Search Results for author: Changjie Fan

Found 74 papers, 29 papers with code

Easy and Efficient Transformer: Scalable Inference Solution For Large NLP Model

no code implementations NAACL (ACL) 2022 Gongzheng li, Yadong Xi, Jingzhen Ding, Duan Wang, Ziyang Luo, Rongsheng Zhang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao

To fill such a gap, we introduce a scalable inference solution: Easy and Efficient Transformer (EET), including a series of transformer inference optimization at the algorithm and implementation levels.

Decoder Inference Optimization

A Dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment

1 code implementation10 Mar 2024 Fei Wang, Haoyu Liu, Haoyang Bi, Xiangzhuang Shen, Renyu Zhu, Runze Wu, Minmin Lin, Tangjie Lv, Changjie Fan, Qi Liu, Zhenya Huang, Enhong Chen

In this paper, we introduce a substantial crowdsourcing annotation dataset collected from a real-world crowdsourcing platform.

XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques

1 code implementation20 Feb 2024 Yu Xiong, Zhipeng Hu, Ye Huang, Runze Wu, Kai Guan, Xingchen Fang, Ji Jiang, Tianze Zhou, Yujing Hu, Haoyu Liu, Tangjie Lyu, Changjie Fan

To address this, we introduce XRL-Bench, a unified standardized benchmark tailored for the evaluation and comparison of XRL methods, encompassing three main modules: standard RL environments, explainers based on state importance, and standard evaluators.

Decision Making Reinforcement Learning (RL)

Towards Long-term Annotators: A Supervised Label Aggregation Baseline

no code implementations15 Nov 2023 Haoyu Liu, Fei Wang, Minmin Lin, Runze Wu, Renyu Zhu, Shiwei Zhao, Kai Wang, Tangjie Lv, Changjie Fan

These annotators could leave substantial historical annotation records on the crowdsourcing platforms, which can benefit label aggregation, but are ignored by previous works.

A New Baseline Assumption of Integated Gradients Based on Shaply value

no code implementations7 Oct 2023 Shuyang Liu, Zixuan Chen, Ge Shi, Ji Wang, Changjie Fan, Yu Xiong, Runze Wu Yujing Hu, Ze Ji, Yang Gao

The selection of appropriate baselines in IG is crucial for crafting meaningful and unbiased explanations of model predictions in diverse settings.

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model

no code implementations3 Oct 2023 Zibin Dong, Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Tangjie Lv, Changjie Fan, Zhipeng Hu

Aligning agent behaviors with diverse human preferences remains a challenging problem in reinforcement learning (RL), owing to the inherent abstractness and mutability of human preferences.

Attribute Reinforcement Learning (RL)

EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Prior

1 code implementation25 Aug 2023 Zhipeng Hu, Minda Zhao, Chaoyi Zhao, Xinyue Liang, Lincheng Li, Zeng Zhao, Changjie Fan, Xiaowei Zhou, Xin Yu

This limitation leads to the Janus problem, where multi-faced 3D models are generated under the guidance of such diffusion models.

Text to 3D

Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective

1 code implementation28 Jul 2023 Renyu Zhu, Haoyu Liu, Runze Wu, Minmin Lin, Tangjie Lv, Changjie Fan, Haobo Wang

In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambiguity noise.

Learning with noisy labels

Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning

no code implementations27 Jun 2023 Jinyi Liu, Yi Ma, Jianye Hao, Yujing Hu, Yan Zheng, Tangjie Lv, Changjie Fan

In summary, our research emphasizes the significance of trajectory-based data sampling techniques in enhancing the efficiency and performance of offline RL algorithms.

D4RL Offline RL +2

FlowFace++: Explicit Semantic Flow-supervised End-to-End Face Swapping

no code implementations22 Jun 2023 Yu Zhang, Hao Zeng, Bowen Ma, Wei zhang, Zhimeng Zhang, Yu Ding, Tangjie Lv, Changjie Fan

The discriminator is shape-aware and relies on a semantic flow-guided operation to explicitly calculate the shape discrepancies between the target and source faces, thus optimizing the face swapping network to generate highly realistic results.

Decoder Face Swapping

TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles

no code implementations1 Apr 2023 Yifeng Ma, Suzhen Wang, Yu Ding, Bowen Ma, Tangjie Lv, Changjie Fan, Zhipeng Hu, Zhidong Deng, Xin Yu

In this work, we propose an expression-controllable one-shot talking head method, dubbed TalkCLIP, where the expression in a speech is specified by the natural language.

2D Semantic Segmentation task 3 (25 classes) Talking Head Generation

DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video

1 code implementation7 Mar 2023 Zhimeng Zhang, Zhipeng Hu, Wenjin Deng, Changjie Fan, Tangjie Lv, Yu Ding

Different from previous works relying on multiple up-sample layers to directly generate pixels from latent embeddings, DINet performs spatial deformation on feature maps of reference images to better preserve high-frequency textural details.

Decoder Face Dubbing

Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglement

1 code implementation CVPR 2023 Xingqun Qi, Chen Liu, Muyi Sun, Lincheng Li, Changjie Fan, Xin Yu

Considering the asymmetric gestures and motions of two hands, we introduce a Spatial-Residual Memory (SRM) module to model spatial interaction between the body and each hand by residual learning.

Disentanglement

Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation

no code implementations CVPR 2023 Rui Zhao, Wei Li, Zhipeng Hu, Lincheng Li, Zhengxia Zou, Zhenwei Shi, Changjie Fan

In our method, taking the power of large-scale pre-trained multi-modal CLIP and neural rendering, T2P searches both continuous facial parameters and discrete facial parameters in a unified framework.

3D Generation Face Model +3

Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning

1 code implementation14 Feb 2023 Shanqi Liu, Yujing Hu, Runze Wu, Dong Xing, Yu Xiong, Changjie Fan, Kun Kuang, Yong liu

We first illustrate that the proposed value decomposition can consider the complicated interactions among agents and is feasible to learn in large-scale scenarios.

Multi-agent Reinforcement Learning

Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning

no code implementations7 Feb 2023 Rundong Wang, Longtao Zheng, Wei Qiu, Bowei He, Bo An, Zinovi Rabinovich, Yujing Hu, Yingfeng Chen, Tangjie Lv, Changjie Fan

Despite its success, ACL's applicability is limited by (1) the lack of a general student framework for dealing with the varying number of agents across tasks and the sparse reward problem, and (2) the non-stationarity of the teacher's task due to ever-changing student strategies.

Multi-agent Reinforcement Learning reinforcement-learning +1

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

1 code implementation3 Jan 2023 Yifeng Ma, Suzhen Wang, Zhipeng Hu, Changjie Fan, Tangjie Lv, Yu Ding, Zhidong Deng, Xin Yu

In a nutshell, we aim to attain a speaking style from an arbitrary reference speaking video and then drive the one-shot portrait to speak with the reference speaking style and another piece of audio.

Decoder Talking Face Generation +1

Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors

no code implementations CVPR 2023 Yongqiang Zhang, Zhipeng Hu, Haoqian Wu, Minda Zhao, Lincheng Li, Zhengxia Zou, Changjie Fan

In this paper, we argue that this limited accuracy is due to the bias of their volume rendering strategies, especially when the viewing direction is close to be tangent to the surface.

Surface Reconstruction

TCFimt: Temporal Counterfactual Forecasting from Individual Multiple Treatment Perspective

no code implementations17 Dec 2022 Pengfei Xi, Guifeng Wang, Zhipeng Hu, Yu Xiong, Mingming Gong, Wei Huang, Runze Wu, Yu Ding, Tangjie Lv, Changjie Fan, Xiangnan Feng

TCFimt constructs adversarial tasks in a seq2seq framework to alleviate selection and time-varying bias and designs a contrastive learning-based block to decouple a mixed treatment effect into separated main treatment effects and causal interactions which further improves estimation accuracy.

Contrastive Learning counterfactual +3

FlowFace: Semantic Flow-guided Shape-aware Face Swapping

no code implementations6 Dec 2022 Hao Zeng, Wei zhang, Changjie Fan, Tangjie Lv, Suzhen Wang, Zhimeng Zhang, Bowen Ma, Lincheng Li, Yu Ding, Xin Yu

Unlike most previous methods that focus on transferring the source inner facial features but neglect facial contours, our FlowFace can transfer both of them to a target face, thus leading to more realistic face swapping.

Face Swapping

Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation

no code implementations28 Oct 2022 Bowen Ma, Rudong An, Wei zhang, Yu Ding, Zeng Zhao, Rongsheng Zhang, Tangjie Lv, Changjie Fan, Zhipeng Hu

As a fine-grained and local expression behavior measurement, facial action unit (FAU) analysis (e. g., detection and intensity estimation) has been documented for its time-consuming, labor-intensive, and error-prone annotation.

Action Unit Detection Facial Action Unit Detection

EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model

no code implementations2 Oct 2022 Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Jinyi Liu, Yingfeng Chen, Changjie Fan

Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks.

reinforcement-learning Reinforcement Learning (RL) +2

Youling: an AI-Assisted Lyrics Creation System

no code implementations EMNLP 2020 Rongsheng Zhang, Xiaoxi Mao, Le Li, Lin Jiang, Lin Chen, Zhiwei Hu, Yadong Xi, Changjie Fan, Minlie Huang

In the lyrics generation process, \textit{Youling} supports traditional one pass full-text generation mode as well as an interactive generation mode, which allows users to select the satisfactory sentences from generated candidates conditioned on preceding context.

Text Generation

Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

1 code implementation NeurIPS 2021 Xiangyu Liu, Hangtian Jia, Ying Wen, Yaodong Yang, Yujing Hu, Yingfeng Chen, Changjie Fan, Zhipeng Hu

With this unified diversity measure, we design the corresponding diversity-promoting objective and population effectivity when seeking the best responses in open-ended learning.

RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System

1 code implementation18 Oct 2021 Kai Wang, Zhene Zou, Minghao Zhao, Qilin Deng, Yue Shang, Yile Liang, Runze Wu, Xudong Shen, Tangjie Lyu, Changjie Fan

In summary, the RL4RS (Reinforcement Learning for Recommender Systems), a new resource with special concerns on the reality gaps, contains two real-world datasets, data understanding tools, tuned simulation environments, related advanced RL baselines, batch RL baselines, and counterfactual policy evaluation algorithms.

Combinatorial Optimization counterfactual +3

Learning the Representation of Behavior Styles with Imitation Learning

no code implementations29 Sep 2021 Xiao Liu, Meng Wang, Zhaorong Wang, Yingfeng Chen, Yujing Hu, Changjie Fan, Chongjie Zhang

Imitation learning is one of the methods for reproducing expert demonstrations adaptively by learning a mapping between observations and actions.

Imitation Learning

Analyzing the Implicit Position Encoding Ability of Transformer Decoder

no code implementations29 Sep 2021 Ziyang Luo, Yadong Xi, Jing Ma, Xiaoxi Mao, Changjie Fan

A common limitation of Transformer Encoder's self-attention mechanism is that it cannot automatically capture the information of word order, so one needs to feed the explicit position encodings into the target model.

Decoder Language Modelling +1

LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation

2 code implementations30 Aug 2021 Jian Guan, Zhuoer Feng, Yamei Chen, Ruilin He, Xiaoxi Mao, Changjie Fan, Minlie Huang

Therefore, we propose a story-centric benchmark named LOT for evaluating Chinese long text modeling, which aggregates two understanding tasks and two generation tasks.

Decoder Text Infilling

Neural-to-Tree Policy Distillation with Policy Improvement Criterion

no code implementations16 Aug 2021 Zhao-Hua Li, Yang Yu, Yingfeng Chen, Ke Chen, Zhipeng Hu, Changjie Fan

The empirical results show that the proposed method can preserve a higher cumulative reward than behavior cloning and learn a more consistent policy to the original one.

Decision Making reinforcement-learning +1

KuiLeiXi: a Chinese Open-Ended Text Adventure Game

no code implementations ACL 2021 Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu

Equipped with GPT-2 and the latest GPT-3, AI Dungeon has been seen as a famous example of the powerful text generation capabilities of large-scale pre-trained language models, and a possibility for future games.

Story Generation

Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion

1 code implementation20 Jul 2021 Suzhen Wang, Lincheng Li, Yu Ding, Changjie Fan, Xin Yu

As this keypoint based representation models the motions of facial regions, head, and backgrounds integrally, our method can better constrain the spatial and temporal consistency of the generated videos.

Image Generation Talking Head Generation

GLIB: Towards Automated Test Oracle for Graphically-Rich Applications

1 code implementation19 Jun 2021 Ke Chen, Yufei Li, Yingfeng Chen, Changjie Fan, Zhipeng Hu, Wei Yang

We perform an evaluation of \texttt{GLIB} on 20 real-world game apps (with bug reports available) and the result shows that \texttt{GLIB} can achieve 100\% precision and 99. 5\% recall in detecting non-crashing bugs such as game GUI glitches.

Data Augmentation

Flow-Guided One-Shot Talking Face Generation With a High-Resolution Audio-Visual Dataset

1 code implementation CVPR 2021 Zhimeng Zhang, Lincheng Li, Yu Ding, Changjie Fan

To synthesize high-definition videos, we build a large in-the-wild high-resolution audio-visual dataset and propose a novel flow-guided talking face generation framework.

Talking Face Generation

Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

no code implementations9 Jun 2021 Xiangyu Liu, Hangtian Jia, Ying Wen, Yaodong Yang, Yujing Hu, Yingfeng Chen, Changjie Fan, Zhipeng Hu

With this unified diversity measure, we design the corresponding diversity-promoting objective and population effectivity when seeking the best responses in open-ended learning.

OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics

1 code implementation ACL 2021 Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang

Automatic metrics are essential for developing natural language generation (NLG) models, particularly for open-ended language generation tasks such as story generation.

Story Generation

Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence

1 code implementation ACL 2021 Jian Guan, Xiaoxi Mao, Changjie Fan, Zitao Liu, Wenbiao Ding, Minlie Huang

Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation.

Decoder Semantic Similarity +3

Easy and Efficient Transformer : Scalable Inference Solution For large NLP model

1 code implementation26 Apr 2021 Gongzheng li, Yadong Xi, Jingzhen Ding, Duan Wang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao

To fill such a gap, we introduce a scalable inference solution: Easy and Efficient Transformer (EET), including a series of transformer inference optimization at the algorithm and implementation levels.

Decoder Inference Optimization +1

Personalized Bundle Recommendation in Online Games

no code implementations12 Apr 2021 Qilin Deng, Kai Wang, Minghao Zhao, Zhene Zou, Runze Wu, Jianrong Tao, Changjie Fan, Liang Chen

In business domains, \textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers.

Link Prediction Marketing +1

Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation

no code implementations7 Apr 2021 Kai Wang, Zhene Zou, Qilin Deng, Runze Wu, Jianrong Tao, Changjie Fan, Liang Chen, Peng Cui

As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal.

Model-based Reinforcement Learning Recommendation Systems +2

GraphFederator: Federated Visual Analysis for Multi-party Graphs

no code implementations27 Aug 2020 Dongming Han, Wei Chen, Rusheng Pan, Yijing Liu, Jiehui Zhou, Ying Xu, Tianye Zhang, Changjie Fan, Jianrong Tao, Xiaolong, Zhang

This paper presents GraphFederator, a novel approach to construct joint representations of multi-party graphs and supports privacy-preserving visual analysis of graphs.

Human-Computer Interaction Cryptography and Security Graphics

Neutral Face Game Character Auto-Creation via PokerFace-GAN

1 code implementation17 Aug 2020 Tianyang Shi, Zhengxia Zou, Xinhui Song, Zheng Song, Changjian Gu, Changjie Fan, Yi Yuan

Besides, the neural network based renderer used in previous methods is also difficult to be extended to multi-view rendering cases.

Self-Supervised Learning

Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation

no code implementations17 Aug 2020 Tianyang Shi, Zhengxia Zou, Yi Yuan, Changjie Fan

With the rapid development of Role-Playing Games (RPGs), players are now allowed to edit the facial appearance of their in-game characters with their preferences rather than using default templates.

3D Face Reconstruction Face Verification +3

Unsupervised Facial Action Unit Intensity Estimation via Differentiable Optimization

no code implementations13 Apr 2020 Xinhui Song, Tianyang Shi, Tianjia Shao, Yi Yuan, Zunlei Feng, Changjie Fan

The generator learns to "render" a face image from a set of facial parameters in a differentiable way, and the feature extractor extracts deep features for measuring the similarity of the rendered image and input real image.

Exploring Unknown States with Action Balance

2 code implementations10 Mar 2020 Yan Song, Yingfeng Chen, Yujing Hu, Changjie Fan

In this paper, we focus on improving the effectiveness of finding unknown states and propose action balance exploration, which balances the frequency of selecting each action at a given state and can be treated as an extension of upper confidence bound (UCB) to deep reinforcement learning.

Montezuma's Revenge reinforcement-learning +1

Efficient Deep Reinforcement Learning via Adaptive Policy Transfer

1 code implementation19 Feb 2020 Tianpei Yang, Jianye Hao, Zhaopeng Meng, Zongzhang Zhang, Yujing Hu, Yingfeng Cheng, Changjie Fan, Weixun Wang, Wulong Liu, Zhaodong Wang, Jiajie Peng

Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks.

reinforcement-learning Reinforcement Learning (RL) +1

From Few to More: Large-scale Dynamic Multiagent Curriculum Learning

no code implementations6 Sep 2019 Weixun Wang, Tianpei Yang, Yong liu, Jianye Hao, Xiaotian Hao, Yujing Hu, Yingfeng Chen, Changjie Fan, Yang Gao

In this paper, we design a novel Dynamic Multiagent Curriculum Learning (DyMA-CL) to solve large-scale problems by starting from learning on a multiagent scenario with a small size and progressively increasing the number of agents.

Face-to-Parameter Translation for Game Character Auto-Creation

no code implementations ICCV 2019 Tianyang Shi, Yi Yuan, Changjie Fan, Zhengxia Zou, Zhenwei Shi, Yong liu

Character customization system is an important component in Role-Playing Games (RPGs), where players are allowed to edit the facial appearance of their in-game characters with their own preferences rather than using default templates.

Style Transfer Translation

FReeNet: Multi-Identity Face Reenactment

1 code implementation CVPR 2020 Jiangning Zhang, Xianfang Zeng, Mengmeng Wang, Yusu Pan, Liang Liu, Yong liu, Yu Ding, Changjie Fan

This paper presents a novel multi-identity face reenactment framework, named FReeNet, to transfer facial expressions from an arbitrary source face to a target face with a shared model.

Decoder Face Reenactment

Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces

1 code implementation12 Mar 2019 Haotian Fu, Hongyao Tang, Jianye Hao, Zihan Lei, Yingfeng Chen, Changjie Fan

Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces.

Multi-agent Reinforcement Learning Q-Learning +2

A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents

no code implementations NeurIPS 2018 Yan Zheng, Zhaopeng Meng, Jianye Hao, Zongzhang Zhang, Tianpei Yang, Changjie Fan

In multiagent domains, coping with non-stationary agents that change behaviors from time to time is a challenging problem, where an agent is usually required to be able to quickly detect the other agent's policy during online interaction, and then adapt its own policy accordingly.

Hierarchical Deep Multiagent Reinforcement Learning with Temporal Abstraction

no code implementations25 Sep 2018 Hongyao Tang, Jianye Hao, Tangjie Lv, Yingfeng Chen, Zongzhang Zhang, Hangtian Jia, Chunxu Ren, Yan Zheng, Zhaopeng Meng, Changjie Fan, Li Wang

Besides, we propose a new experience replay mechanism to alleviate the issue of the sparse transitions at the high level of abstraction and the non-stationarity of multiagent learning.

reinforcement-learning Reinforcement Learning (RL)

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