2,316 Hits in 4.9 sec

Social Adaptive Module for Weakly-supervised Group Activity Recognition [article]

Rui Yan, Lingxi Xie, Jinhui Tang, Xiangbo Shu, Qi Tian
2020 arXiv   pre-print
This paper presents a new task named weakly-supervised group activity recognition (GAR) which differs from conventional GAR tasks in that only video-level labels are available, yet the important persons  ...  To mine useful information from weak supervision, we present a key insight that key instances are likely to be related to each other, and thus design a social adaptive module (SAM) to reason about key  ...  Weakly-supervised Group Activity Recognition Weakly-supervised Setting For a more practical group activity recognition, i) the number of people in the scene varies over different activities even time  ... 
arXiv:2007.09470v1 fatcat:5lc2zk2rtfchtg2ksk3ao2g5di

MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection [article]

Fa-Ting Hong, Xuanteng Huang, Wei-Hong Li, Wei-Shi Zheng
2020 arXiv   pre-print
We address the weakly supervised video highlight detection problem for learning to detect segments that are more attractive in training videos given their video event label but without expensive supervision  ...  In this work, we propose casting weakly supervised video highlight detection modeling for a given specific event as a multiple instance ranking network (MINI-Net) learning.  ...  The second strategy treats video highlight detection as a weakly supervised recognition task [34, 31, 29] .  ... 
arXiv:2007.09833v2 fatcat:i66exkby2fbejmir2jftgfcsqm

Visual Social Relationship Recognition [article]

Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli
2018 arXiv   pre-print
Since visually identifying social relationship bears certain degree of uncertainty, we further propose an Adaptive Focal Loss to leverage the ambiguous annotations for more effective learning.  ...  We propose a Dual-Glance model for social relationship recognition, where the first glance fixates at the person of interest and the second glance deploys attention mechanism to exploit contextual cues  ...  For group activity recognition, social roles and relationship information have been implicitly embedded into the inference model (Choi and Savarese 2012; Deng et al 2016; Direkoglu and O'Connor 2012; Lan  ... 
arXiv:1812.05917v1 fatcat:rublmiitdbf4hibkfneucm5you

Physiological Inspired Deep Neural Networks for Emotion Recognition

Pedro M. Ferreira, Filipe Marques, Jaime S. Cardoso, Ana Rebelo
2018 IEEE Access  
Facial expression recognition (FER) is currently one of the most active research topics due to its wide range of applications in the human-computer interaction field.  ...  .: Physiological Inspired Deep Neural Networks for Emotion Recognition FIGURE 1. Illustration of the main challenges of FER.  ...  Figures 9 and 10 depict the learned relevance mapsx for some test samples using the proposed fully supervised and weakly supervised regularization schemes, respectively.  ... 
doi:10.1109/access.2018.2870063 fatcat:6euqkvfmkfgajdhzmcfrvmgqnm

A Survey on Temporal Action Localization

Huifen Xia, Yongzhao Zhan
2020 IEEE Access  
In addition, we summarize temporal action localization from two aspects: fully-supervised learning and weakly-supervised learning.  ...  And more demand is for temporal action localization in untrimmed videos. In this paper, our target is to survey the state-of-the-art techniques and models for video temporal action localization.  ...  Temporal class activation mapping (T-CAM) or Class activation sequence (CAS) is another recently group of methods for W-TAL.  ... 
doi:10.1109/access.2020.2986861 fatcat:rsndgkzhi5fm5l6nmfmgfvugby

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TIP 2021 5573-5588 Semi-Supervised Low-Rank Semantics Grouping for Zero-Shot Learning. Dual Modulated QR Codes for Proximal Privacy and Security.  ...  Gui, Relational Reasoning for Group Activity Recognition via Self-Attention standing. Wang, L., +, TIP 2021 7541-7553 and Bright Channels.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

A Comprehensive Review of Group Activity Recognition in Videos

Li-Fang Wu, Qi Wang, Meng Jian, Yu Qiao, Bo-Xuan Zhao
2021 International Journal of Automation and Computing  
From this comprehensive literature review, readers can obtain an overview of progress in group activity recognition for future studies.  ...  AbstractHuman group activity recognition (GAR) has attracted significant attention from computer vision researchers due to its wide practical applications in security surveillance, social role understanding  ...  Weakly-supervised group activity recognition tasks where only video-level group activity is accessible could be another direction for group activity recognition.  ... 
doi:10.1007/s11633-020-1258-8 fatcat:ycka4thcy5a6vghpenpthtrndi

Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospects [article]

Bing Wei, Yudi Zhao, Kuangrong Hao, Lei Gao
2021 arXiv   pre-print
Through this survey, it will provide a comprehensive reference for research in this direction.  ...  Finally, for weakly supervised-based models based on feedforward inference, Cao et al.  ...  supervised supervised supervised supervised supervised unsupervised unsupervised unsupervised weakly supervised  ... 
arXiv:2109.03391v1 fatcat:xtgda2x6azd2laun45tqfj77gi

Editorial: From Stimulus to Behavioral Decision-Making

Gérard Manière, Gérard Coureaud
2020 Frontiers in Behavioral Neuroscience  
Indeed, the activation of a cluster of octopaminergic neurons leads to an attraction toward ethanol, while the activation of another group of octopaminergic neurons results in avoidance of the same stimulus  ...  ., for food searching, identification of conspecifics, recognition of sexual partners, or detecting dangers such as predators or noxious compounds.  ...  AUTHOR CONTRIBUTIONS GM and GC conceived and supervised this Frontiers Research Topic and wrote and edited the editorial.  ... 
doi:10.3389/fnbeh.2019.00274 pmid:31998089 pmcid:PMC6965054 fatcat:huiiwhkxcnh7rphwzw5q5j7ktm

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TMM 2021 4171-4183 Weakly Supervised Emotion Intensity Prediction for Recognition of Emotions in Images.  ...  ., +, TMM 2021 2683-2693 Weakly Supervised Emotion Intensity Prediction for Recognition of Emo-tions in Images.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

Deep multiple instance learning for image classification and auto-annotation

Jiajun Wu, Yinan Yu, Chang Huang, Kai Yu
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we attempt to model deep learning in a weakly supervised learning (multiple instance learning) framework.  ...  However, there has been little investigation on how we could build up a deep learning framework in a weakly supervised setting.  ...  Deep Multiple Instance Learning (DMIL) In this section, we present our method for learning deep representations in a weakly supervised manner.  ... 
doi:10.1109/cvpr.2015.7298968 dblp:conf/cvpr/WuYHY15 fatcat:x4b4cmcuvzbdphuevi6f2upy2a

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
for Unconstrained Face Recognition DAY 4 -Jan 15, 2021 -DAY 4 -Jan 15, 2021 Yang, Zhengyuan; Li, Yuncheng; Yang, Linjie; Zhang, Ning; Luo, Jiebo 78 OS T2.3 Weakly Supervised Body Part Segmentation with  ...  ; Wang, Shilin; Zhu, Yiwei; Huang, Zheng; Chen, Kai 391 Weakly Supervised Attention Rectification for Scene Text Recognition DAY 3 -Jan 14, 2021 Guo, Jun; Wei, Wenjing; Ma, Yifeng; Peng, Cong  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

A Survey of Deep Learning-based Object Detection

Licheng Jiao, Fan Zhang, Fang Liu, Shuyuan Yang, Lingling Li, Zhixi Feng, Rong Qu
2019 IEEE Access  
With the rapid development of deep learning networks for detection tasks, the performance of object detectors has been greatly improved.  ...  Weakly supervised deep detection network in [222] is a representative framework for weakly supervised object detection.  ...  We describe some representative branches in this part. 1) WEAKLY SUPERVISED OBJECT DETECTION Weakly supervised object detection (WSOD) aims at utilizing a few fully annotated images (supervision) to  ... 
doi:10.1109/access.2019.2939201 fatcat:jesz2av2tjbkxfpaqyecptgls4

Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions [article]

Anil Rahate, Rahee Walambe, Sheela Ramanna, Ketan Kotecha
2021 arXiv   pre-print
Our final goal is to discuss challenges and perspectives along with the important ideas and directions for future work that we hope to be beneficial for the entire research community focusing on this exciting  ...  Semi-supervised Un-supervised Weakly supervised Domain Adaptation Domain General.  ...  Text data from different news portals and associated images from social media are utilized in a weakly supervised manner.  ... 
arXiv:2107.13782v2 fatcat:s4spofwxjndb7leqbcqnwbifq4

Surveying Human Habit Modeling and Mining Techniques in Smart Spaces

Francesco Leotta, Massimo Mecella, Daniele Sora, Tiziana Catarci
2019 Future Internet  
Approaches suggested in the literature may differ in terms of required facilities, possible applications, amount of human intervention required, ability to support multiple users at the same time adapting  ...  These dimensions allow to choose a specific method or approach according to available sensors, amount of labeled data, need for visual analysis, requirements in terms of enactment and decision-making on  ...  Weakly supervised recognition of daily life activities with wearable sensors.  ... 
doi:10.3390/fi11010023 fatcat:hdvhtvf7qbavthdxdwjrwfvjy4
« Previous Showing results 1 — 15 out of 2,316 results