Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce

no code implementations • CVPR 2023 • Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu

Extensive experimental results show that, without further fine-tuning, ECLIP surpasses existing methods by a large margin on a broad range of downstream tasks, demonstrating the strong transferability to real-world E-commerce applications.

Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding

1 code implementation • 27 Sep 2022 • Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu

Spatio-Temporal video grounding (STVG) focuses on retrieving the spatio-temporal tube of a specific object depicted by a free-form textual expression.

Spatio-Temporal Video Grounding Video Grounding

FORCE: A Framework of Rule-Based Conversational Recommender System

no code implementations • 18 Mar 2022 • Jun Quan, Ze Wei, Qiang Gan, Jingqi Yao, Jingyi Lu, Yuchen Dong, Yiming Liu, Yi Zeng, Chao Zhang, Yongzhi Li, Huang Hu, Yingying He, Yang Yang, Daxin Jiang

The conversational recommender systems (CRSs) have received extensive attention in recent years.

Recommendation Systems

Integrating Pre-trained Model into Rule-based Dialogue Management

no code implementations • 17 Feb 2021 • Jun Quan, Meng Yang, Qiang Gan, Deyi Xiong, Yiming Liu, Yuchen Dong, Fangxin Ouyang, Jun Tian, Ruiling Deng, Yongzhi Li, Yang Yang, Daxin Jiang

Rule-based dialogue management is still the most popular solution for industrial task-oriented dialogue systems for their interpretablility.

Dialogue Management Management +1

Visual-Semantic Matching by Exploring High-Order Attention and Distraction

no code implementations • CVPR 2020 • Yongzhi Li, Duo Zhang, Yadong Mu

Specifically, we build scene graphs for both visual and textual modalities.

Attribute Graph Attention +6