Jun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jun Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jun Wan
Institute of Automation, Chinese Academy of Sciences, Beijing, China, China
3 shared publications - Zhen Lei
Chinese Academy of Sciences
3 shared publications - Zichang Tan
Institute of Deep Learning, Baidu Research, Beijing, China
2 shared publications Baihui Li
State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China
1 shared publication- Hao Fang
State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China
1 shared publication - Hao Tan
State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation Chinese Academy of Sciences (CASIA), Beijing, China
1 shared publication
Latest Publications
- Open Access
- 20 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (9) , 17239-17252
UBG: An Unreal BattleGround Benchmark With Object-Aware Hierarchical Proximal Policy Optimization
The deep reinforcement learning (DRL) has made significant progress in various simulation environments. However, applying DRL methods to real-world scenarios poses certain challenges due to limitations in visual fidelity, scene complexity, and task diversity within existing environments. To address limitations and explore the potential ability of DRL, we developed a 3-D open-world first-person shooter (FPS) game called Unreal BattleGround (UBG) using the unreal engine (UE). UBG provides a realistic 3-D environment with variable complexity, random scenes, diverse tasks, and multiple scene interaction methods. This benchmark involves far more complex state-action spaces than classic pseudo-3-D FPS games (e.g., ViZDoom), making it challenging for DRL to learn human-level decision sequences. Then, we propose the object-aware hierarchically proximal policy optimization (OaH-PPO) method in the UBG. It involves a two-level hierarchy, where the high-level controller is tasked with learning option control, and the low-level workers focus on mastering subtasks. To boost the learning of subtasks, we propose three modules: an object-aware module for extracting depth detection information from the environment, potential-based intrinsic reward shaping for efficient exploration, and annealing imitation learning (IL) to guide the initialization. Experimental results have demonstrated the broad applicability of the UBG and the effectiveness of the OaH-PPO. We will release the code of the UBG and OaH-PPO after publication.
- 20 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (9) , 17239-17252
Open AccessUBG: An Unreal BattleGround Benchmark With Object-Aware Hierarchical Proximal Policy Optimization
The deep reinforcement learning (DRL) has made significant progress in various simulation environments. However, applying DRL methods to real-world scenarios poses certain challenges due to limitations in visual fidelity, scene complexity, and task diversity within existing environments. To address limitations and explore the potential ability of DRL, we developed a 3-D open-world first-person shooter (FPS) game called Unreal BattleGround (UBG) using the unreal engine (UE). UBG provides a realistic 3-D environment with variable complexity, random scenes, diverse tasks, and multiple scene interaction methods. This benchmark involves far more complex state-action spaces than classic pseudo-3-D FPS games (e.g., ViZDoom), making it challenging for DRL to learn human-level decision sequences. Then, we propose the object-aware hierarchically proximal policy optimization (OaH-PPO) method in the UBG. It involves a two-level hierarchy, where the high-level controller is tasked with learning option control, and the low-level workers focus on mastering subtasks. To boost the learning of subtasks, we propose three modules: an object-aware module for extracting depth detection information from the environment, potential-based intrinsic reward shaping for efficient exploration, and annealing imitation learning (IL) to guide the initialization. Experimental results have demonstrated the broad applicability of the UBG and the effectiveness of the OaH-PPO. We will release the code of the UBG and OaH-PPO after publication.
- 8 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 6155-6167
General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds With One Stone
Facial age estimation has received a lot of attention for its diverse application scenarios. Most existing studies treat each sample equally and aim to reduce the average estimation error for the entire dataset, which can be summarized as General Age Estimation . However, due to the long-tailed distribution prevalent in the dataset, treating all samples equally will inevitably bias the model toward the head classes (usually the adult with a majority of samples). Driven by this, some works suggest that each class should be treated equally to improve performance in tail classes (with a minority of samples), which can be summarized as Long-tailed Age Estimation . However, Long-tailed Age Estimation usually faces a performance trade-off, i.e ., achieving improvement in tail classes by sacrificing the head classes. In this paper, our goal is to design a unified framework to perform well on both tasks, killing two birds with one stone. To this end, we propose a simple, effective, and flexible training paradigm named GLAE, which is two-fold. First, we propose Feature Rearrangement (FR) and Pixel-level Auxiliary learning (PA) for better feature utilization to improve the overall age estimation performance. Second, we propose Adaptive Routing (AR) for selecting the appropriate classifier to improve performance in the tail classes while maintaining the head classes. Moreover, we introduce a new metric, named Class-wise Mean Absolute Error (CMAE), to equally evaluate the performance of all classes. Our GLAE provides a surprising improvement on Morph II, reaching the lowest MAE and CMAE of 1.14 and 1.27 years, respectively. Compared to the previous best method, MAE dropped by up to 34%, which is an unprecedented improvement, and for the first time, MAE is close to 1 year old. Extensive experiments on other age benchmark datasets, including CACD, MIVIA, and Chalearn LAP 2015, also indicate that GLAE outperforms the state-of-the-art approaches significantly.
- 8 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 6155-6167
General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds With One Stone
Facial age estimation has received a lot of attention for its diverse application scenarios. Most existing studies treat each sample equally and aim to reduce the average estimation error for the entire dataset, which can be summarized as General Age Estimation . However, due to the long-tailed distribution prevalent in the dataset, treating all samples equally will inevitably bias the model toward the head classes (usually the adult with a majority of samples). Driven by this, some works suggest that each class should be treated equally to improve performance in tail classes (with a minority of samples), which can be summarized as Long-tailed Age Estimation . However, Long-tailed Age Estimation usually faces a performance trade-off, i.e ., achieving improvement in tail classes by sacrificing the head classes. In this paper, our goal is to design a unified framework to perform well on both tasks, killing two birds with one stone. To this end, we propose a simple, effective, and flexible training paradigm named GLAE, which is two-fold. First, we propose Feature Rearrangement (FR) and Pixel-level Auxiliary learning (PA) for better feature utilization to improve the overall age estimation performance. Second, we propose Adaptive Routing (AR) for selecting the appropriate classifier to improve performance in the tail classes while maintaining the head classes. Moreover, we introduce a new metric, named Class-wise Mean Absolute Error (CMAE), to equally evaluate the performance of all classes. Our GLAE provides a surprising improvement on Morph II, reaching the lowest MAE and CMAE of 1.14 and 1.27 years, respectively. Compared to the previous best method, MAE dropped by up to 34%, which is an unprecedented improvement, and for the first time, MAE is close to 1 year old. Extensive experiments on other age benchmark datasets, including CACD, MIVIA, and Chalearn LAP 2015, also indicate that GLAE outperforms the state-of-the-art approaches significantly.
- 7 November 2015
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 16 (11) , 930-939
Multiclass classification based on a deep convolutional network for head pose estimation
Head pose estimation has been considered an important and challenging task in computer vision. In this paper we propose a novel method to estimate head pos
- 7 November 2015
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 16 (11) , 930-939
Multiclass classification based on a deep convolutional network for head pose estimation
Head pose estimation has been considered an important and challenging task in computer vision. In this paper we propose a novel method to estimate head pos