no code implementations • 4 May 2024 • Meiqi Cao, Rui Yan, Xiangbo Shu, Guangzhao Dai, Yazhou Yao, Guo-Sen Xie
Therefore, we propose a novel Adapt-Focused bi-Propagating Prototype learning (AdaFPP) framework to jointly recognize individual, group, and global activities in panoramic activity scenes by learning an adapt-focused detector and multi-granularity prototypes as the pretext tasks in an end-to-end way.
no code implementations • 3 May 2024 • Hongyu Qu, Rui Yan, Xiangbo Shu, Haoliang Gao, Peng Huang, Guo-Sen Xie
Recent few-shot action recognition (FSAR) methods achieve promising performance by performing semantic matching on learned discriminative features.
no code implementations • 18 Jan 2024 • Guangzhao Dai, Xiangbo Shu, Wenhao Wu
Vision-Language Models (VLMs), pre-trained on large-scale datasets, have shown impressive performance in various visual recognition tasks.
no code implementations • 8 Apr 2023 • Binqian Xu, Xiangbo Shu, Rui Yan, Guo-Sen Xie, Yixiao Ge, Mike Zheng Shou
In particular, we propose a novel Attack-Augmentation Mixing-Contrastive learning (A$^2$MC) to contrast hard positive features and hard negative features for learning more robust skeleton representations.
1 code implementation • 5 Feb 2023 • Binqian Xu, Xiangbo Shu
Most semi-supervised skeleton-based action recognition approaches aim to learn the skeleton action representations only at the joint level, but neglect the crucial motion characteristics at the coarser-grained body (e. g., limb, trunk) level that provide rich additional semantic information, though the number of labeled data is limited.
no code implementations • 5 Feb 2023 • Binqian Xu, Xiangbo Shu
Moreover, we present a new Spatial-squeezing Temporal-contrasting Loss (STL), a new Temporal-squeezing Spatial-contrasting Loss (TSL), and the Global-contrasting Loss (GL) to contrast the spatial-squeezing joint and motion features at the frame level, temporal-squeezing joint and motion features at the joint level, as well as global joint and motion features at the skeleton level.
1 code implementation • 23 Jan 2023 • Fei Shen, Xiaoyu Du, Liyan Zhang, Xiangbo Shu, Jinhui Tang
To address this problem, in this paper, we propose a simple Triplet Contrastive Representation Learning (TCRL) framework which leverages cluster features to bridge the part features and global features for unsupervised vehicle re-identification.
1 code implementation • ICCV 2023 • Bo Fang, Wenhao Wu, Chang Liu, Yu Zhou, Yuxin Song, Weiping Wang, Xiangbo Shu, Xiangyang Ji, Jingdong Wang
In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation.
1 code implementation • 13 Dec 2022 • Bin Wang, Yan Song, Fanming Wang, Yang Zhao, Xiangbo Shu, Yan Rui
To balance the annotation labor and the granularity of supervision, single-frame annotation has been introduced in temporal action localization.
no code implementations • CVPR 2022 • Zeren Sun, Fumin Shen, Dan Huang, Qiong Wang, Xiangbo Shu, Yazhou Yao, Jinhui Tang
Label noise has been a practical challenge in deep learning due to the strong capability of deep neural networks in fitting all training data.
no code implementations • 21 Dec 2021 • Xiangbo Shu, Jiawen Yang, Rui Yan, Yan Song
This work focuses on the task of elderly activity recognition, which is a challenging task due to the existence of individual actions and human-object interactions in elderly activities.
1 code implementation • 10 Dec 2020 • Rui Yan, Lingxi Xie, Xiangbo Shu, Jinhui Tang
To understand a complex action, multiple sources of information, including appearance, positional, and semantic features, need to be integrated.
1 code implementation • 6 Aug 2020 • Chuanyi Zhang, Yazhou Yao, Xiangbo Shu, Zechao Li, Zhenmin Tang, Qi Wu
To this end, we propose a data-driven meta-set based approach to deal with noisy web images for fine-grained recognition.
no code implementations • ECCV 2020 • Rui Yan, Lingxi Xie, Jinhui Tang, Xiangbo Shu, Qi Tian
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 within each frame are not provided even in the training data.
no code implementations • 29 Sep 2019 • Xiangbo Shu, Liyan Zhang, Guo-Jun Qi, Wei Liu, Jinhui Tang
To this end, we propose a novel Skeleton-joint Co-attention Recurrent Neural Networks (SC-RNN) to capture the spatial coherence among joints, and the temporal evolution among skeletons simultaneously on a skeleton-joint co-attention feature map in spatiotemporal space.
no code implementations • 3 Jul 2019 • Jian Wang, Xiaoyao Li, Xiangbo Shu, Weiqin Li
Specifically, to effectively highlight the imperceptible lesion regions, a novel region-manipulated scheme in RMFN is proposed to force the lesion regions while weaken the non-lesion regions by ceaselessly aggregating the multi-scale local information onto feature maps.
no code implementations • 1 Nov 2018 • Xiangbo Shu, Jinhui Tang, Guo-Jun Qi, Wei Liu, Jian Yang
In a Co-LSTM unit, each sub-memory unit stores individual motion information, while this Co-LSTM unit selectively integrates and stores inter-related motion information between multiple interacting persons from multiple sub-memory units via the cell gate and co-memory cell, respectively.
Ranked #1 on Human Interaction Recognition on UT
no code implementations • 7 May 2018 • Lu Jin, Xiangbo Shu, Kai Li, Zechao Li, Guo-Jun Qi, Jinhui Tang
However, most existing deep hashing methods directly learn the hash functions by encoding the global semantic information, while ignoring the local spatial information of images.
no code implementations • 12 Apr 2018 • Jinhui Tang, Xiangbo Shu, Zechao Li, Yu-Gang Jiang, Qi Tian
Recent approaches simultaneously explore visual, user and tag information to improve the performance of image retagging by constructing and exploring an image-tag-user graph.
no code implementations • 1 Feb 2018 • Si Liu, Yao Sun, Defa Zhu, Renda Bao, Wei Wang, Xiangbo Shu, Shuicheng Yan
The age discriminative network guides the synthesized face to fit the real conditional distribution.
no code implementations • 4 Jun 2017 • Xiangbo Shu, Jinhui Tang, Zechao Li, Hanjiang Lai, Liyan Zhang, Shuicheng Yan
Basically, for each age group, we learn an aging dictionary to reveal its aging characteristics (e. g., wrinkles), where the dictionary bases corresponding to the same index yet from two neighboring aging dictionaries form a particular aging pattern cross these two age groups, and a linear combination of all these patterns expresses a particular personalized aging process.
no code implementations • 3 Jun 2017 • Xiangbo Shu, Jinhui Tang, Guo-Jun Qi, Yan Song, Zechao Li, Liyan Zhang
To this end, we propose a novel Concurrence-Aware Long Short-Term Sub-Memories (Co-LSTSM) to model the long-term inter-related dynamics between two interacting people on the bounding boxes covering people.
Ranked #2 on Human Interaction Recognition on BIT
no code implementations • CVPR 2016 • Wei Wang, Zhen Cui, Yan Yan, Jiashi Feng, Shuicheng Yan, Xiangbo Shu, Nicu Sebe
Modeling the aging process of human face is important for cross-age face verification and recognition.
no code implementations • 10 Mar 2016 • Hanjiang Lai, Pan Yan, Xiangbo Shu, Yunchao Wei, Shuicheng Yan
The instance-aware representations not only bring advantages to semantic hashing, but also can be used in category-aware hashing, in which an image is represented by multiple pieces of hash codes and each piece of code corresponds to a category.
no code implementations • ICCV 2015 • Guo-Sen Xie, Xu-Yao Zhang, Xiangbo Shu, Shuicheng Yan, Cheng-Lin Liu
Feature pooling is an important strategy to achieve high performance in image classification.
no code implementations • ICCV 2015 • Xiangbo Shu, Jinhui Tang, Hanjiang Lai, Luoqi Liu, Shuicheng Yan
Second, it is challenging or even impossible to collect faces of all age groups for a particular subject, yet much easier and more practical to get face pairs from neighboring age groups.