中文
相关论文

相关论文: A Theory-Inspired Framework for Few-Shot Cross-Mod…

200 篇论文

Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They…

计算机视觉与模式识别 · 计算机科学 2025-07-15 Lingfeng He , De Cheng , Zhiheng Ma , Huaijie Wang , Dingwen Zhang , Nannan Wang , Xinbo Gao

Caricature attributes provide distinctive facial features to help research in Psychology and Neuroscience. However, unlike the facial photo attribute datasets that have a quantity of annotated images, the annotations of caricature…

计算机视觉与模式识别 · 计算机科学 2020-07-21 Wen Ji , Kelei He , Jing Huo , Zheng Gu , Yang Gao

Although sketch-to-photo retrieval has a wide range of applications, it is costly to obtain paired and rich-labeled ground truth. Differently, photo retrieval data is easier to acquire. Therefore, previous works pre-train their models on…

计算机视觉与模式识别 · 计算机科学 2022-12-07 Fan Yang , Yang Wu , Zheng Wang , Xiang Li , Sakriani Sakti , Satoshi Nakamura

Recently, weakly supervised person search is proposed to discard human-annotated identities and train the model with only bounding box annotations. A natural way to solve this problem is to separate it into detection and unsupervised…

计算机视觉与模式识别 · 计算机科学 2022-03-29 Chengyou Jia , Minnan Luo , Caixia Yan , Xiaojun Chang , Qinghua Zheng

Few-shot segmentation aims to train a segmentation model that can fast adapt to a novel task for which only a few annotated images are provided. Most recent models have adopted a prototype-based paradigm for few-shot inference. These…

计算机视觉与模式识别 · 计算机科学 2024-01-19 Li Guo , Haoming Liu , Yuxuan Xia , Chengyu Zhang , Xiaochen Lu

Person re-identification (re-ID) requires densely distributed cameras. In practice, the person of interest may not be captured by cameras and, therefore, needs to be retrieved using subjective information (e.g., sketches from witnesses).…

计算机视觉与模式识别 · 计算机科学 2023-09-18 Kejun Lin , Zhixiang Wang , Zheng Wang , Yinqiang Zheng , Shin'ichi Satoh

Inspired by the effectiveness of adversarial training in the area of Generative Adversarial Networks we present a new approach for learning feature representations in person re-identification. We investigate different types of bias that…

计算机视觉与模式识别 · 计算机科学 2019-04-02 Sara Iodice , Krystian Mikolajczyk

With the assistance of sophisticated training methods applied to single labeled datasets, the performance of fully-supervised person re-identification (Person Re-ID) has been improved significantly in recent years. However, these models…

计算机视觉与模式识别 · 计算机科学 2021-02-03 Shan Lin , Chang-Tsun Li , Alex C. Kot

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

In this paper we introduce a method to overcome one of the main challenges of person re-identification in multi-camera networks, namely cross-view appearance changes. The proposed solution addresses the extreme variability of person…

计算机视觉与模式识别 · 计算机科学 2017-03-22 Giuseppe Lisanti , Svebor Karaman , Iacopo Masi

Face sketch to digital image matching is an important challenge of face recognition that involves matching across different domains. Current research efforts have primarily focused on extracting domain invariant representations or learning…

计算机视觉与模式识别 · 计算机科学 2017-10-10 Shruti Nagpal , Maneet Singh , Richa Singh , Mayank Vatsa , Afzel Noore , Angshul Majumdar

Person re-identification (re-id) is to match people across disjoint camera views in a multi-camera system, and re-id has been an important technology applied in smart city in recent years. However, the majority of existing person re-id…

计算机视觉与模式识别 · 计算机科学 2017-11-10 Wei-Hong Li , Zhuowei Zhong , Wei-Shi Zheng

Recent advances in Visual Question Answering (VQA) have demonstrated impressive performance in natural image domains, with models like LLaVA leveraging large language models (LLMs) for open-ended reasoning. However, their generalization…

计算机视觉与模式识别 · 计算机科学 2025-10-31 Xinjin Li , Yulie Lu , Jinghan Cao , Yu Ma , Zhenglin Li , Yeyang Zhou

An ongoing major challenge in computer vision is the task of person re-identification, where the goal is to match individuals across different, non-overlapping camera views. While recent success has been achieved via supervised learning…

计算机视觉与模式识别 · 计算机科学 2020-01-15 Devinder Kumar , Parthipan Siva , Paul Marchwica , Alexander Wong

Different from existing cross-modality identification tasks (e.g., heterogeneous face recognition, sketch re-identification, etc.), we introduce a novel yet practical setting for these related identification tasks, named \textbf{sketch…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Decheng Liu , Bin Hu , Xinbo Gao , Dawei Zhou , Chunlei Peng , Nannan Wang , Ruimin Hu

Person Re-identification (ReID) has been advanced remarkably over the last 10 years along with the rapid development of deep learning for visual recognition. However, the i.i.d. (independent and identically distributed) assumption commonly…

计算机视觉与模式识别 · 计算机科学 2022-05-24 Qilei Li , Jiabo Huang , Jian Hu , Shaogang Gong

Entity alignment (EA) aims at finding equivalent entities in different knowledge graphs (KGs). Embedding-based approaches have dominated the EA task in recent years. Those methods face problems that come from the geometric properties of…

数据库 · 计算机科学 2022-06-07 Yunjun Gao , Xiaoze Liu , Junyang Wu , Tianyi Li , Pengfei Wang , Lu Chen

In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain. As an important tool of regularizing the distribution, batch normalization…

计算机视觉与模式识别 · 计算机科学 2022-03-29 Ke Han , Chenyang Si , Yan Huang , Liang Wang , Tieniu Tan

Person re-identification (re-id), the process of matching pedestrian images across different camera views, is an important task in visual surveillance. Substantial development of re-id has recently been observed, and the majority of…

计算机视觉与模式识别 · 计算机科学 2020-02-10 Qize Yang , Ancong Wu , Wei-Shi Zheng

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic…

机器学习 · 计算机科学 2020-02-19 Chen Xing , Negar Rostamzadeh , Boris N. Oreshkin , Pedro O. Pinheiro
‹ 上一页 1 2 3 10 下一页 ›