Chunping Wang

Chunping Wang

Auto-generated profile, based on publicly available information

Chunping Wang

FinVolution Group, Shanghai, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
ZCZhiqing Chen
Zhiqing Chen
YLYawei Luo
Yawei Luo
JSJian Shao
Jian Shao
YYYi Yang
Yi Yang
CWChunping Wang
Chunping Wang
JXJun Xiao
Jun Xiao
One of the major obstacles that hinders the current scene graph generation (SGG) performance lies in the severe predicate annotation bias. Conventional solutions to this problem are mainly based on reweighting/resampling heuristics. Despite achieving some improvements on tail classes, these methods are prone to cause serious performance degradation of head predicates. In this paper, we propose to tackle this problem from a brand-new perspective of dark knowledge. In consideration of the unique nature of SGG that requires a large number of negative samples to be employed for predicate learning, we design to capitalize on the dark knowledge contained in negative samples for debiasing the predicate distribution. Along such vein, we propose a novel SGG method dubbed Dark Knowledge Balance Learning (DKBL). In DKBL, we first design a dark knowledge balancing loss, which helps the model learn to balance head and tail predicates while maintaining the overall performance. We further introduce a dark knowledge semantic enhancement module to better encode the semantics of predicates. DKBL is orthogonal to existing SGG methods and can be easily plugged into their training process for further improvement. Extensive experiments on VG dataset show that the proposed DKBL can consistently achieve well trade-off performance between head and tail predicates, which is significantly better than previous state-of-the-art methods. The code is available in https://github.com/chenzqing/DKBL.

13 May 2024
Verified
Conference Paper
Open access
LCLinfeng Cao
Linfeng Cao
HDHaoran Deng
Haoran Deng
YYYang Yang
Yang Yang
CWChunping Wang
Chunping Wang
LCLei Chen
Lei Chen
Due to the ubiquity of graph data on the web, web graph mining has become a hot research spot. Nonetheless, the prevalence of largescale web graphs in real applications poses significant challenges to storage, computational capacity and graph model design. Despite numerous studies to enhance the scalability of graph models, a noticeable gap remains between academic research and practical web graph mining applications. One major cause is that in most industrial scenarios, only a small part of nodes in a web graph are actually required to be analyzed, where we term these nodes as target nodes, while others as background nodes. In this paper, we argue that properly fetching and condensing the background nodes from massive web graph data might be a more economical shortcut to tackle the obstacles fundamentally. To this end, we make the first attempt to study the problem of massive background nodes compression for target nodes classification. Through extensive experiments, we reveal two critical roles played by the background nodes in target node classification: enhancing structural connectivity between target nodes, and feature correlation with target nodes. Following this, we propose a novel Graph-Skeleton model, which properly fetches the background nodes, and further condenses the semantic and topological information of background nodes within similar target-background local structures. Extensive experiments on various web graph datasets demonstrate the effectiveness and efficiency of the proposed method. In particular, for MAG240M dataset with 0.24 billion nodes, our generated skeleton graph achieves highly comparable performance while only containing 1.8% nodes of the original graph.

20 July 2025
Verified
Conference Paper
Open access
YSYifei Sun
Yifei Sun
YYYang Yang
Yang Yang
XFXiao Feng
Xiao Feng
ZWZijun Wang
Zijun Wang
HZHaoyang Zhong
Haoyang Zhong
LCLei Chen
Lei Chen

20 July 2025
Verified
Conference Paper
Open access
YCYuxuan Cao
Yuxuan Cao
JXJiarong Xu
Jiarong Xu
CZChen Zhao
Chen Zhao
JWJiaan Wang
Jiaan Wang
CYCarl Yang
Carl Yang
YYYang Yang
Yang Yang

22 April 2025
Verified
Conference Paper
Open access
XHXuanwen Huang
Xuanwen Huang
WCWei Chow
Wei Chow
YZYize Zhu
Yize Zhu
YWYang Wang
Yang Wang
ZCZiwei Chai
Ziwei Chai
YYYang Yang
Yang Yang

28 October 2024
Verified
Conference Paper
Open access
JLJiaming Lei
Jiaming Lei
LLLin Li
Lin Li
CWChunping Wang
Chunping Wang
JXJun Xiao
Jun Xiao
LCLong Chen
Long Chen
Benefiting from strong generalization ability, pre-trained vision-language models (VLMs), e.g., CLIP, have been widely utilized in zero-shot scene understanding. Unlike simple recognition tasks, grounded situation recognition (GSR) requires the model not only to classify salient activity (verb) in the image, but also to detect all semantic roles that participate in the action. This complex task usually involves three steps: verb recognition, semantic role grounding, and noun recognition. Directly employing class-based prompts with VLMs and grounding models for this task suffers from several limitations, e.g., it struggles to distinguish ambiguous verb concepts, accurately localize roles with fixed verb-centric template input, and achieve context-aware noun predictions. In this paper, we argue that these limitations stem from the model's poor understanding of verb/noun classes. To this end, we introduce a new approach for zero-shot GSR via Language EXplainer (LEX), which significantly boosts the model's comprehensive capabilities through three explainers: 1) verb explainer, which generates general verb-centric descriptions to enhance the discriminability of different verb classes; 2) grounding explainer, which rephrases verb-centric templates for clearer understanding, thereby enhancing precise semantic role localization; and 3) noun explainer, which creates scene-specific noun descriptions to ensure context-aware noun recognition. By equipping each step of the GSR process with an auxiliary explainer, LEX facilitates complex scene understanding in real-world scenarios. Our extensive validations on the SWiG dataset demonstrate LEX's effectiveness and interoperability in zero-shot GSR.