Hongjie Zhang

Hongjie Zhang

Auto-generated profile, based on publicly available information

Hongjie Zhang

Shanghai Artificial Intelligence Laboratory, 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
25 November 2019 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YZYang Zhang
Yang Zhang
MLMoyun Liu
Moyun Liu
YCYunian Chen
Yunian Chen
HZHongjie Zhang
Hongjie Zhang
YGYanwen Guo
Yanwen Guo
Real-time vision based system of fault detection (RVBS-FD) for freight trains aims to complete routine maintenance tasks efficiently for ensuring railway transportation security. However, most existing systems are designed to detect only one specific type of faults or even one fault, which fail to deal with multi-fault detection. Recently, the rapid development of deep learning techniques enables systems to provide a robust solution for the RVBS-FD of freight trains. But general convolutional neural networks (CNN) cannot fully meet the actual requirements in terms of the real-time, accuracy, and resource constrains for the RVBS-FD of freight trains. To solve these problems, we propose a CNN-based detector called Light FTI-FDet for the RVBS-FD of freight train. First, we use the multi-region proposal networks which extract a set of prior bounding boxes to achieve initial fault proposal generation. Then, a powerful multi-level region-of-interest pooling is presented for proposal classification and accurate detection. We finally design a reliable model reduction scheme to pursue fast speed with high detection accuracy in a simple manner. The experimental results on five typical fault benchmarks indicate that our Light FTI-FDet achieves higher accuracy and fast speed with about 17% model size of the well-known Faster R-CNN detector, substantially outperforming state-of-the-art methods.

29 April 2024 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
YHYifei Huang
Yifei Huang
LYLijin Yang
Lijin Yang
GCGuo Chen
Guo Chen
HZHongjie Zhang
Hongjie Zhang
FLFeng Lu
Feng Lu
YSYoichi Sato
Yoichi Sato
The task of few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. How to better describe the action in each video and how to compare the similarity between videos are two of the most critical factors in this task. Directly describing the video globally or by its individual frames cannot well represent the spatiotemporal dependencies within an action. On the other hand, naively matching the global representations of two videos is also not optimal since action can happen at different locations in a video with different speeds. In this work, we propose a novel approach that describes each video using multiple types of prototypes and then computes the video similarity with a particular matching strategy for each type of prototypes. To better model the spatiotemporal dependency, we describe the video by generating prototypes that model the multi-level spatiotemporal relations via transformers. There are a total of three types of prototypes. The first type of prototypes are trained to describe specific aspects of the action in the video e.g., the start of the action, regardless of its timestamp. These prototypes are directly matched one-to-one between two videos to compare their similarity. The second type of prototypes are the timestamp-centered prototypes that are trained to focus on specific timestamps of the video. To deal with the temporal variation of actions in a video, we apply bipartite matching to allow the matching of prototypes of different timestamps. The third type of prototypes are generated from the timestamp-centered prototypes, which regularize their temporal consistency while serving as an auxiliary summarization of the whole video. Experiments demonstrate that our proposed method achieves state-of-the-art results on multiple benchmarks.

26 October 2023
Verified
Conference Paper
Open access
HZHongjie Zhang
Hongjie Zhang
YLYi Liu
Yi Liu
YWYali Wang
Yali Wang
LWLimin Wang
Limin Wang
YQYu Qiao
Yu Qiao
Open set action recognition (OSAR) is a challenging task that requires a classifier to identify actions that do not belong to any of the classes in its training set. Existing methods employ the Evidential Neural Network (ENN) as an open-set classifier, which is trained in a supervised manner on feature representations from known classes to quantify the predictive uncertainty of human actions. In this paper, we propose a novel framework for OSAR that enriches the discriminative representation from a backbone with a reconstructive one to further improve performance. Our approach involves augmenting the input features with their reconstruction obtained from a reconstruction-based model in unsupervised training on known classes. We then use the correspondence between the two features to learn the open-set classifier, forcing it to associate low correspondence both when the feature is from unknown classes as well as when the input feature and its reconstruction variant are inconsistent with each other. Our experimental results on standard OSAR benchmarks demonstrate that our end-to-end trained model significantly outperforms state-of-the-art methods. Our proposed approach shows the effectiveness of combining discriminative and reconstructive representations for OSAR.

18 April 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
LDLu Dong
Lu Dong
HZHaiyu Zhang
Haiyu Zhang
HZHongjie Zhang
Hongjie Zhang
YHYifei Huang
Yifei Huang
ZLZhenhua Ling
Zhenhua Ling
YWYali Wang
Yali Wang
The task of weakly supervised temporal sentence grounding (WSTSG) aims to detect temporal intervals corresponding to a language description from untrimmed videos with only video-level video-language correspondence. For an anchor sample, most existing approaches generate negative samples either from other videos or within the same video for contrastive learning. However, some training samples are highly similar to the anchor sample, directly regarding them as negative samples leads to difficulties for optimization and ignores the correlations between these similar samples and the anchor sample. To address this, we propose Positive Sample Mining (PSM), a novel framework that mines positive samples from the training set to provide more discriminative supervision. Specifically, for a given anchor sample, we partition the remaining training set into semantically similar and dissimilar subsets based on the similarity of their text queries. To effectively leverage these correlations, we introduce a PSM-guided contrastive loss to ensure that the anchor proposal is closer to similar samples and further from dissimilar ones. Additionally, we design a PSM-guided rank loss to ensure that similar samples are closer to the anchor proposal than to the negative intra-video proposal, aiming to distinguish the anchor proposal and the negative intra-video proposal. Experiments on the WSTSG and grounded VideoQA tasks demonstrate the effectiveness and superiority of our method.

8 August 2025 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
HZHongjie Zhang
Hongjie Zhang
LDLu Dong
Lu Dong
YLYi Liu
Yi Liu
YHYifei Huang
Yifei Huang
YWYali Wang
Yali Wang
YQYu Qiao
Yu Qiao