Shengjun Deng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shengjun Deng has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Guo Niu
Foshan University, Foshan, China
2 shared publications - Nannan Zhu
Sun Yat-Sen University, Guangzhou, China
2 shared publications - Shuaiwei Jiao
Foshan University, Foshan, China
2 shared publications - Hanyan Huang
School of Systems Science and Engineering, Sun Yat-Sen University, Guangzhou, China
1 shared publication - Huanlin Mo
Foshan University, Foshan, China
1 shared publication - Tao Li
Foshan University, Foshan, China
1 shared publication
Latest Publications
- 11 August 2026
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 20 (10) , 570
Balancing clean accuracy and gradient robustness via mask-guided mixup and adaptive label refinement
- 11 August 2026
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 20 (10) , 570
Balancing clean accuracy and gradient robustness via mask-guided mixup and adaptive label refinement
- Open Access
- 9 February 2026
- Published by Elsevier in SSRN Electronic Journal
CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning
While multimodal large language models (MLLMs) exhibit strong performance on single-video tasks (e.g., video question answering), their capability for spatiotemporal pattern reasoning across multiple videos remains a critical gap in pattern recognition research. However, this capability is essential for real-world applications, including multi-camera surveillance and cross-video procedural learning. To bridge this gap, we present CVBench, the first diagnostic benchmark designed to assess cross-video relational reasoning rigorously. CVBench comprises 1,000 question-answer pairs spanning three hierarchical tiers: cross-video object association (identifying shared entities), cross-video event association (linking temporal or causal event chains), and cross-video complex reasoning (integrating commonsense and domain knowledge). Built from five domain-diverse video clusters (e.g., sports, life records), the benchmark challenges models to analyze and integrate spatiotemporal patterns from dynamic visual streams. Extensive evaluation of 10+ leading MLLMs (including GPT-4o, Gemini-2.0-flash, Qwen2.5-VL) under zero-shot or chain-of-thought prompting paradigms. Key findings reveal stark performance gaps: even top models, such as GPT-4o, achieve only 63.5% accuracy on causal reasoning tasks, compared to the 91.3% accuracy of human performance. Crucially, our analysis reveals fundamental bottlenecks inherent in current MLLMs architectures, notably deficient inter-video context retention and poor disambiguation of overlapping entities. CVBench establishes a rigorous framework for advancing pattern recognition methodologies in multi-video scenarios, providing architectural insights for next-generation models. The data and evaluation code are available at: https://github.com/Hokhim2/CVBench.
- 9 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning
While multimodal large language models (MLLMs) exhibit strong performance on single-video tasks (e.g., video question answering), their capability for spatiotemporal pattern reasoning across multiple videos remains a critical gap in pattern recognition research. However, this capability is essential for real-world applications, including multi-camera surveillance and cross-video procedural learning. To bridge this gap, we present CVBench, the first diagnostic benchmark designed to assess cross-video relational reasoning rigorously. CVBench comprises 1,000 question-answer pairs spanning three hierarchical tiers: cross-video object association (identifying shared entities), cross-video event association (linking temporal or causal event chains), and cross-video complex reasoning (integrating commonsense and domain knowledge). Built from five domain-diverse video clusters (e.g., sports, life records), the benchmark challenges models to analyze and integrate spatiotemporal patterns from dynamic visual streams. Extensive evaluation of 10+ leading MLLMs (including GPT-4o, Gemini-2.0-flash, Qwen2.5-VL) under zero-shot or chain-of-thought prompting paradigms. Key findings reveal stark performance gaps: even top models, such as GPT-4o, achieve only 63.5% accuracy on causal reasoning tasks, compared to the 91.3% accuracy of human performance. Crucially, our analysis reveals fundamental bottlenecks inherent in current MLLMs architectures, notably deficient inter-video context retention and poor disambiguation of overlapping entities. CVBench establishes a rigorous framework for advancing pattern recognition methodologies in multi-video scenarios, providing architectural insights for next-generation models. The data and evaluation code are available at: https://github.com/Hokhim2/CVBench.