no code implementations • 10 Oct 2024 • Zhipeng Chen, Liang Song, Kun Zhou, Wayne Xin Zhao, Bingning Wang, WeiPeng Chen, Ji-Rong Wen
In the extraction stage, we firstly locate key neurons that are highly related to specific abilities, and then employ them to extract the transferable ability-specific weights.
no code implementations • 20 Sep 2024 • Liangyu Teng, Yang Liu, Jing Liu, Liang Song
Specifically, the large cloud model acts as a teacher, guiding and promoting the learning of the end model, which significantly reduces the end model's reliance on large-scale, high-quality data and thereby addresses the data bottleneck in traditional end model training, offering a new paradigm for the rapid deployment of industry applications.
no code implementations • 25 Jul 2024 • Hanqi Wang, Kun Yang, Jingyu Zhang, Tao Chen, Liang Song
The recent rise of EEG-based end-to-end deep learning models presents a significant challenge in elucidating how these models process raw EEG signals and generate predictions in the frequency domain.
no code implementations • 17 Jun 2024 • Yuyan Zhou, Liang Song, Bingning Wang, WeiPeng Chen
The advent of large language models (LLMs) like GPT-4 has catalyzed the exploration of multi-task learning (MTL), in which a single model demonstrates proficiency across diverse tasks.
1 code implementation • 16 May 2024 • Jing Liu, Yang Liu, Jieyu Lin, Jielin Li, Peng Sun, Bo Hu, Liang Song, Azzedine Boukerche, Victor C. M. Leung
With the advancements in deep learning and edge computing, VAD has made significant progress and advances synergized with emerging applications in smart cities and video internet, which has moved beyond the conventional research scope of algorithm engineering to deployable Networking Systems for VAD (NSVAD), a practical hotspot for intersection exploration in the AI, IoVT, and computing fields.
no code implementations • 6 Mar 2024 • Hanqi Wang, Tao Chen, Liang Song
Inspired by recent efforts in combining low-level and high-level tasks in deep learning, we propose a cascaded self-supervised architecture for EEG emotion recognition.
1 code implementation • CVPR 2024 • Jingyu Zhang, Kun Yang, Yilei Wang, Hanqi Wang, Peng Sun, Liang Song
Collaborative perception enhances perception performance by enabling autonomous vehicles to exchange complementary information.
2 code implementations • 19 Sep 2023 • Aiyuan Yang, Bin Xiao, Bingning Wang, Borong Zhang, Ce Bian, Chao Yin, Chenxu Lv, Da Pan, Dian Wang, Dong Yan, Fan Yang, Fei Deng, Feng Wang, Feng Liu, Guangwei Ai, Guosheng Dong, Haizhou Zhao, Hang Xu, Haoze Sun, Hongda Zhang, Hui Liu, Jiaming Ji, Jian Xie, Juntao Dai, Kun Fang, Lei Su, Liang Song, Lifeng Liu, Liyun Ru, Luyao Ma, Mang Wang, Mickel Liu, MingAn Lin, Nuolan Nie, Peidong Guo, Ruiyang Sun, Tao Zhang, Tianpeng Li, Tianyu Li, Wei Cheng, WeiPeng Chen, Xiangrong Zeng, Xiaochuan Wang, Xiaoxi Chen, Xin Men, Xin Yu, Xuehai Pan, Yanjun Shen, Yiding Wang, Yiyu Li, Youxin Jiang, Yuchen Gao, Yupeng Zhang, Zenan Zhou, Zhiying Wu
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
no code implementations • 10 Sep 2023 • Liang Song, Guangming Wang, Jiuming Liu, Zhenyang Fu, Yanzi Miao, Hesheng
By combining these modules, our approach successfully tackles the challenges of outdoor scene generalization, producing high-quality rendering results.
1 code implementation • ICCV 2023 • Kun Yang, Dingkang Yang, Jingyu Zhang, Mingcheng Li, Yang Liu, Jing Liu, Hanqi Wang, Peng Sun, Liang Song
In this paper, we propose SCOPE, a novel collaborative perception framework that aggregates the spatio-temporal awareness characteristics across on-road agents in an end-to-end manner.
no code implementations • 17 Jun 2023 • Zhiyuan Ning, Zhangxun Li, Zhengliang Guo, Zile Wang, Liang Song
To address these deficiencies, we propose a Multi-scale Spatial-Temporal Interaction Network (MSTI-Net) for VAD.
no code implementations • 23 Feb 2023 • Kun Yang, Jing Liu, Dingkang Yang, Hanqi Wang, Peng Sun, Yanni Zhang, Yan Liu, Liang Song
With the rapid development of intelligent transportation system applications, a tremendous amount of multi-view video data has emerged to enhance vehicle perception.
1 code implementation • 10 Feb 2023 • Yang Liu, Dingkang Yang, Yan Wang, Jing Liu, Jun Liu, Azzedine Boukerche, Peng Sun, Liang Song
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos.
no code implementations • 27 Jul 2022 • Yang Liu, Jing Liu, Mengyang Zhao, Dingkang Yang, Xiaoguang Zhu, Liang Song
Video anomaly detection is a challenging task in the computer vision community.
no code implementations • 30 May 2022 • Hanqi Wang, Xiaoguang Zhu, Tao Chen, Chengfang Li, Liang Song
The results of the experiments support the advantages of our method.
no code implementations • 11 Mar 2022 • Jianzhang Zheng, Fan Yang, Hao Shen, Xuan Tang, Mingsong Chen, Liang Song, Xian Wei
We propose an algorithmic framework that leverages the advantages of the DNNs for data self-expression and task-specific predictions, to improve image classification.
no code implementations • 1 Jan 2021 • Liang Song, Jinlu Liu, Yongqiang Qin
We first introduce and derive a theoretical upper bound of error rate which is constrained to 1) linear separability in the learned embedding space and 2) discrepancy of task-specific and task-independent classifier.
no code implementations • 23 Nov 2020 • Jinlu Liu, Liang Song, Yongqiang Qin
On each task, the inner loop aims to learn optimized prototypes from the query images.
no code implementations • 25 Nov 2019 • Liang Song, Jinlu Liu, Yongqiang Qin
Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model.
1 code implementation • ECCV 2020 • Jinlu Liu, Liang Song, Yongqiang Qin
Few-shot learning requires to recognize novel classes with scarce labeled data.