Publications

2024

1. 

   Self-Supervised Vision Transformer for Enhanced Virtual Clothes Try-On

   Lingxiao Lu, Shengyi Wu, Haoxuan Sun, Junhong Gou, Jianlou Si, Chen Qian, Jianfu Zhang, and Liqing Zhang

   2024

   arXiv

2. 

   I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models

   Wenqi Ouyang, Yi Dong, Lei Yang, Jianlou Si, and Xingang Pan

   2024

   arXiv Website

2023

1. 

   Object Part Parsing with Hierarchical Dual Transformer

   Jiamin Chen, Jianlou Si, Naihao Liu, Yao Wu, Li Niu, and Chen Qian

   In ACMM, Ottawa ON, Canada, 2023

   Abs PDF

   Object part parsing involves segmenting objects into semantic parts, which has drawn great attention recently. The current methods ignore the specific hierarchical structure of the object, which can be used as strong prior knowledge. To address this, we propose the Hierarchical Dual Transformer (HDTR) to explore the contribution of the typical structural priors of the object parts. HDTR first generates the pyramid multi-granularity pixel representations under the supervision of the object part parsing maps at different semantic levels and then assigns each region an initial part embedding. Moreover, HDTR generates an edge pixel representation to extend the capability of the network to capture detailed information. Afterward, we design a Hierarchical Part Transformer to upgrade the part embeddings to their hierarchical counterparts with the assistance of the multi-granularity pixel representations. Next, we propose a Hierarchical Pixel Transformer to infer the hierarchical information from the part embeddings to enrich the pixel representations. Note that both transformer decoders rely on the structural relations between object parts, i.e., dependency, composition, and decomposition relations. The experiments on five large-scale datasets, i.e., LaPa, CelebAMask-HQ, CIHP, LIP and Pascal Animal, demonstrate that our method sets a new state-of-the-art performance for object part parsing.

2. 

   Virtual Accessory Try-On via Keypoint Hallucination

   Junhong Gou, Bo Zhang, Li Niu, Jianfu Zhang, Jianlou Si, Chen Qian, and Liqing Zhang

   2023

   arXiv Code

3. 

   Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow

   Junhong Gou, Siyu Sun, Jianfu Zhang, Jianlou Si, Chen Qian, and Liqing Zhang

   In ACMM, Ottawa ON, Canada, 2023

   Abs arXiv Code

   Virtual try-on is a critical image synthesis task that aims to transfer clothes from one image to another while preserving the details of both humans and clothes. While many existing methods rely on Generative Adversarial Networks (GANs) to achieve this, flaws can still occur, particularly at high resolutions. Recently, the diffusion model has emerged as a promising alternative for generating high-quality images in various applications. However, simply using clothes as a condition for guiding the diffusion model to inpaint is insufficient to maintain the details of the clothes. To overcome this challenge, we propose an exemplar-based inpainting approach that leverages a warping module to guide the diffusion model’s generation effectively. The warping module performs initial processing on the clothes, which helps to preserve the local details of the clothes. We then combine the warped clothes with clothes-agnostic person image and add noise as the input of diffusion model. Additionally, the warped clothes is used as local conditions for each denoising process to ensure that the resulting output retains as much detail as possible. Our approach, namely Diffusion-based Conditional Inpainting for Virtual Try-ON(DCI-VTON), effectively utilizes the power of the diffusion model, and the incorporation of the warping module helps to produce high-quality and realistic virtual try-on results. Experimental results on VITON-HD demonstrate the effectiveness and superiority of our method. Source code and trained models will be publicly released at: https://github.com/bcmi/DCI-VTON-Virtual-Try-On.

4. ASHFormer: Axial and Sliding Window-Based Attention With High-Resolution Transformer for Automatic Stratigraphic Correlation

   Naihao Liu, Zhuo Li, Rongchang Liu, Haidong Zhang, Jinghuai Gao, Tao Wei, Jianlou Si, and Hao Wu

   IEEE Transactions on GRS, 2023

5. 

   Amodal Instance Segmentation via Prior-Guided Expansion

   Junjie Chen, Li Niu, Jianfu Zhang, Jianlou Si, Chen Qian, and Liqing Zhang

   AAAI, Jun 2023

   PDF

2022

1. 

   Weak-shot Semantic Segmentation via Dual Similarity Transfer

   Junjie Chen, Li Niu, Siyuan Zhou, Jianlou Si, Chen Qian, and Liqing Zhang

   In NeurIPS, Jun 2022

   arXiv PDF Code

2. 

   Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary

   Siyuan Zhou, Li Niu, Jianlou Si, Chen Qian, and Liqing Zhang

   BMVC, Jun 2022

   arXiv Code

2021

1. 

   Video Semantic Segmentation via Sparse Temporal Transformer

   Jiangtong Li, Wentao Wang, Junjie Chen, Li Niu, Jianlou Si, Chen Qian, and Liqing Zhang

   In ACMM, Virtual Event, China, Jun 2021

   Abs PDF Supp Video

   Currently, video semantic segmentation mainly faces two challenges: 1) the demand of temporal consistency; 2) the balance between segmentation accuracy and inference efficiency. For the first challenge, existing methods usually use optical flow to capture the temporal relation in consecutive frames and maintain the temporal consistency, but the low inference speed by means of optical flow limits the real-time applications. For the second challenge, flow based key frame warping is one mainstream solution. However, the unbalanced inference latency of flow-based key frame warping makes it unsatisfactory for real-time applications. Considering the segmentation accuracy and inference efficiency, we propose a novel Sparse Temporal Transformer (STT) to bridge temporal relation among video frames adaptively, which is also equipped with query selection and key selection. The key selection and query selection strategies are separately applied to filter out temporal and spatial redundancy in our temporal transformer. Specifically, our STT can reduce the time complexity of temporal transformer by a large margin without harming the segmentation accuracy and temporal consistency. Experiments on two benchmark datasets, Cityscapes and Camvid, demonstrate that our method achieves the state-of-the-art segmentation accuracy and temporal consistency with comparable inference speed.

2020

1. 

   DMVOS: Discriminative Matching for Real-time Video Object Segmentation

   Peisong Wen, Ruolin Yang, Qianqian Xu, Chen Qian, Qingming Huang, Runmin Cong, and Jianlou Si

   In ACMM, Seattle, WA, USA, Jun 2020

   Abs PDF Supp Video

   Though recent methods on semi-supervised video object segmentation (VOS) have achieved an appreciable improvement of segmentation accuracy, it is still hard to get an adequate speed-accuracy balance when facing real-world application scenarios. In this work, we propose Discriminative Matching for real-time Video Object Segmentation (DMVOS), a real-time VOS framework with high-accuracy to fill this gap. Based on the matching mechanism, our framework introduces discriminative information through the Isometric Correlation module and the Instance Center Offset module. Specifically, the isometric correlation module learns a pixel-level similarity map with semantic discriminability, and the instance center offset module is applied to exploit the instance-level spatial discriminability. Experiments on two benchmark datasets show that our model achieves state-of-the-art performance with extremely fast speed, for example, J&F of 87.8% on DAVIS-2016 validation set with 35 milliseconds per frame.

2018

1. 

   Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-Identification

   Jianlou Si, Honggang Zhang, Chun-Guang Li, Jason Kuen, Xiangfei Kong, Alex C. Kot, and Gang Wang

   In CVPR, Jun 2018

   arXiv

2. 

   Spatial Pyramid-Based Statistical Features for Person Re-Identification: A Comprehensive Evaluation

   Jianlou Si, Honggang Zhang, Chun-Guang Li, and Jun Guo

   IEEE Transactions on SMC: Systems, Jun 2018

   PDF

2016

1. 

   Fusing multiple statistical features via explicit feature mapping for person re-identification

   Hongli Zhang, Honggang Zhang, and Jianlou Si

   In IC-NIDC, Jun 2016

   PDF

2015

1. 

   Regularization in metric learning for person re-identification

   Jianlou Si, Honggang Zhang, and Chun-Guang Li

   In ICIP, Jun 2015

   PDF

2014

1. 

   Person re-identification via region-of-interest based features

   Jianlou Si, Honggang Zhang, and Chun-Guang Li

   In VCIP, Jun 2014

   PDF