中文
相关论文

相关论文: MambaPro: Multi-Modal Object Re-Identification wit…

200 篇论文

Recent advances in multi-modal detection have significantly improved detection accuracy in challenging environments (e.g., low light, overexposure). By integrating RGB with modalities such as thermal and depth, multi-modal fusion increases…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Xiaofan Yang , Yubin Liu , Wei Pan , Guoqing Chu , Junming Zhang , Jie Zhao , Zhuoqi Man , Xuanming Cao

Current strong pedestrian attribute recognition models are developed based on Transformer networks, which are computationally heavy. Recently proposed models with linear complexity (e.g., Mamba) have garnered significant attention and have…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Xiao Wang , Weizhe Kong , Jiandong Jin , Shiao Wang , Ruichong Gao , Qingchuan Ma , Chenglong Li , Jin Tang

Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging by matching signal evolutions to a predefined dictionary. However, conventional dictionary matching suffers from exponential growth in computational cost and memory…

图像与视频处理 · 电气工程与系统科学 2025-07-08 Tianyi Ding , Hongli Chen , Yang Gao , Zhuang Xiong , Feng Liu , Martijn A. Cloos , Hongfu Sun

In various domains, Sequential Recommender Systems (SRS) have become essential due to their superior capability to discern intricate user preferences. Typically, SRS utilize transformer-based architectures to forecast the subsequent item…

人工智能 · 计算机科学 2024-12-25 Ziwei Liu , Qidong Liu , Yejing Wang , Wanyu Wang , Pengyue Jia , Maolin Wang , Zitao Liu , Yi Chang , Xiangyu Zhao

Linear modeling methods like Mamba have been merged as the effective backbone for the 3D object detection task. However, previous Mamba-based methods utilize the bidirectional encoding for the whole non-empty voxel sequence, which contains…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Zhiwei Ning , Xuanang Gao , Jiaxi Cao , Runze Yang , Huiying Xu , Xinzhong Zhu , Jie Yang , Wei Liu

Human identification is a key requirement for many applications in everyday life, such as personalized services, automatic surveillance, continuous authentication, and contact tracing during pandemics, etc. This work studies the problem of…

计算机视觉与模式识别 · 计算机科学 2022-07-19 Dongjiang Cao , Ruofeng Liu , Hao Li , Shuai Wang , Wenchao Jiang , Chris Xiaoxuan Lu

RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images. In this work, we propose a novel…

计算机视觉与模式识别 · 计算机科学 2022-03-17 Zhipeng Huang , Jiawei Liu , Liang Li , Kecheng Zheng , Zheng-Jun Zha

Human intelligence can retrieve any person according to both visual and language descriptions. However, the current computer vision community studies specific person re-identification (ReID) tasks in different scenarios separately, which…

计算机视觉与模式识别 · 计算机科学 2025-04-30 Weizhen He , Yiheng Deng , Shixiang Tang , Qihao Chen , Qingsong Xie , Yizhou Wang , Lei Bai , Feng Zhu , Rui Zhao , Wanli Ouyang , Donglian Qi , Yunfeng Yan

Magnetic resonance (MR) imaging produces detailed images of organs and tissues with better contrast, but it suffers from a long acquisition time, which makes the image quality vulnerable to say motion artifacts. Recently, many approaches…

图像与视频处理 · 电气工程与系统科学 2022-02-22 Chun-Mei Feng , Huazhu Fu , Tianfei Zhou , Yong Xu , Ling Shao , David Zhang

Significant progress has been achieved in multi-object tracking (MOT) through the evolution of detection and re-identification (ReID) techniques. Despite these advancements, accurately tracking objects in scenarios with homogeneous…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Changcheng Xiao , Qiong Cao , Yujie Zhong , Long Lan , Xiang Zhang , Zhigang Luo , Dacheng Tao

Long-range 3D object detection remains challenging because LiDAR observations become highly sparse and fragmented in the far field, making reliable context modeling difficult for existing detectors. To address this issue, recent state space…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Cheng Lu , Mingqian Ji , Shanshan Zhang , Zhihao Li , Jian Yang

RGB-Infrared (IR) cross-modality person re-identification (re-ID), which aims to search an IR image in RGB gallery or vice versa, is a challenging task due to the large discrepancy between IR and RGB modalities. Existing methods address…

计算机视觉与模式识别 · 计算机科学 2020-07-06 Mengxi Jia , Yunpeng Zhai , Shijian Lu , Siwei Ma , Jian Zhang

Natural images are often degraded by complex, composite degradations such as rain, snow, and haze, which adversely impact downstream vision applications. While existing image restoration efforts have achieved notable success, they are still…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Yongzhen Wang , Yongjun Li , Zhuoran Zheng , Xiao-Ping Zhang , Mingqiang Wei

Object re-identification (ReID) in large camera networks faces numerous challenges. First, the similar appearances of objects degrade ReID performance, a challenge that needs to be addressed by existing appearance-based ReID methods.…

计算机视觉与模式识别 · 计算机科学 2024-08-23 Hye-Geun Kim , Yong-Hyuk Moon , Yeong-Jun Cho

Data associations in multi-target multi-camera tracking (MTMCT) usually estimate affinity directly from re-identification (re-ID) feature distances. However, we argue that it might not be the best choice given the difference in matching…

计算机视觉与模式识别 · 计算机科学 2021-12-15 Yunzhong Hou , Zhongdao Wang , Shengjin Wang , Liang Zheng

The goal of multimodal image fusion is to integrate complementary information from infrared and visible images, generating multimodal fused images for downstream tasks. Existing downstream pre-training models are typically trained on…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Yushen Xu , Xiaosong Li , Zhenyu Kuang , Xiaoqi Cheng , Haishu Tan , Huafeng Li

A key for person re-identification is achieving consistent local details for discriminative representation across variable environments. Current stripe-based feature learning approaches have delivered impressive accuracy, but do not make a…

计算机视觉与模式识别 · 计算机科学 2020-09-09 Guanshuo Wang , Yufeng Yuan , Jiwei Li , Shiming Ge , Xi Zhou

General object detection (OD) struggles to detect objects in the target domain that differ from the training distribution. To address this, recent studies demonstrate that training from multiple source domains and explicitly processing them…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Sangin Lee , Seokjun Kwon , Jeongmin Shin , Namil Kim , Yukyung Choi

Description-based person re-identification (Re-id) is an important task in video surveillance that requires discriminative cross-modal representations to distinguish different people. It is difficult to directly measure the similarity…

计算机视觉与模式识别 · 计算机科学 2019-06-25 Kai Niu , Yan Huang , Wanli Ouyang , Liang Wang

State Space Models (SSMs) with selective scan (Mamba) have been adapted into efficient vision models. Mamba, unlike Vision Transformers, achieves linear complexity for token interactions through a recurrent hidden state process. This…

计算机视觉与模式识别 · 计算机科学 2025-02-04 Saarthak Kapse , Robin Betz , Srinivasan Sivanandan