Search Results for author: Hanjun Li

Found 6 papers, 4 papers with code

D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation

1 code implementation ICCV 2023 Hanjun Li, Xiujun Shu, Sunan He, Ruizhi Qiao, Wei Wen, Taian Guo, Bei Gan, Xing Sun

Under this setup, we propose a Dynamic Gaussian prior based Grounding framework with Glance annotation (D3G), which consists of a Semantic Alignment Group Contrastive Learning module (SA-GCL) and a Dynamic Gaussian prior Adjustment module (DGA).

Contrastive Learning Sentence +1

Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies

1 code implementation CVPR 2023 Bei Gan, Xiujun Shu, Ruizhi Qiao, Haoqian Wu, Keyu Chen, Hanjun Li, Bo Ren

Based on existing efforts, this work has two observations: (1) For different annotators, labeling highlight has uncertainty, which leads to inaccurate and time-consuming annotations.

Highlight Detection Learning with noisy labels +1

Combined Depth Space based Architecture Search For Person Re-identification

1 code implementation CVPR 2021 Hanjun Li, Gaojie Wu, Wei-Shi Zheng

We propose a novel search space called Combined Depth Space (CDS), based on which we search for an efficient network architecture, which we call CDNet, via a differentiable architecture search algorithm.

Image Classification Person Re-Identification

Cannot find the paper you are looking for? You can Submit a new open access paper.