Search Results for author: Congqi Cao

Found 10 papers, 1 papers with code

Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition

1 code implementation ECCV 2020 Ke Cheng, Yifan Zhang, Congqi Cao, Lei Shi, Jian Cheng, Hanqing Lu

Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment.

Action Recognition Skeleton Based Action Recognition

Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection

no code implementations7 Sep 2022 Congqi Cao, Yue Lu, Yanning Zhang

For the context recovery stream, we propose a spatiotemporal U-Net which can fully utilize the motion information to predict the future frame.

Anomaly Detection

Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos

no code implementations14 Feb 2022 Congqi Cao, Xin Zhang, Shizhou Zhang, Peng Wang, Yanning Zhang

For weakly supervised anomaly detection, most existing work is limited to the problem of inadequate video representation due to the inability of modeling long-term contextual information.

Anomaly Detection Graph Learning

Learnable Locality-Sensitive Hashing for Video Anomaly Detection

no code implementations15 Nov 2021 Yue Lu, Congqi Cao, Yanning Zhang

In this paper, we propose a novel distance-based VAD method to take advantage of all the available normal data efficiently and flexibly.

Abnormal Event Detection In Video

Time-Domain Doppler Biomotion Detections Immune to Unavoidable DC Offsets

no code implementations29 Jun 2021 Qinyi Lv, Lingtong Min, Congqi Cao, Shigang Zhou, Deyun Zhou, Chengkai Zhu, Yun Li, Zhongbo Zhu, Xiaojun Li, Lixin Ran

In the past decades, continuous Doppler radar sensor-based bio-signal detections have attracted many research interests.

Efficient Spatialtemporal Context Modeling for Action Recognition

no code implementations20 Mar 2021 Congqi Cao, Yue Lu, Yifan Zhang, Dongmei Jiang, Yanning Zhang

Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition.

Action Recognition

Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization

no code implementations13 Oct 2020 Congqi Cao, Yajuan Li, Qinyi Lv, Peng Wang, Yanning Zhang

Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application.

Few Shot Action Recognition Few-Shot Learning +2

Learning to Compare Relation: Semantic Alignment for Few-Shot Learning

no code implementations29 Feb 2020 Congqi Cao, Yanning Zhang

First, we introduce a semantic alignment loss to align the relation statistics of the features from samples that belong to the same category.

Few-Shot Learning Metric Learning

Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition

no code implementations24 Apr 2017 Congqi Cao, Yifan Zhang, Chunjie Zhang, Hanqing Lu

To make it end-to-end and do not rely on any sophisticated body joint detection algorithm, we further propose a two-stream bilinear model which can learn the guidance from the body joints and capture the spatio-temporal features simultaneously.

Action Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.