中文
相关论文

相关论文: Triple Correlations-Guided Label Supplementation f…

200 篇论文

Most of current image captioning models heavily rely on paired image-caption datasets. However, getting large scale image-caption paired data is labor-intensive and time-consuming. In this paper, we present a scene graph-based approach for…

计算机视觉与模式识别 · 计算机科学 2019-08-20 Jiuxiang Gu , Shafiq Joty , Jianfei Cai , Handong Zhao , Xu Yang , Gang Wang

Video self-supervised learning is a challenging task, which requires significant expressive power from the model to leverage rich spatial-temporal knowledge and generate effective supervisory signals from large amounts of unlabeled videos.…

计算机视觉与模式识别 · 计算机科学 2023-07-19 Yang Liu , Keze Wang , Lingbo Liu , Haoyuan Lan , Liang Lin

Dynamic Scene Graph Generation (DSGG) focuses on identifying visual relationships within the spatial-temporal domain of videos. Conventional approaches often employ multi-stage pipelines, which typically consist of object detection,…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Guan Wang , Zhimin Li , Qingchao Chen , Yang Liu

Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…

机器学习 · 计算机科学 2023-05-23 Gang Liu , Tong Zhao , Eric Inae , Tengfei Luo , Meng Jiang

We investigate the problem of producing structured graph representations of visual scenes. Our work analyzes the role of motifs: regularly appearing substructures in scene graphs. We present new quantitative insights on such repeated…

计算机视觉与模式识别 · 计算机科学 2018-03-30 Rowan Zellers , Mark Yatskar , Sam Thomson , Yejin Choi

Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models.…

计算机视觉与模式识别 · 计算机科学 2017-09-28 Mang Ye , Andy J Ma , Liang Zheng , Jiawei Li , P C Yuen

We propose a text-to-image generation algorithm based on deep neural networks when text captions for images are unavailable during training. In this work, instead of simply generating pseudo-ground-truth sentences of training images using…

计算机视觉与模式识别 · 计算机科学 2023-03-29 Minsoo Kang , Doyup Lee , Jiseob Kim , Saehoon Kim , Bohyung Han

Multi-label learning has attracted significant interests in computer vision recently, finding applications in many vision tasks such as multiple object recognition and automatic image annotation. Associating multiple labels to a complex…

计算机视觉与模式识别 · 计算机科学 2016-08-05 Hao Yang , Joey Tianyi Zhou , Jianfei Cai

Precise action spotting has attracted considerable attention due to its promising applications. While existing methods achieve substantial performance by employing well-designed model architecture, they overlook a significant challenge: the…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Masato Tamura

Most of the existing works on human activity analysis focus on recognition or early recognition of the activity labels from complete or partial observations. Similarly, almost all of the existing video captioning approaches focus on the…

计算机视觉与模式识别 · 计算机科学 2021-05-28 Tahmida Mahmud , Mohammad Billah , Mahmudul Hasan , Amit K. Roy-Chowdhury

Research in scene graph generation (SGG) usually considers two-stage models, that is, detecting a set of entities, followed by combining them and labeling all possible relationships. While showing promising results, the pipeline structure…

计算机视觉与模式识别 · 计算机科学 2023-06-12 Alakh Desai , Tz-Ying Wu , Subarna Tripathi , Nuno Vasconcelos

Diverse video captioning aims to generate a set of sentences to describe the given video in various aspects. Mainstream methods are trained with independent pairs of a video and a caption from its ground-truth set without exploiting the…

计算机视觉与模式识别 · 计算机科学 2024-01-01 Yifan Lu , Ziqi Zhang , Chunfeng Yuan , Peng Li , Yan Wang , Bing Li , Weiming Hu

Panoptic Scene Graph has recently been proposed for comprehensive scene understanding. However, previous works adopt a fully-supervised learning manner, requiring large amounts of pixel-wise densely-annotated data, which is always tedious…

计算机视觉与模式识别 · 计算机科学 2025-04-11 Chengyang Zhao , Yikang Shen , Zhenfang Chen , Mingyu Ding , Chuang Gan

Joint video-language learning has received increasing attention in recent years. However, existing works mainly focus on single or multiple trimmed video clips (events), which makes human-annotated event boundaries necessary during…

计算机视觉与模式识别 · 计算机科学 2023-05-18 Teng Wang , Jinrui Zhang , Feng Zheng , Wenhao Jiang , Ran Cheng , Ping Luo

Unsupervised graph representation learning(GRL) aims to distill diverse graph information into task-agnostic embeddings without label supervision. Due to a lack of support from labels, recent representation learning methods usually adopt…

机器学习 · 计算机科学 2023-04-18 Bei Lin , You Li , Ning Gui , Zhuopeng Xu , Zhiwu Yu

Training Scene Graph Generation (SGG) models with natural language captions has become increasingly popular due to the abundant, cost-effective, and open-world generalization supervision signals that natural language offers. However, such…

计算机视觉与模式识别 · 计算机科学 2024-06-04 Zuyao Chen , Jinlin Wu , Zhen Lei , Zhaoxiang Zhang , Changwen Chen

Scene graph generation aims to identify objects and their relations in images, providing structured image representations that can facilitate numerous applications in computer vision. However, scene graph models usually require supervised…

计算机视觉与模式识别 · 计算机科学 2021-08-23 Yuan Yao , Ao Zhang , Xu Han , Mengdi Li , Cornelius Weber , Zhiyuan Liu , Stefan Wermter , Maosong Sun

Video anomaly detection has proved to be a challenging task owing to its unsupervised training procedure and high spatio-temporal complexity existing in real-world scenarios. In the absence of anomalous training samples, state-of-the-art…

计算机视觉与模式识别 · 计算机科学 2022-11-17 Masoud Pourreza , Mohammadreza Salehi , Mohammad Sabokrou

Scene graph generation (SGG) is an important task in image understanding because it represents the relationships between objects in an image as a graph structure, making it possible to understand the semantic relationships between objects…

计算机视觉与模式识别 · 计算机科学 2024-05-22 Hyeongjin Kim , Sangwon Kim , Dasom Ahn , Jong Taek Lee , Byoung Chul Ko

Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might…

计算机视觉与模式识别 · 计算机科学 2024-01-24 Xin Lin , Chong Shi , Yibing Zhan , Zuopeng Yang , Yaqi Wu , Dacheng Tao