Tingting Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tingting Zhang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Bin Wu
Beijing University of Posts and Telecommunications, Beijing, Beijing, CHINA
3 shared publications Chunping Zheng
School of Humanities, Beijing University of Posts and Telecommunications, Beijing, 100876, China
1 shared publication- Chunping Zheng
Beijing University of Posts and Telecommunications
1 shared publication - Feng Gu
Department of Computer Science, College of Staten Island, Staten Island, New York, USA
1 shared publication - Guangyao Su
China Unicom Software Research Institute, Beijing, China
1 shared publication - Guosheng Hao
School of Artificial Intelligence and Computer Science, Jiangsu Normal University, Xuzhou, China
1 shared publication
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1317-1326
DenseSpeech: Dense Multi-Segment Temporal Grounding in Public Speaking Videos
Temporal video grounding aims to localize temporal segments in untrimmed videos based on natural language queries. While dense grounding methods accept paragraph queries, they retain a restrictive one-to-one mapping between sentences and segments. This assumption fails in real-world behavioral analysis like public speaking, where a single query often corresponds to multiple, scattered, and overlapping segments due to event repetition, co-occurrence, and cross-modal complexity. To address this gap, we extend dense video grounding to a multi-segment setting and present DenseSpeech, the first densely annotated video grounding dataset in the speech domain. DenseSpeech comprises 1,800 authentic classroom recordings with 13,880 annotated segments spanning over 52 hours, featuring high annotation density, frequent boundary overlap, and pervasive event repetition with form variability. We further propose DenseMSG, an end-to-end dense multi-scale grounding model. Its Cross-modal Consistent Interaction module employs text-guided cross-attention to highlight query-relevant temporal regions and performs hierarchical bidirectional audiovisual fusion with adaptive gating to build a multi-scale feature pyramid. A Multi-Scale Integration module enables bidirectional feature propagation across scales for complementary global-local modeling, while similarity-based classification and query-aware regression heads jointly predict boundaries at all scales, naturally supporting one-to-many retrieval. Experiments show DenseMSG achieves state-of-the-art performance on DenseSpeech and public benchmarks (TACoS, ActivityNet Captions), validating the dataset and model.
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1317-1326
Open AccessDenseSpeech: Dense Multi-Segment Temporal Grounding in Public Speaking Videos
Temporal video grounding aims to localize temporal segments in untrimmed videos based on natural language queries. While dense grounding methods accept paragraph queries, they retain a restrictive one-to-one mapping between sentences and segments. This assumption fails in real-world behavioral analysis like public speaking, where a single query often corresponds to multiple, scattered, and overlapping segments due to event repetition, co-occurrence, and cross-modal complexity. To address this gap, we extend dense video grounding to a multi-segment setting and present DenseSpeech, the first densely annotated video grounding dataset in the speech domain. DenseSpeech comprises 1,800 authentic classroom recordings with 13,880 annotated segments spanning over 52 hours, featuring high annotation density, frequent boundary overlap, and pervasive event repetition with form variability. We further propose DenseMSG, an end-to-end dense multi-scale grounding model. Its Cross-modal Consistent Interaction module employs text-guided cross-attention to highlight query-relevant temporal regions and performs hierarchical bidirectional audiovisual fusion with adaptive gating to build a multi-scale feature pyramid. A Multi-Scale Integration module enables bidirectional feature propagation across scales for complementary global-local modeling, while similarity-based classification and query-aware regression heads jointly predict boundaries at all scales, naturally supporting one-to-many retrieval. Experiments show DenseMSG achieves state-of-the-art performance on DenseSpeech and public benchmarks (TACoS, ActivityNet Captions), validating the dataset and model.
- 4 March 2025
- Published by Elsevier in Neural Networks
- Vol. 187, 107314
A general debiasing framework with counterfactual reasoning for multimodal public speaking anxiety detection
- 4 March 2025
- Published by Elsevier in Neural Networks
- Vol. 187, 107314
A general debiasing framework with counterfactual reasoning for multimodal public speaking anxiety detection
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3667-3676
PCENet: Psychological Clues Exploration Network for Multimodal Personality Assessment
Multimodal personality assessment aims to identify and express human personality traits in videos. Existing methods primarily focus on multimodal fusion while ignoring the inherent psychological clues essential for this interdisciplinary task. Modality clues: personality traits are stable over time due to their genetic and environmental origins, resulting in stable personality traits in the multimodal data. Trait clues: multiple traits often co-occur with non-negligible correlations, which can collectively aid trait identification. To simultaneously capture the above psychological clues, we propose a novel Psychological Clues Exploration Network (PCENet) for multimodal personality assessment, which is a human-like judgment paradigm with more generalization capability. Specifically, we first devise a multimodal hierarchical disentanglement, which clearly aligns stable representations among different modalities and separates the mutability of each modality. Subsequently, a Transformer-backbone decoder equipped with modality-to-trait attention is exploited to adaptively generate a tailored representation for each trait with the guidance of trait semantics. The trait semantics are obtained by exploiting trait correlations through self-attention. Extensive experiments on the First Impression V2 dataset demonstrate that our PCENet outperforms the state-of-the-art methods for multimodal personality assessment.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3667-3676
Open AccessPCENet: Psychological Clues Exploration Network for Multimodal Personality Assessment
Multimodal personality assessment aims to identify and express human personality traits in videos. Existing methods primarily focus on multimodal fusion while ignoring the inherent psychological clues essential for this interdisciplinary task. Modality clues: personality traits are stable over time due to their genetic and environmental origins, resulting in stable personality traits in the multimodal data. Trait clues: multiple traits often co-occur with non-negligible correlations, which can collectively aid trait identification. To simultaneously capture the above psychological clues, we propose a novel Psychological Clues Exploration Network (PCENet) for multimodal personality assessment, which is a human-like judgment paradigm with more generalization capability. Specifically, we first devise a multimodal hierarchical disentanglement, which clearly aligns stable representations among different modalities and separates the mutability of each modality. Subsequently, a Transformer-backbone decoder equipped with modality-to-trait attention is exploited to adaptively generate a tailored representation for each trait with the guidance of trait semantics. The trait semantics are obtained by exploiting trait correlations through self-attention. Extensive experiments on the First Impression V2 dataset demonstrate that our PCENet outperforms the state-of-the-art methods for multimodal personality assessment.
- Open Access
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 135661-135674
A Molecular Interactions-Based Social Learning Particle Swarm Optimization Algorithm
Social learning particle swarm optimization (SL-PSO) allows individuals to learn from others to improve the scalability with easy parameter settings. However, it still suffers from the poor convergence for those multi-modal problems due to the loss of swarm diversity. To improve both the diversity and the convergence, this paper proposes a novel algorithm to apply the mechanism of molecular interactions to SL-PSO, in which the molecular attraction aims to improve the convergence, and the molecular repulsion intends to enhance the diversity. In the experiments, we compare our algorithm with the SL-PSO algorithm and other representative PSO and evolutionary algorithms on 49 benchmark functions. The results show the performance of the proposed algorithm is better than that of the SL-PSO algorithm and other representative PSO and evolutionary algorithms on average. This work builds the solid foundation for the integration of the molecular interaction mechanism with PSO and other optimization algorithms.
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 135661-135674
Open AccessA Molecular Interactions-Based Social Learning Particle Swarm Optimization Algorithm
Social learning particle swarm optimization (SL-PSO) allows individuals to learn from others to improve the scalability with easy parameter settings. However, it still suffers from the poor convergence for those multi-modal problems due to the loss of swarm diversity. To improve both the diversity and the convergence, this paper proposes a novel algorithm to apply the mechanism of molecular interactions to SL-PSO, in which the molecular attraction aims to improve the convergence, and the molecular repulsion intends to enhance the diversity. In the experiments, we compare our algorithm with the SL-PSO algorithm and other representative PSO and evolutionary algorithms on 49 benchmark functions. The results show the performance of the proposed algorithm is better than that of the SL-PSO algorithm and other representative PSO and evolutionary algorithms on average. This work builds the solid foundation for the integration of the molecular interaction mechanism with PSO and other optimization algorithms.