中文
相关论文

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

200 篇论文

Training-free video large language models (LLMs) leverage pretrained Image LLMs to process video content without the need for further training. A key challenge in such approaches is the difficulty of retaining essential visual and temporal…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Leqi Shen , Tao He , Guoqiang Gong , Fan Yang , Yifeng Zhang , Pengzhang Liu , Sicheng Zhao , Guiguang Ding

Conversational image segmentation grounds abstract, intent-driven concepts into pixel-accurate masks. Prior work on referring image grounding focuses on categorical and spatial queries (e.g., "left-most apple") and overlooks functional and…

计算机视觉与模式识别 · 计算机科学 2026-02-16 Aadarsh Sahoo , Georgia Gkioxari

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

计算机视觉与模式识别 · 计算机科学 2025-07-21 Binbin Ji , Siddharth Agrawal , Qiance Tang , Yvonne Wu

Recent advances in legged locomotion learning are still dominated by the utilization of geometric representations of the environment, limiting the robot's capability to respond to higher-level semantics such as human instructions. To…

机器人学 · 计算机科学 2026-02-12 I Made Aswin Nahrendra , Seunghyun Lee , Dongkyu Lee , Hyun Myung

Emerging unified editing models have demonstrated strong capabilities in general object editing tasks. However, it remains a significant challenge to perform fine-grained editing in complex multi-entity scenes, particularly those where…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Yecong Wan , Fan Li , Chunwei Wang , Hao Wu , Mingwen Shao , Wangmeng Zuo

Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Ilias Stogiannidis , Steven McDonagh , Sotirios A. Tsaftaris

In recent years, video question answering based on multimodal large language models (MLLM) has garnered considerable attention, due to the benefits from the substantial advancements in LLMs. However, these models have a notable deficiency…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Jinglei Zhang , Yuanfan Guo , Rolandos Alexandros Potamias , Jiankang Deng , Hang Xu , Chao Ma

The reasoning segmentation task involves segmenting objects within an image by interpreting implicit user instructions, which may encompass subtleties such as contextual cues and open-world knowledge. Despite significant advancements made…

计算机视觉与模式识别 · 计算机科学 2025-08-14 Weihuang Lin , Yiwei Ma , Xiaoshuai Sun , Shuting He , Jiayi Ji , Liujuan Cao , Rongrong Ji

Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring precise spatiotemporal localization at the instance level. Existing methods primarily rely…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Yiming Zhao , Yu Zeng , Wenxuan Huang , Zhen Fang , Qing Miao , Qisheng Su , Jiawei Zhao , Jiayin Cai , Lin Chen , Zehui Chen , Yukun Qi , Yao Hu , Xiaolong Jiang , Feng Zhao

The complexity of the real world demands robotic systems that can intelligently adapt to unseen situations. We present STEER, a robot learning framework that bridges high-level, commonsense reasoning with precise, flexible low-level…

The Segment Anything Model (SAM) has gained significant attention for its impressive performance in image segmentation. However, it lacks proficiency in referring video object segmentation (RVOS) due to the need for precise user-interactive…

计算机视觉与模式识别 · 计算机科学 2024-09-04 Yonglin Li , Jing Zhang , Xiao Teng , Long Lan , Xinwang Liu

It is critical for vision-language models (VLMs) to comprehensively understand visual, temporal, and textual cues. However, despite rapid progress in multimodal modeling, video understanding performance still lags behind text-based…

计算机视觉与模式识别 · 计算机科学 2026-04-08 Yuxuan Zhang , EunJeong Hwang , Huaisong Zhang , Penghui Du , Yiming Jia , Dongfu Jiang , Xuan He , Shenhui Zhang , Ping Nie , Peter West , Kelsey R. Allen

Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to…

计算机视觉与模式识别 · 计算机科学 2022-11-30 Tianfei Zhou , Fatih Porikli , David Crandall , Luc Van Gool , Wenguan Wang

Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in…

计算机视觉与模式识别 · 计算机科学 2023-09-04 Ali Athar , Sabarinath Mahadevan , Aljoša Ošep , Laura Leal-Taixé , Bastian Leibe

Vision Language Models (VLMs) have recently achieved significant progress in bridging visual perception and linguistic reasoning. Recently, OpenAI o3 model introduced a zoom-in search strategy that effectively elicits active perception…

计算机视觉与模式识别 · 计算机科学 2025-09-05 Wanfu Wang , Qipeng Huang , Guangquan Xue , Xiaobo Liang , Juntao Li

Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignment or process imitation, lacking explicit constraints on the…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Jiangyang Li , Cong Wan , Changjie Wu , Songlin Dong , Lingjun Zhang , Linzhe Shi , Xu Wang , Zhiheng Ma , Hang Zhang , Mu Xu , Yihong Gong

Natural scene analysis and remote sensing imagery offer immense potential for advancements in large-scale language-guided context-aware data utilization. This potential is particularly significant for enhancing performance in downstream…

计算机视觉与模式识别 · 计算机科学 2023-10-30 Lei Li

Video anomaly detection (VAD) aims to identify abnormal events in videos. Traditional VAD methods generally suffer from the high costs of labeled data and full training, thus some recent works have explored leveraging frozen multi-modal…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Zhaolin Cai , Fan Li , Huiyu Duan , Lijun He , Guangtao Zhai

Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: inadequate 3D understanding capabilities stemming from…

计算机视觉与模式识别 · 计算机科学 2026-03-06 Yejie Guo , Yunzhong Hou , Wufei Ma , Meng Tang , Ming-Hsuan Yang

Inspired by recent advances in neural machine translation, that jointly align and translate using encoder-decoder networks equipped with attention, we propose an attentionbased LSTM model for human activity recognition. Our model jointly…

计算机视觉与模式识别 · 计算机科学 2017-09-01 Atousa Torabi , Leonid Sigal