中文
相关论文

相关论文: GazeQwen: Lightweight Gaze-Conditioned LLM Modulat…

200 篇论文

Current large multimodal models (LMMs) face challenges in grounding, which requires the model to relate language components to visual entities. Contrary to the common practice that fine-tunes LMMs with additional grounding supervision, we…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Shengcao Cao , Liang-Yan Gui , Yu-Xiong Wang

Large Multimodal Models (LMMs) uniformly perceive video frames, creating computational inefficiency for videos with inherently varying temporal information density. This paper present \textbf{Quicksviewer}, an LMM with new perceiving…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Ji Qi , Yuan Yao , Yushi Bai , Bin Xu , Juanzi Li , Zhiyuan Liu , Tat-Seng Chua

Although recent gaze estimation methods lay great emphasis on attentively extracting gaze-relevant features from facial or eye images, how to define features that include gaze-relevant components has been ambiguous. This obscurity makes the…

计算机视觉与模式识别 · 计算机科学 2022-09-22 Isack Lee , Jun-Seok Yun , Hee Hyeon Kim , Youngju Na , Seok Bong Yoo

Deep learning-based appearance gaze estimation methods are gaining popularity due to their high accuracy and fewer constraints from the environment. However, existing high-precision models often rely on deeper networks, leading to problems…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Zhang Cheng , Yanxia Wang

This paper introduces MiniGPT4-Video, a multimodal Large Language Model (LLM) designed specifically for video understanding. The model is capable of processing both temporal visual and textual data, making it adept at understanding the…

计算机视觉与模式识别 · 计算机科学 2024-04-05 Kirolos Ataallah , Xiaoqian Shen , Eslam Abdelrahman , Essam Sleiman , Deyao Zhu , Jian Ding , Mohamed Elhoseiny

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation.…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Wentong Li , Yuqian Yuan , Jian Liu , Dongqi Tang , Song Wang , Jie Qin , Jianke Zhu , Lei Zhang

Reading dense text and locating objects within images are fundamental abilities for Large Vision-Language Models (LVLMs) tasked with advanced jobs. Previous LVLMs, including superior proprietary models like GPT-4o, have struggled to excel…

计算机视觉与模式识别 · 计算机科学 2024-10-08 Ya-Qi Yu , Minghui Liao , Jiwen Zhang , Jihao Wu

Current visual grounding models are either based on a Multimodal Large Language Model (MLLM) that performs auto-regressive decoding, which is slow and risks hallucinations, or on re-aligning an LLM with vision features to learn new special…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Weitai Kang , Jason Kuen , Mengwei Ren , Zijun Wei , Yan Yan , Kangning Liu

Using lightweight models as backbone networks in gaze estimation tasks often results in significant performance degradation. The main reason is that the number of feature channels in lightweight networks is usually small, which makes the…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Zhang Cheng , Yanxia Wang

Multimodal Large Language Models (MLLMs) have demonstrated significant success in visual understanding tasks. However, challenges persist in adapting these models for video comprehension due to the large volume of data and temporal…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Shaojie Zhang , Jiahui Yang , Jianqin Yin , Zhenbo Luo , Jian Luan

Recent advances in multimodal large language models (MLLMs) have enabled impressive progress in vision-language understanding, yet their high computational cost limits deployment in resource-constrained scenarios such as personal…

计算机视觉与模式识别 · 计算机科学 2026-04-08 Quoc-Huy Trinh , Mustapha Abdullahi , Bo Zhao , Debesh Jha

Recent advancements in reinforcement learning (RL) have enhanced the reasoning abilities of large language models (LLMs), yet the impact on multimodal LLMs (MLLMs) is limited. Particularly in vision-intensive tasks like geometric reasoning,…

计算与语言 · 计算机科学 2025-09-23 Guizhen Chen , Weiwen Xu , Hao Zhang , Hou Pong Chan , Deli Zhao , Anh Tuan Luu , Yu Rong

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Jiedong Zhuang , Lu Lu , Ming Dai , Rui Hu , Jian Chen , Qiang Liu , Haoji Hu

Multimodal Large Language Models (MLLMs) have shown impressive results on various multimodal tasks. However, most existing MLLMs are not well suited for document-oriented tasks, which require fine-grained image perception and information…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Ya-Qi Yu , Minghui Liao , Jihao Wu , Yongxin Liao , Xiaoyu Zheng , Wei Zeng

Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by…

计算机视觉与模式识别 · 计算机科学 2024-06-13 Shimin Chen , Yitian Yuan , Shaoxiang Chen , Zequn Jie , Lin Ma

Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large…

计算机视觉与模式识别 · 计算机科学 2026-04-17 Zheyu Zhang , Ziqi Pang , Shixing Chen , Xiang Hao , Vimal Bhat , Yu-Xiong Wang

Despite advances in Vision-Language-Action (VLA) models, robotic manipulation struggles with fine-grained tasks because current models lack mechanisms for active visual attention allocation. Human gaze naturally encodes intent, planning,…

计算机视觉与模式识别 · 计算机科学 2026-04-08 Anupam Pani , Yanchao Yang

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing…

计算机视觉与模式识别 · 计算机科学 2024-12-20 Qirui Jiao , Daoyuan Chen , Yilun Huang , Yaliang Li , Ying Shen

Large Multimodal Models (LMMs) for video-audio understanding have traditionally been evaluated only on shorter videos of a few minutes long. In this paper, we introduce QMAVIS (Q Team-Multimodal Audio Video Intelligent Sensemaking), a novel…

人工智能 · 计算机科学 2026-01-13 Zixing Lin , Jiale Wang , Gee Wah Ng , Lee Onn Mak , Chan Zhi Yang Jeriel , Jun Yang Lee , Yaohao Li

Despite significant advances in Multimodal Large Language Models (MLLMs), understanding complex temporal dynamics in videos remains a major challenge. Our experiments show that current Video Large Language Model (Video-LLM) architectures…

计算机视觉与模式识别 · 计算机科学 2025-10-31 Ali Rasekh , Erfan Bagheri Soula , Omid Daliran , Simon Gottschalk , Mohsen Fayyaz