Search Results for author: Guoqiang Wei

Found 12 papers, 7 papers with code

Boximator: Generating Rich and Controllable Motions for Video Synthesis

no code implementations2 Feb 2024 Jiawei Wang, Yuchen Zhang, Jiaxin Zou, Yan Zeng, Guoqiang Wei, Liping Yuan, Hang Li

Its robust motion controllability is validated by drastic increases in the bounding box alignment metric.

High-Fidelity Diffusion-based Image Editing

no code implementations25 Dec 2023 Chen Hou, Guoqiang Wei, Zhibo Chen

Diffusion models have attained remarkable success in the domains of image generation and editing.

Denoising Image Reconstruction +1

Make Pixels Dance: High-Dynamic Video Generation

no code implementations18 Nov 2023 Yan Zeng, Guoqiang Wei, Jiani Zheng, Jiaxin Zou, Yang Wei, Yuchen Zhang, Hang Li

Creating high-dynamic videos such as motion-rich actions and sophisticated visual effects poses a significant challenge in the field of artificial intelligence.

Text-to-Video Generation Video Generation

What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?

2 code implementations5 Jul 2023 Yan Zeng, Hanbo Zhang, Jiani Zheng, Jiangnan Xia, Guoqiang Wei, Yang Wei, Yuchen Zhang, Tao Kong

However, the performance of these models heavily relies on design choices such as network structures, training data, and training strategies, and these choices have not been extensively discussed in the literature, making it difficult to quantify progress in this field.

Instruction Following Language Modelling

Mask-Based Modeling for Neural Radiance Fields

1 code implementation11 Apr 2023 Ganlin Yang, Guoqiang Wei, Zhizheng Zhang, Yan Lu, Dong Liu

Most Neural Radiance Fields (NeRFs) exhibit limited generalization capabilities, which restrict their applicability in representing multiple scenes using a single model.

Representation Learning

Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation

1 code implementation6 Dec 2022 Xin Li, Cuiling Lan, Guoqiang Wei, Zhibo Chen

In this way, our message broadcasting encourages the group tokens to learn more informative and diverse information for effective domain alignment.

Pseudo Label Unsupervised Domain Adaptation

Active Token Mixer

2 code implementations11 Mar 2022 Guoqiang Wei, Zhizheng Zhang, Cuiling Lan, Yan Lu, Zhibo Chen

In this work, we propose an innovative token-mixer, dubbed Active Token Mixer (ATM), to actively incorporate flexible contextual information distributed across different channels from other tokens into the given query token.

Image Classification Instance Segmentation +2

Confounder Identification-free Causal Visual Feature Learning

no code implementations26 Nov 2021 Xin Li, Zhizheng Zhang, Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Xin Jin, Zhibo Chen

In this paper, we propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders.

Domain Generalization Meta-Learning

ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation

1 code implementation NeurIPS 2021 Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhizheng Zhang, Zhibo Chen

Unsupervised domain adaptive classifcation intends to improve the classifcation performance on unlabeled target domain.

Unsupervised Domain Adaptation

MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation

1 code implementation CVPR 2021 Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhibo Chen

For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statistics.

Classification General Classification +5

Semantics-Aligned Representation Learning for Person Re-identification

1 code implementation30 May 2019 Xin Jin, Cuiling Lan, Wen-Jun Zeng, Guoqiang Wei, Zhibo Chen

Specifically, we build a Semantics Aligning Network (SAN) which consists of a base network as encoder (SA-Enc) for re-ID, and a decoder (SA-Dec) for reconstructing/regressing the densely semantics aligned full texture image.

Person Re-Identification Representation Learning +1

View Invariant 3D Human Pose Estimation

no code implementations30 Jan 2019 Guoqiang Wei, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen

The diversity of capturing viewpoints and the flexibility of the human poses, however, remain some significant challenges.

3D Human Pose Estimation 3D Pose Estimation

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