Pan Ji

Pan Ji

Auto-generated profile, based on publicly available information

Pan Ji

Tencent, Shanghai, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 September 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Open access
Zhenyue QinZhenyue Qin
Zhenyue Qin
YLYang Liu
Yang Liu
PJPan Ji
Pan Ji
DKDongwoo Kim
Dongwoo Kim
Lei WangLei Wang
Lei Wang
Tom GedeonTom Gedeon
Tom Gedeon
Skeleton sequences are lightweight and compact and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract features from 3-D joint coordinates as spatial–temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance. The use of first-and second-order features, that is, joint and bone representations, has led to high accuracy. Nonetheless, many models are still confused by actions that have similar motion trajectories. To address these issues, we propose fusing higher-order features in the form of angular encoding (AGE) into modern architectures to robustly capture the relationships between joints and body parts. This simple fusion with popular spatial–temporal graph neural networks achieves new state-of-the-art accuracy in two large benchmarks, including NTU60 and NTU120, while employing fewer parameters and reduced run time. Our source code is publicly available at: https://github.com/ZhenyueQin/Angular-Skeleton-Encoding.

19 July 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
ZWZhennan Wu
Zhennan Wu
YLYang Li
Yang Li
HYHan Yan
Han Yan
TSTaizhang Shang
Taizhang Shang
WSWeixuan Sun
Weixuan Sun
PJPan Ji
Pan Ji
We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using datasets of 3D blocks that are randomly cropped from complete 3D scene meshes. Through per-block fitting, all training blocks are converted into the hybrid neural fields: with a tri-plane containing the geometry features, followed by a Multi-layer Perceptron (MLP) for decoding the signed distance values. A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed. Diffusion applied to the latent representations allows for high-quality and diverse 3D scene generation.To expand a scene during generation, one needs only to append empty blocks to overlap with the current scene and extrapolate existing latent tri-planes to populate new blocks. The extrapolation is done by conditioning the generation process with the feature samples from the overlapping tri-planes during the denoising iterations. Latent tri-plane extrapolation produces semantically and geometrically meaningful transitions that harmoniously blend with the existing scene. A 2D layout conditioning mechanism is used to control the placement and arrangement of scene elements. Experimental results indicate that BlockFusion is capable of generating diverse, geometrically consistent and unbounded large 3D scenes with unprecedented high-quality shapes in both indoor and outdoor scenarios.

13 November 2020
Verified
Book Chapter
Closed access
PDF file
YZYuliang Zou
Yuliang Zou
PJPan Ji
Pan Ji
QTQuoc-Huy Tran
Quoc-Huy Tran
JHJia-Bin Huang
Jia-Bin Huang
MCManmohan Chandraker
Manmohan Chandraker

27 November 2020
Verified
Book Chapter
Closed access
PDF file
LTLokender Tiwari
Lokender Tiwari
PJPan Ji
Pan Ji
QTQuoc-Huy Tran
Quoc-Huy Tran
BZBingbing Zhuang
Bingbing Zhuang
SASaket Anand
Saket Anand
MCManmohan Chandraker
Manmohan Chandraker

15 April 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
PFPengfei Fang
Pengfei Fang
JZJieming Zhou
Jieming Zhou
SRSoumava Kumar Roy
Soumava Kumar Roy
PJPan Ji
Pan Ji
LPLars Petersson
Lars Petersson
Mehrtash HarandiMehrtash Harandi
Mehrtash Harandi
This paper generalizes the Attention in Attention (AiA) mechanism, proposed in [1], by employing explicit mapping in reproducing kernel Hilbert spaces to generate attention values of the input feature map. The AiA mechanism models the capacity of building inter-dependencies among the local and global features by the interaction of inner and outer attention modules. Besides a vanilla AiA module, termed linear attention with AiA, two non-linear counterparts, namely, second-order polynomial attention and Gaussian attention, are also proposed to utilize the non-linear properties of the input features explicitly, via the second-order polynomial kernel and Gaussian kernel approximation. The deep convolutional neural network, equipped with the proposed AiA blocks, is referred to as Attention in Attention Network (AiA-Net). The AiA-Net learns to extract a discriminative pedestrian representation, which combines complementary person appearance and corresponding part features. Extensive ablation studies verify the effectiveness of the AiA mechanism and the use of non-linear features hidden in the feature map for attention design. Furthermore, our approach outperforms current state-of-the-art by a considerable margin across a number of benchmarks. In addition, state-of-the-art performance is also achieved in the video person retrieval task with the assistance of the proposed AiA blocks.

14 December 2022 in Sensors
Verified
Journal Article
Open access
PDF file
YLYang Liu
Yang Liu
SASaeed Anwar
Saeed Anwar
Zhenyue QinZhenyue Qin
Zhenyue Qin
PJPan Ji
Pan Ji
SCSabrina Caldwell
Sabrina Caldwell
Tom GedeonTom Gedeon
Tom Gedeon
The prevalent convolutional neural network (CNN)-based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy. However, these methods may ignore the underlying distribution of clean images, inducing distortions or artifacts in denoising results. This paper proposes a new perspective to treat image denoising as a distribution learning and disentangling task. Since the noisy image distribution can be viewed as a joint distribution of clean images and noise, the denoised images can be obtained via manipulating the latent representations to the clean counterpart. This paper also provides a distribution-learning-based denoising framework. Following this framework, we present an invertible denoising network, FDN, without any assumptions on either clean or noise distributions, as well as a distribution disentanglement method. FDN learns the distribution of noisy images, which is different from the previous CNN-based discriminative mapping. Experimental results demonstrate FDN’s capacity to remove synthetic additive white Gaussian noise (AWGN) on both category-specific and remote sensing images. Furthermore, the performance of FDN surpasses that of previously published methods in real image denoising with fewer parameters and faster speed.