Search Results for author: Yizhou Zhou

Found 12 papers, 3 papers with code

Inter-X: Towards Versatile Human-Human Interaction Analysis

no code implementations26 Dec 2023 Liang Xu, Xintao Lv, Yichao Yan, Xin Jin, Shuwen Wu, Congsheng Xu, Yifan Liu, Yizhou Zhou, Fengyun Rao, Xingdong Sheng, Yunhui Liu, Wenjun Zeng, Xiaokang Yang

We also equip Inter-X with versatile annotations of more than 34K fine-grained human part-level textual descriptions, semantic interaction categories, interaction order, and the relationship and personality of the subjects.

Image Captioning with Multi-Context Synthetic Data

no code implementations29 May 2023 Feipeng Ma, Yizhou Zhou, Fengyun Rao, Yueyi Zhang, Xiaoyan Sun

This potential can be harnessed to create synthetic image-text pairs for training captioning models.

Image Captioning Language Modelling +2

Distribution Consistent Neural Architecture Search

no code implementations CVPR 2022 Junyi Pan, Chong Sun, Yizhou Zhou, Ying Zhang, Chen Li

We first theoretically investigate how the weight coupling problem affects the network searching performance from a parameter distribution perspective, and then propose a novel supernet training strategy with a Distribution Consistent Constraint that can provide a good measurement for the extent to which two architectures can share weights.

Neural Architecture Search

Unsupervised Visual Representation Learning by Tracking Patches in Video

1 code implementation CVPR 2021 Guangting Wang, Yizhou Zhou, Chong Luo, Wenxuan Xie, Wenjun Zeng, Zhiwei Xiong

The proxy task is to estimate the position and size of the image patch in a sequence of video frames, given only the target bounding box in the first frame.

Action Classification Action Recognition +1

VAE^2: Preventing Posterior Collapse of Variational Video Predictions in the Wild

no code implementations28 Jan 2021 Yizhou Zhou, Chong Luo, Xiaoyan Sun, Zheng-Jun Zha, Wenjun Zeng

We believe that VAE$^2$ is also applicable to other stochastic sequence prediction problems where training data are lack of stochasticity.

Video Prediction

Data-driven discovery of multiscale chemical reactions governed by the law of mass action

1 code implementation17 Jan 2021 Juntao Huang, Yizhou Zhou, Wen-An Yong

First, we use a single matrix to represent the stoichiometric coefficients for both the reactants and products in a system without catalysis reactions.

Learning Thermodynamically Stable and Galilean Invariant Partial Differential Equations for Non-equilibrium Flows

no code implementations28 Sep 2020 Juntao Huang, Zhiting Ma, Yizhou Zhou, Wen-An Yong

In this work, we develop a method for learning interpretable, thermodynamically stable and Galilean invariant partial differential equations (PDEs) based on the Conservation-dissipation Formalism of irreversible thermodynamics.

Spatiotemporal Fusion in 3D CNNs: A Probabilistic View

no code implementations CVPR 2020 Yizhou Zhou, Xiaoyan Sun, Chong Luo, Zheng-Jun Zha, Wen-Jun Zeng

Based on the probability space, we further generate new fusion strategies which achieve the state-of-the-art performance on four well-known action recognition datasets.

Action Recognition In Videos Temporal Action Localization

Posterior-Guided Neural Architecture Search

1 code implementation23 Jun 2019 Yizhou Zhou, Xiaoyan Sun, Chong Luo, Zheng-Jun Zha, Wen-Jun Zeng

Accordingly, a hybrid network representation is presented which enables us to leverage the Variational Dropout so that the approximation of the posterior distribution becomes fully gradient-based and highly efficient.

Image Classification Neural Architecture Search

Context-Reinforced Semantic Segmentation

no code implementations CVPR 2019 Yizhou Zhou, Xiaoyan Sun, Zheng-Jun Zha, Wenjun Zeng

Recent efforts have shown the importance of context on deep convolutional neural network based semantic segmentation.

Segmentation Semantic Segmentation

MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition

no code implementations CVPR 2018 Yizhou Zhou, Xiaoyan Sun, Zheng-Jun Zha, Wen-Jun Zeng

Recent attempts use 3D convolutional neural networks (CNNs) to explore spatio-temporal information for human action recognition.

Action Recognition Temporal Action Localization

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