多媒体内容分析，多模态大模型，实时视频理解与生成，数据挖掘，跨模态检索

钱胜胜，中国科学院自动化研究所研究员。研究方向为多媒体内容分析，多模态大模型等，在IEEE/ACM Trans.期刊和CCF-A类会议上发表论文70余篇，相关成果获中科院优博、ACM MM 2016年最佳论文、2019年最佳论文提名、SIGIR 2024年最佳论文提名、ICIG 2025年最佳论文等。担任CCF多媒体专委会副秘书长，主持国家自然科学基金青年基金B类、企业联合基金重点项目、国家重点研发计划青年科学家项目、某部委专项、北京市杰出青年基金、腾讯微信犀牛鸟专项、百度科研专项、小米科研专项和快手科研专项等，相关成果获中国电子学会技术发明一等奖（序2）。

081104-模式识别与智能系统
081203-计算机应用技术

多媒体内容分析，跨模态检索与推荐

2012-09--2017-07   中国科学院大学   博士学位
2008-09--2012-07   吉林大学   学士学位

工作简历

2026-03~现在，中国科学院自动化研究所, 研究员

2019-10~2026-03, 中国科学院自动化研究所, 副研究员

2017-07~2019-10,中国科学院自动化研究所, 助理研究员

社会兼职

2019-09~今，中国计算机学会多媒体专业委员会委员,

2019-09~今，中国图象图形学学会多媒体专业委员会委员,

2017-07~今，IEEE TPAMI/TKDE/IEEE TMM/IEEE TCSVT和ACM MM/AAAI/CVPR/ICCV等国际期刊和国际会议审稿

   

（1） 2025年 第十三届国际图象图形学学术会议（ICIG）最佳论文奖, 2025

（2） 2024年 第 47 届国际计算机协会信息检索大会（ACM SIGIR） 最佳论文提名, 2024

（3） 2023年 ACM SIGMM 中国新星, 2023

（4） 2019年 中国多媒体大会最佳论文奖, 2019

（5） 2019年 ACM Multimedia 最佳论文提名, 2019

（6） 2018年 中国科学院优秀博士学位论文, 2018

（7） 2016年 ACM Multimedia 最佳论文奖, 2016

[1] Zhenyu Yang, Yuhang Hu, Zemin Du, Dizhan Xue, Shengsheng Qian, Jiahong Wu, Fan Yang, Weiming Dong, Changsheng Xu: SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding. The Thirteenth International Conference on Learning Representations (ICLR) 2025 Spotlight.

[2] Shangheng Chen, Shengsheng Qian, Quan Fang, Jun Hu, Changsheng Xu: A Large-Scale Dataset for Short-Video Topic Peak Prediction and a Large Heterogeneous Graph Model. ACM Multimedia (MM) 2025: 7998-8007.

[3] Yuhang Hu, Zhenyu Yang, Shihan Wang, Shengsheng Qian, Bin Wen, Fan Yang, Tingting Gao, Changsheng Xu: StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA. ACM Multimedia (MM) 2025: 13464-13470.

[4] Dizhan Xue, Shengsheng Qian, Quan Fang, Changsheng Xu: LININ: Logic Integrated Neural Inference Network for Explanatory Visual Question Answering. IEEE Transactions on Multimedia (TMM) 27: 16-27 (2025).

[5] Shengsheng Qian, Shengjie Zhang, Dizhan Xue, Huaiwen Zhang, Changsheng Xu: Learning Temporal Event Knowledge for Continual Social Event Classification. IEEE Transactions on Knowledge and Data Engineering (TKDE). 37(6): 3485-3498 (2025).

[6] Zuyi Zhou, Dizhan Xue, Baoyuan Qi, Shengsheng Qian, Changsheng Xu: Code-Driven LLM Agent for One-Shot Explanatory Visual Question Answering. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) (2025).

[7] Huaiwen Zhang, Yang Yang, Fan Qi, Shengsheng Qian, Changsheng Xu: Active supervised cross-modal retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 47(6): 5112-5126 (2025).

[8] Shangheng Chen, Quan Fang, Shengsheng Qian, Changsheng Xu: Metapath-enhanced Language Model Pretraining on Text-Attributed Heterogeneous Graphs. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) (2025).

[9] Yongxi Li, Wenzhong Tang, Shuai Wang, Shengsheng Qian, Quan Fang, Changsheng Xu: Propagation based Recycling Contrastive Learning for Coupled Noisy Visible-Infrared Person Re-identification. IEEE Transactions on Multimedia (TMM) 27: 9330-9341 (2025).

[10] Jinguang Wang, Shengsheng Qian, Jun Hu, Wenxiang Dong, Xudong Huang, Richang Hong: End-to-End Explainable Fake News Detection Via Evidence-Claim Variational Causal Inference. ACM Transactions on Information Systems (TOIS). 43(4): 89:1-89:26 (2025).

[11] Huaiwen Zhang, Xin xin Liu, Qing Yang, Yang Yang, Fan Qi, Shengsheng Qian, Changsheng Xu. T3RD: Test-Time Training for Rumor Detection on Social Media. The ACM Web Conference (WWW) 2024.

[12] Jun Hu, Bryan Hooi, Shengsheng Qian, Quan Fang, Changsheng Xu. MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering. IEEE Transactions on Knowledge and Data Engineering (TKDE) 2024.

[13] Yifei Wang, Dizhan Xue, Shengjie Zhang, Shengsheng Qian: BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents. Annual Meeting of the Association for Computational Linguistics (ACL) (1) 2024: 9811-9827.

[14] Zhenyu Yang, Shengsheng Qian, Dizhan Xue, Jiahong Wu, Fan Yang, Weiming Dong, Changsheng Xu: Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval. ACM Multimedia (MM) 2024: 1245-1254.

[15] Dizhan Xue, Shengsheng Qian, Changsheng Xu: Few-Shot Multimodal Explanation for Visual Question Answering. ACM Multimedia (MM) 2024: 1875-1884.

[16] Zhenyu Yang, Dizhan Xue, Shengsheng Qian, Weiming Dong, Changsheng Xu: LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval. The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2024: 80-90. 《最佳论文提名》

[17] Huaiwen Zhang, Xinxin Liu, Qing Yang, Yang Yang, Fan Qi, Shengsheng Qian, Changsheng Xu: T3RD: Test-Time Training for Rumor Detection on Social Media. The ACM Web Conference (WWW) 2024: 2407-2416.

[18] Jinguang Wang, Shengsheng Qian, Jun Hu, Richang Hong, Comment-Context Dual Collaborative Masked Transformer Network for Fake News Detection. IEEE Transactions on Multimedia (TMM) 2024.

[19] Jinguang Wang, Shengsheng Qian, Jun Hu, Richang Hong. Positive Unlabeled Fake News Detection Via Multi-Modal Masked Transformer Network. IEEE Transactions on Multimedia (TMM) 26: 234-244 (2024).

[20] Yongxi Li, Wenzhong Tang, Shuai Wang, Shengsheng Qian, Changsheng Xu: Distribution-Guided Hierarchical Calibration Contrastive Network for Unsupervised Person Re-Identification. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). Video Technol. 34(8): 7149-7164 (2024).

[21] Yang Yang, Yishan Zhang, Shengsheng Qian, Kaiquan Cai: Scenario-Guided Transformer-Enabled Multi-Modal Unknown Event Classification for Air Transport. IEEE Trans. IEEE Transactions on Intelligent Transportation Systems(T-ITS). 25(12): 21658-21671 (2024).

[22] Jun Hu, Bryan Hooi, Shengsheng Qian, Quan Fang, Changsheng Xu: MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering. IEEE Transactions on Knowledge and Data Engineering (TKDE). 36(7): 3281-3296 (2024).

[23] Jinguang Wang, Shengsheng Qian, Jun Hu, Richang Hong: Positive Unlabeled Fake News Detection via Multi-Modal Masked Transformer Network. IEEE Transactions on Multimedia (TMM) 26: 234-244 (2024).

[24] Jinguang Wang, Shengsheng Qian, Jun Hu, Richang Hong: Comment-Context Dual Collaborative Masked Transformer Network for Fake News Detection. IEEE Transactions on Multimedia (TMM) 26: 5170-5180 (2024).

[25] Xingrui Zhuo, Shengsheng Qian, Jun Hu, Fuxin Dai, Kangyi Lin, Gongqing Wu: Multi-Hop Multi-View Memory Transformer for Session-Based Recommendation. ACM Transactions on Information Systems (TOIS). 42(6): 144:1-144:28 (2024).

[26] Shengsheng Qian, Hong Chen, Dizhan Xue, Quan Fang, Changsheng Xu: Open-World Social Event Classification. The ACM Web Conference (WWW) 2023: 1562-1571.

[27] Dizhan Xue, Shengsheng Qian, Changsheng Xu. Variational Causal Inference Network for Explanatory Visual Question Answering. International Conference on Computer Vision (ICCV) 2023: 2515-2525.

[28] Huaiwen Zhang, Yang Yang, Fan Qi, Shengsheng Qian, Changsheng Xu. C2MR: Continual Cross-Modal Retrieval for Streaming Multi-modal Data. ACM Multimedia (MM) 2023: 8963-8974.

[29] Shengsheng Qian, Dizhan Xue, Quan Fang, Changsheng Xu: Integrating Multi-Label Contrastive Learning With Dual Adversarial Graph Neural Networks for Cross-Modal Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 45(4): 4794-4811 (2023).

[30] Huaiwen Zhang, Yang Yang, Fan Qi, Shengsheng Qian, Changsheng Xu. Debiased Video-Text Retrieval via Soft Positive Sample Calibration. IEEE Transactions on Circuits and Systems for Video Technology (TCVST) 33(9): 5257-5270 (2023).

[31] Huaiwen Zhang, Yang Yang, Fan Qi, Shengsheng Qian, Changsheng Xu. Robust Video-Text Retrieval via Noisy Pair Calibration. IEEE Transactions on Multimedia (TMM) 25: 8632-8645 (2023).

[32] Lei Sang, Min Xu, Shengsheng Qian, Xindong Wu: Adversarial Heterogeneous Graph Neural Network for Robust Recommendation. IEEE Transactions on Computational Social Systems (TCSS) 10(5): 2660-2671 (2023).

[33] Kang Liu, Feng Xue, Dan Guo, Peijie Sun, Shengsheng Qian, Richang Hong. Multimodal Graph Contrastive Learning for Multimedia-Based Recommendation. IEEE Transactions on Multimedia (TMM) 25: 9343-9355 (2023).

[34] Desheng Cai, Shengsheng Qian, Quan Fang, Jun Hu, Changsheng Xu. User cold-start recommendation via inductive heterogeneous graph neural network. ACM Transactions on Information Systems (TOIS) 41(3): 64:1-64:27 (2023).

[35] Yingying Zhang, Xian Wu, Quan Fang, Shengsheng Qian, Changsheng Xu: Knowledge-Enhanced Attributed Multi-Task Learning for Medicine Recommendation. ACM Transactions on Information Systems (TOIS) 41(1): 17:1-17:24 (2023).

[36] Desheng Cai, Shengsheng Qian, Quan Fang, Jun Hu, Changsheng Xu: Adaptive Anti-Bottleneck Multi-Modal Graph Learning Network for Personalized Micro-video Recommendation. ACM Multimedia (MM) 2022: 581-590.

[37] Dizhan Xue, Shengsheng Qian, Quan Fang, Changsheng Xu: MMT: Image-guided Story Ending Generation with Multimodal Memory Transformer. ACM Multimedia (MM) 2022: 750-758.

[38] Zhangming Li, Shengsheng Qian, Jie Cao, Quan Fang, Changsheng Xu: Adaptive Transformer-Based Conditioned Variational Autoencoder for Incomplete Social Event Classification. ACM Multimedia (MM) 2022: 1698-1707.

[39] Shengsheng Qian, Dizhan Xue, Quan Fang, and Changsheng Xu. Adaptive Label-aware Graph Convolutional Networks for Cross-Modal Retrieval. IEEE Transactions on Multimedia (TMM), 24: 3520-3532 (2022).

[40] Desheng Cai, Shengsheng Qian, Quan Fang, Changsheng Xu. Heterogeneous Hierarchical Feature Aggregation Network for Personalized Micro-video Recommendation. IEEE Transactions on Multimedia (TMM) 24: 805-818 (2022).

[41] Huaiwen Zhang, Shengsheng Qian, Quan Fang, Changsheng Xu: Multi-modal Meta Multi-Task Learning for Social Media Rumor Detection. IEEE Transactions on Multimedia (TMM) 24: 1449-1459 (2022).

[42] Shengsheng Qian, Dizhan Xue, Huaiwen Zhang, Quan Fang, Changsheng Xu. Dual Adversarial Graph Neural Networks for Multi-¬Label Cross-Modal Retrieval. The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI) 2021: 2440-2448.

[43] Shengsheng Qian, Jinguang Wang, Jun Hu, Quan Fang, Changsheng Xu. Hierarchical Multi-modal Contextual Attention Network for Fake News Detection. The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2021: 153-162. ，

[44] Song Liu, Haoqi Fan, Shengsheng Qian, Yiru Chen, Wenkui Ding, Zhongyuan Wang. HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval. International Conference on Computer Vision (ICCV) 2021: 11895-11905.

[45] Jun Hu, Shengsheng Qian, Quan Fang, Youze Wang, Quan Zhao, Huaiwen Zhang, Changsheng Xu: Efficient Graph Deep Learning in TensorFlow with tf_geometric. ACM Multimedia (MM) 2021: 3775-3778.

[46] Shengsheng Qian, Jun Hu, Quan Fang, Changsheng Xu: Knowledge-aware Multi-modal Adaptive Graph Convolutional Networks for Fake News Detection. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 17(3): 98:1-98:23 (2021).

[47] Lei Sang, Min Xu, Shengsheng Qian, Matt Martin, Peter Li, Xindong Wu: Context-Dependent Propagating-Based Video Recommendation in Multimodal Heterogeneous Information Networks. IEEE Transactions on Multimedia (TMM) 23: 2019-2032 (2021).

[48] Jun Hu, Shengsheng Qian, Quan Fang, Changsheng Xu: Heterogeneous Community Question Answering via Social-Aware Multi-Modal Co-Attention Convolutional Matching. IEEE Transactions on Multimedia (TMM) 23: 2321-2334 (2021).

[49] Chaofan Chen, Shengsheng Qian, Quan Fang, Changsheng Xu: HAPGN: Hierarchical Attentive Pooling Graph Network for Point Cloud Segmentation. IEEE Transactions on Multimedia (TMM) 23: 2335-2346 (2021).

[50] Huaiwen Zhang, Shengsheng Qian, Quan Fang, Changsheng Xu: Multimodal Disentangled Domain Adaption for Social Media Event Rumor Detection. IEEE Transactions on Multimedia (TMM) 23: 4441-4454 (2021).

[51] Song Liu, Shengsheng Qian, Yang Guan, Jiawei Zhan, Long Ying. Joint-modal Distribution-based Similarity Hashing for Large-scale Unsupervised Deep Cross-modal Retrieval. The 43th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2020: 1379-1388. ，

[52] Jun Hu, Quan Fang, Shengsheng Qian, Changsheng Xu: Multi-modal Attentive Graph Pooling Model for Community Question Answer Matching. ACM Multimedia (MM) 2020: 3505-3513.

[53] Yingying Zhang, Quan Fang, Shengsheng Qian, Changsheng Xu: Multi-modal Multi-relational Feature Aggregation Network for Medical Knowledge Representation Learning. ACM Multimedia (MM) 2020: 3956-3965.

[54] Yingying Zhang, Quan Fang, Shengsheng Qian, Changsheng Xu: Knowledge-aware Attentive Wasserstein Adversarial Dialogue Response Generation. ACM Transactions on Intelligent Systems and Technology (TIST). 11(4): 37:1-37:20 (2020).

[55] Feng Xue, Richang Hong, Xiangnan He, Jianwei Wang, Shengsheng Qian, Changsheng Xu: Knowledge-Based Topic Model for Multi-Modal Social Event Analysis. IEEE Transactions on Multimedia (TMM) 22(8): 2098-2110 (2020).

[56] Xiaowen Huang, Shengsheng Qian, Quan Fang, Jitao Sang, Changsheng Xu: Meta-path Augmented Sequential Recommendation with Contextual Co-attention Network. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16(2): 52:1-52:24 (2020).

[57] Lingxiang Wu, Min Xu, Shengsheng Qian, Jianwei Cui: Image to Modern Chinese Poetry Creation via a Constrained Topic-aware Model. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16(2): 53:1-53:21 (2020).

[58] Yingying Zhang, Shengsheng Qian, Quan Fang, Changsheng Xu: Multi-modal Knowledge-aware Hierarchical Attention Network for Explainable Medical Question Answering. ACM Multimedia (MM) 2019: 1089-1097. 《最佳论文提名》

[59] Xiaowen Huang, Quan Fang, Shengsheng Qian, Jitao Sang, Yan Li, Changsheng Xu: Explainable Interaction-driven User Modeling over Knowledge Graph for Sequential Recommendation. ACM Multimedia (MM) 2019: 548-556.

[60] Jun Hu, Shengsheng Qian, Quan Fang, Changsheng Xu: Hierarchical Graph Semantic Pooling Network for Multi-modal Community Question Answer Matching. ACM Multimedia (MM) 2019: 1157-1165.

[61] Huaiwen Zhang, Quan Fang, Shengsheng Qian, Changsheng Xu: Multi-modal Knowledge-aware Event Memory Network for Social Media Rumor Detection. ACM Multimedia (MM) 2019: 1942-1951.

[62] Jun Hu, Shengsheng Qian, Quan Fang, Xueliang Liu, Changsheng Xu: A2CMHNE: Attention-Aware Collaborative Multimodal Heterogeneous Network Embedding. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 15(2): 45:1-45:17 (2019).

[63] Xiaowen Huang, Shengsheng Qian, Quan Fang, Jitao Sang, Changsheng Xu: CSAN: Contextual Self-Attention Network for User Sequential Recommendation. ACM Multimedia (MM) 2018: 447-455.

[64] Jun Hu, Shengsheng Qian, Quan Fang, Changsheng Xu: Attentive Interactive Convolutional Matching for Community Question Answering in Social Multimedia. ACM Multimedia (MM) 2018: 456-464.

[65] Huaiwen Zhang, Quan Fang, Shengsheng Qian, Changsheng Xu: Learning Multimodal Taxonomy via Variational Deep Graph Embedding and Clustering. ACM Multimedia (MM) 2018: 681-689.

[66] Shengsheng Qian, Tianzhu Zhang, Changsheng Xu: Cross-Domain Collaborative Learning via Discriminative Nonparametric Bayesian Model. IEEE Transactions on Multimedia (TMM) 20(8): 2086-2099 (2018).

[67] Shengsheng Qian, Tianzhu Zhang, Changsheng Xu: Online Multimodal Multiexpert Learning for Social Event Tracking. IEEE Transactions on Multimedia (TMM) 20(10): 2733-2748 (2018).

[68] Shengsheng Qian, Tianzhu Zhang, Changsheng Xu: Multi-modal Multi-view Topic-opinion Mining for Social Event Analysis. ACM Multimedia (MM) 2016, 2-11. 《最佳论文》

[69] Shengsheng Qian, Tianzhu Zhang, Changsheng Xu, Jie Shao. Multi-Modal Event Topic Model for Social Event Analysis. IEEE Transactions on Multimedia (TMM) 18(2): 233-246 (2016).

[70] Shengsheng Qian, Tianzhu Zhang, Richang Hong, Changsheng Xu: Cross-Domain Collaborative Learning in Social Multimedia. ACM Multimedia (MM) 2015: 99-108.

[71] Shengsheng Qian, Tianzhu Zhang, Changsheng Xu, M. Shamim Hossain: Social Event Classification via Boosted Multimodal Supervised Latent Dirichlet Allocation. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 11(2): 27:1-27:22 (2014).

• 纵向项目

（ 1 ） 国自然青年，负责人， 2019--2021

（ 2 ） 中国科学院特别研究助理资助项目，负责人，2019--2021

（ 3 ） 国自然面上，负责人，2023--2026

（ 4 ） 某部委专项, 负责人，2023--2025

（ 5 ） 国家重点研发计划青年科学家项目，负责人，2023--2026

（ 6 ） 北京市杰青，负责人， 2023--2026

（ 7 ） 国自然青B, 负责人，2026--2028

（ 8 ） 国自然企业联合基金重点项目, 负责人，2026--2028

• 企业项目

（ 1 ） 基于多轮交互强化学习决策的在线视频理解研究 （CAAI-腾讯犀牛鸟专项）, 负责人, 企业项目（腾讯科研项目）, 2026--2027

（ 2 ） 面向长文本理解与生成的隐式推理机制研究, 负责人, 企业项目（百度科研项目）, 2026--2027

（ 3 ） 基于多模态大模型的视频流式理解技术研究, 负责人, 北京达佳信息技术有限公司（快手科研项目）, 2024--2026

（ 4 ） 面向大语言模型的高效压缩与加速推理技术研究, 负责人, 北京小米移动软件有限公司（小米科研项目）, 2024--2026

（ 5 ） 推荐场景中结合视频多模态&用户行为的主题模型 （CCF-腾讯微信犀牛鸟专项）, 负责人, 企业项目（腾讯科研项目）, 2021--2022