中文
相关论文

相关论文: TF-CLIP: Learning Text-free CLIP for Video-based P…

200 篇论文

Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks, including video ones such as action recognition and text-to-video retrieval. However, these models have not been adapted to video,…

计算机视觉与模式识别 · 计算机科学 2022-10-07 Santiago Castro , Fabian Caba Heilbron

Person Re-Identification (ReID) aims to recognize a person-of-interest across different places and times. Existing ReID methods rely on images or videos collected using RGB cameras. They extract appearance features like clothes, shoes,…

计算机视觉与模式识别 · 计算机科学 2020-04-03 Lijie Fan , Tianhong Li , Rongyao Fang , Rumen Hristov , Yuan Yuan , Dina Katabi

The Contrastive Language-Image Pre-training (CLIP) Model is a recently proposed large-scale pre-train model which attracts increasing attention in the computer vision community. Benefiting from its gigantic image-text training set, the CLIP…

计算机视觉与模式识别 · 计算机科学 2022-07-21 Yuxuan Ding , Lingqiao Liu , Chunna Tian , Jingyuan Yang , Haoxuan Ding

Person re-identification (ReID) aims to extract accurate identity representation features. However, during feature extraction, individual samples are inevitably affected by noise (background, occlusions, and model limitations). Considering…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Chao Yuan , Guiwei Zhang , Changxiao Ma , Tianyi Zhang , Guanglin Niu

Clothes-Changing Person Re-Identification (ReID) aims to recognize the same individual across different videos captured at various times and locations. This task is particularly challenging due to changes in appearance, such as clothing,…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Asaf Joseph , Shmuel Peleg

Text-based person re-identification (Re-ID) is a challenging topic in the field of complex multimodal analysis, its ultimate aim is to recognize specific pedestrians by scrutinizing attributes/natural language descriptions. Despite the wide…

计算机视觉与模式识别 · 计算机科学 2024-08-02 Fanzhi Jiang , Su Yang , Mark W. Jones , Liumei Zhang

Text-based Person Retrieval (TPR) aims to retrieve the target person images given a textual query. The primary challenge lies in bridging the substantial gap between vision and language modalities, especially when dealing with limited…

计算机视觉与模式识别 · 计算机科学 2024-01-03 Yating Liu , Yaowei Li , Zimo Liu , Wenming Yang , Yaowei Wang , Qingmin Liao

Multimodal large language models (MLLM) have achieved satisfactory results in many tasks. However, their performance in the task of ReID (ReID) has not been explored to date. This paper will investigate how to adapt them for the task of…

计算机视觉与模式识别 · 计算机科学 2024-06-11 Shan Yang , Yongfei Zhang

Traditional text-based person re-identification (ReID) techniques heavily rely on fully matched multi-modal data, which is an ideal scenario. However, due to inevitable data missing and corruption during the collection and processing of…

计算机视觉与模式识别 · 计算机科学 2023-10-04 Tiantian Gong , Guodong Du , Junsheng Wang , Yongkang Ding , Liyan Zhang

Recent advances in person re-identification have demonstrated enhanced discriminability, especially with supervised learning or transfer learning. However, since the data requirements---including the degree of data curations---are becoming…

计算机视觉与模式识别 · 计算机科学 2020-11-04 Kshitij Nikhal , Benjamin S. Riggan

To address the occlusion issues in person Re-Identification (ReID) tasks, many methods have been proposed to extract part features by introducing external spatial information. However, due to missing part appearance information caused by…

计算机视觉与模式识别 · 计算机科学 2024-10-01 Can Cui , Siteng Huang , Wenxuan Song , Pengxiang Ding , Min Zhang , Donglin Wang

Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information and thus is freely deployed to new scenarios. There are very few…

计算机视觉与模式识别 · 计算机科学 2020-04-08 Yutian Lin , Lingxi Xie , Yu Wu , Chenggang Yan , Qi Tian

Among numerous videos shared on the web, well-edited ones always attract more attention. However, it is difficult for inexperienced users to make well-edited videos because it requires professional expertise and immense manual labor. To…

计算机视觉与模式识别 · 计算机科学 2023-11-21 Yu Xiong , Fabian Caba Heilbron , Dahua Lin

Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security. Matching persons across disjoint camera views in their video fragments is inherently challenging due to the…

计算机视觉与模式识别 · 计算机科学 2018-10-17 Lin Wu , Yang Wang , Junbin Gao , Xue Li

Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality…

计算机视觉与模式识别 · 计算机科学 2023-12-20 Yuwei Guo , Wenhao Zhang , Licheng Jiao , Shuang Wang , Shuo Wang , Fang Liu

Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and limited training samples. Existing methods mainly leverage auxiliary information to…

计算机视觉与模式识别 · 计算机科学 2024-06-21 Qizao Wang , Xuelin Qian , Bin Li , Xiangyang Xue , Yanwei Fu

Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from semantic drift, limited adaptability, and catastrophic forgetting as new domains emerge.…

计算机视觉与模式识别 · 计算机科学 2026-05-07 Wen Wen , Hao Chen , Shiliang Zhang

Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image, however, the performance is unreliable in challenging scenarios, such as heavy occlusion, motion blur, etc. In this work, we propose to…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Xiao Wang , Qian Zhu , Jiandong Jin , Jun Zhu , Futian Wang , Bo Jiang , Yaowei Wang , Yonghong Tian

Adapting CLIP for videos has gained popularity due to its semantic and rich representation. While CLIP is a good starting point, it typically undergoes post-pretraining (contrastive finetuning) on large video narration or caption datasets…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Darshan Singh , Zeeshan Khan , Makarand Tapaswi

Person Re-Identification (re-id) is a challenging task in computer vision, especially when there are limited training data from multiple camera views. In this paper, we pro- pose a deep learning based person re-identification method by…

计算机视觉与模式识别 · 计算机科学 2016-11-21 Qiqi Xiao , Kelei Cao , Haonan Chen , Fangyue Peng , Chi Zhang
‹ 上一页 1 8 9 10 下一页 ›