si , Wei Li , Shaogang Gong

Multimodal Large Reasoning Models (MLRMs) have achieved remarkable strides in visual reasoning through test time compute scaling, yet long chain reasoning remains prone to hallucinations. We identify a concerning phenomenon termed the…

人工智能 · 计算机科学 2026-05-29 Zhe Qian , Yanbiao Ma , Zhuohan Ouyang , Zhonghua Wang , Zhongxing Xu , Fei Luo , Xinyu Liu , Zongyuan Ge , Yike Guo , Jungong Han

Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Rohit Gupta , Mamshad Nayeem Rizve , Jayakrishnan Unnikrishnan , Ashish Tawari , Son Tran , Mubarak Shah , Benjamin Yao , Trishul Chilimbi

Predicting and reasoning how a video would make a human feel is crucial for developing socially intelligent systems. Although Multimodal Large Language Models (MLLMs) have shown impressive video understanding capabilities, they tend to…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Yuxiang Guo , Faizan Siddiqui , Yang Zhao , Rama Chellappa , Shao-Yuan Lo

Spatio-temporal action detection (STAD) is an important fine-grained video understanding task. Current methods require box and label supervision for all action classes in advance. However, in real-world applications, it is very likely to…

计算机视觉与模式识别 · 计算机科学 2024-05-20 Tao Wu , Shuqiu Ge , Jie Qin , Gangshan Wu , Limin Wang

Action detection aims to detect (recognize and localize) human actions spatially and temporally in videos. Existing approaches focus on the closed-set setting where an action detector is trained and tested on videos from a fixed set of…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Wentao Bao , Kai Li , Yuxiao Chen , Deep Patel , Martin Renqiang Min , Yu Kong

Multimodal emotion recognition is a task of great concern. However, traditional data sets are based on fixed labels, resulting in models that often focus on main emotions and ignore detailed emotional changes in complex scenes. This report…

计算机视觉与模式识别 · 计算机科学 2024-08-23 Mengying Ge , Dongkai Tang , Mingyang Li

Existing semi-supervised video anomaly detection (VAD) methods often struggle with detecting complex anomalies involving object interactions and generally lack explainability. To overcome these limitations, we propose a novel VAD framework…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Furkan Mumcu , Michael J. Jones , Anoop Cherian , Yasin Yilmaz

The performance of Large Vision Language Models (LVLMs) is dependent on the size and quality of their training datasets. Existing video instruction tuning datasets lack diversity as they are derived by prompting large language models with…

计算机视觉与模式识别 · 计算机科学 2024-07-09 Orr Zohar , Xiaohan Wang , Yonatan Bitton , Idan Szpektor , Serena Yeung-Levy

Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language alignment, yet they remain limited in visual-spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Zhaozhi Wang , Tong Zhang , Mingyue Guo , Yaowei Wang , Qixiang Ye

Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and…

计算与语言 · 计算机科学 2024-04-29 Mengzhao Jia , Zhihan Zhang , Wenhao Yu , Fangkai Jiao , Meng Jiang

Multimodal Large Language Models (MLLMs) frequently hallucinate due to their reliance on fragile, linear reasoning and weak visual grounding. We propose Visual Attention Reasoning (VAR), a reinforcement learning framework that reformulates…

人工智能 · 计算机科学 2026-01-27 Wei Cai , Jian Zhao , Yuchen Yuan , Tianle Zhang , Ming Zhu , Haichuan Tang , Xuelong Li

Despite an exciting new wave of multimodal machine learning models, current approaches still struggle to interpret the complex contextual relationships between the different modalities present in videos. Going beyond existing methods that…

计算机视觉与模式识别 · 计算机科学 2023-09-20 Laura Hanu , Anita L. Verő , James Thewlis

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs)…

Multimodal large language models (MLLMs) play a pivotal role in advancing the quest for general artificial intelligence. However, achieving unified target for multimodal understanding and generation remains challenging due to optimization…

计算机视觉与模式识别 · 计算机科学 2025-12-17 Jie Qin , Jiancheng Huang , Limeng Qiao , Lin Ma
‹ 上一页 1 2 3 10 下一页 ›