中文
相关论文

相关论文: SteerSeg: Attention Steering for Reasoning Video S…

200 篇论文

Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Yangfu Li , Hongjian Zhan , Jiawei Chen , Yuning Gong , Qi Liu , Yue Lu

Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and…

计算机视觉与模式识别 · 计算机科学 2025-07-24 Xuchen Li , Xuzhao Li , Shiyu Hu , Kaiqi Huang , Wentao Zhang

Recently, multi-modal large language models have made significant progress. However, visual information lacking of guidance from the user's intention may lead to redundant computation and involve unnecessary visual noise, especially in…

计算机视觉与模式识别 · 计算机科学 2025-05-29 Zheng Cheng , Rendong Wang , Zhicheng Wang

Pretrained vision-language models (VLMs), \eg CLIP, are increasingly used to bridge the gap between open- and close-vocabulary recognition in open-vocabulary image segmentation. As VLMs are generally pretrained with low-resolution images…

计算机视觉与模式识别 · 计算机科学 2024-11-28 Yuanbing Zhu , Bingke Zhu , Yingying Chen , Yunfang Niu , Ming Tang , Jinqiao Wang

Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data…

计算机视觉与模式识别 · 计算机科学 2024-08-30 Minghang Zheng , Xinhao Cai , Qingchao Chen , Yuxin Peng , Yang Liu

Semantic segmentation is a fundamental task in computer vision that involves dense pixel-wise classification for scene understanding. Despite significant progress, achieving high accuracy while maintaining real-time performance remains a…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Abhinav Sagar

Large-scale vision-language models (VLMs), trained on extensive datasets of image-text pairs, exhibit strong multimodal understanding capabilities by implicitly learning associations between textual descriptions and image regions. This…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Mir Rayat Imtiaz Hossain , Mennatullah Siam , Leonid Sigal , James J. Little

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Zhenyu Lu , Liupeng Li , Jinpeng Wang , Haoqian Kang , Yan Feng , Ke Chen , Yaowei Wang

Next-token prediction serves as the foundational learning task enabling reasoning in LLMs. But what should the learning task be when aiming to equip MLLMs with temporal reasoning capabilities over video inputs? Existing tasks such as video…

计算机视觉与模式识别 · 计算机科学 2025-05-29 Haonan Wang , Hongfu Liu , Xiangyan Liu , Chao Du , Kenji Kawaguchi , Ye Wang , Tianyu Pang

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, where plausible arguments are incorrectly deemed logically…

人工智能 · 计算机科学 2026-04-02 Marco Valentino , Geonhee Kim , Dhairya Dalal , Zhixue Zhao , André Freitas

Existing research of video understanding still struggles to achieve in-depth comprehension and reasoning in complex videos, primarily due to the under-exploration of two key bottlenecks: fine-grained spatial-temporal perceptive…

人工智能 · 计算机科学 2025-01-08 Hao Fei , Shengqiong Wu , Wei Ji , Hanwang Zhang , Meishan Zhang , Mong-Li Lee , Wynne Hsu

When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast, current multimodal large language models (MLLMs) attend to…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Junha Song , Byeongho Heo , Geonmo Gu , Jaegul Choo , Dongyoon Han , Sangdoo Yun

Video-based spatial reasoning -- such as estimating distances, judging directions, or understanding layouts from multiple views -- requires selecting informative frames and, when needed, actively seeking additional viewpoints during…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Jiaxu Wan , Xu Wang , Mengwei Xie , Hang Zhang , Mu Xu , Yang Han , Hong Zhang , Ding Yuan , Yifan Yang

Reasoning segmentation is a challenging vision-language task that aims to output the segmentation mask with respect to a complex, implicit, and even non-visual query text. Previous works incorporated multimodal Large Language Models (MLLMs)…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Shiu-hong Kao , Yu-Wing Tai , Chi-Keung Tang

In recent years, Multimodal Large Language Models (MLLMs) have made significant progress in visual question answering tasks. However, directly applying existing fine-tuning methods to remote sensing (RS) images often leads to issues such as…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Qigan Sun , Chaoning Zhang , Jianwei Zhang , Xudong Wang , Jiehui Xie , Pengcheng Zheng , Haoyu Wang , Sungyoung Lee , Chi-lok Andy Tai , Yang Yang , Heng Tao Shen

Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Haoyu Zhang , Meng Liu , Zaijing Li , Haokun Wen , Weili Guan , Yaowei Wang , Liqiang Nie

Large language models frequently produce errors in reasoning tasks despite possessing the underlying knowledge required for correct reasoning. One possible approach to improve reasoning consistency is through activation steering. However,…

机器学习 · 计算机科学 2026-05-22 Ian Li , Kapilesh Guruprasad , Raunak Sengupta , Ninad Satish , Loris D'Antoni , Rose Yu

Temporal Action Detection and Moment Retrieval constitute two pivotal tasks in video understanding, focusing on precisely localizing temporal segments corresponding to specific actions or events. Recent advancements introduced Moment…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Weijun Zhuang , Qizhang Li , Xin Li , Ming Liu , Xiaopeng Hong , Feng Gao , Fan Yang , Wangmeng Zuo

Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively handle various tasks simultaneously and enable zero-shot…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Yongxin Guo , Jingyu Liu , Mingda Li , Qingbin Liu , Xi Chen , Xiaoying Tang

Current high-performance semantic segmentation models are purely data-driven sub-symbolic approaches and blind to the structured nature of the visual world. This is in stark contrast to human cognition which abstracts visual perceptions at…

计算机视觉与模式识别 · 计算机科学 2023-09-29 Liulei Li , Wenguan Wang , Yi Yang
‹ 上一页 1 8 9 10 下一页 ›