102 citations · 266 across the 20 of their papers we have counts for
19 papers · 1 filter
SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction
Pin Tang, Zhongdao Wang, Guoqing Wang +4
Vision-based perception for autonomous driving requires an explicit modeling of a 3D space, where 2D latent representations are mapped and subsequent 3D operators are applied. Howe…
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Junsong Chen, Chongjian Ge, Enze Xie +7
In this paper, we introduce PixArt-Σ, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution. PixArt-Σrepresents a significant advancement over…
Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving
Hao Shi, Song Wang, Jiaming Zhang +5
Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision. Previous methods, confined to onboard proc…
PixArt-: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
Junsong Chen, Jincheng Yu, Chongjian Ge +8
The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community…
Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification
Zhaopeng Dou, Zhongdao Wang, Yali Li +1
This paper aims to learn a domain-generalizable (DG) person re-identification (ReID) representation from large-scale videos \textbf{without any annotation}. Prior DG ReID methods e…
MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation
Chongjian Ge, Junsong Chen, Enze Xie +5
Perception systems in modern autonomous driving vehicles typically take inputs from complementary multi-modal sensors, e.g., LiDAR and cameras. However, in real-world applications,…
Generalizable Re-Identification from Videos with Cycle Association
Zhongdao Wang, Zhaopeng Dou, Jingwei Zhang +4
In this paper, we are interested in learning a generalizable person re-identification (re-ID) representation from unlabeled videos. Compared with 1) the popular unsupervised re-ID…
Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval
Zhaopeng Dou, Zhongdao Wang, Weihua Chen +2
Current person image retrieval methods have achieved great improvements in accuracy metrics. However, they rarely describe the reliability of the prediction. In this paper, we prop…
Self-Supervised Learning via Maximum Entropy Coding
Xin Liu, Zhongdao Wang, Yali Li +1
A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on…
Adaptive Affinity for Associations in Multi-Target Multi-Camera Tracking
Yunzhong Hou, Zhongdao Wang, Shengjin Wang +1
Data associations in multi-target multi-camera tracking (MTMCT) usually estimate affinity directly from re-identification (re-ID) feature distances. However, we argue that it might…
How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?
Yuchi Liu, Zhongdao Wang, Tom Gedeon +1
This paper does not contain technical novelty but introduces our key discoveries in a data generation protocol, a database and insights. We aim to address the lack of large-scale d…
Do Different Tracking Tasks Require Different Appearance Models?
Zhongdao Wang, Hengshuang Zhao, Ya-Li Li +3
Tracking objects of interest in a video is one of the most popular and widely applicable problems in computer vision. However, with the years, a Cambrian explosion of use cases and…
Synthetic Data Are as Good as the Real for Association Knowledge Learning in Multi-object Tracking
Yuchi Liu, Zhongdao Wang, Xiangxin Zhou +1
Association, aiming to link bounding boxes of the same identity in a video sequence, is a central component in multi-object tracking (MOT). To train association modules, e.g., para…
CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions
Zhongdao Wang, Jingwei Zhang, Liang Zheng +4
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as t…
Circle Loss: A Unified Perspective of Pair Similarity Optimization
Yifan Sun, Changmao Cheng, Yuhan Zhang +4
This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity and minimize the between-class similarit…
Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking
Yunzhong Hou, Liang Zheng, Zhongdao Wang +1
Multi-target multi-camera tracking (MTMCT) systems track targets across cameras. Due to the continuity of target trajectories, tracking systems usually restrict their data associat…
Towards Real-Time Multi-Object Tracking
Zhongdao Wang, Liang Zheng, Yixuan Liu +2
Modern multiple object tracking (MOT) systems usually follow the \emph{tracking-by-detection} paradigm. It has 1) a detection model for target localization and 2) an appearance emb…
Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learning
Lanqing He, Zhongdao Wang, Yali Li +1
The softmax loss and its variants are widely used as objectives for embedding learning, especially in applications like face recognition. However, the intra- and inter-class object…
Linkage Based Face Clustering via Graph Convolution Network
Zhongdao Wang, Liang Zheng, Yali Li +1
In this paper, we present an accurate and scalable approach to the face clustering task. We aim at grouping a set of faces by their potential identities. We formulate this task as…