Alert button
Picture for Xiang Fang

Xiang Fang

Alert button

ChinaTelecom System Description to VoxCeleb Speaker Recognition Challenge 2023

Aug 16, 2023
Mengjie Du, Xiang Fang, Jie Li

Figure 1 for ChinaTelecom System Description to VoxCeleb Speaker Recognition Challenge 2023
Figure 2 for ChinaTelecom System Description to VoxCeleb Speaker Recognition Challenge 2023
Viaarxiv icon

You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos

Mar 16, 2023
Xiang Fang, Daizong Liu, Pan Zhou, Guoshun Nan

Figure 1 for You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos
Figure 2 for You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos
Figure 3 for You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos
Figure 4 for You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos
Viaarxiv icon

Hypotheses Tree Building for One-Shot Temporal Sentence Localization

Jan 15, 2023
Daizong Liu, Xiang Fang, Pan Zhou, Xing Di, Weining Lu, Yu Cheng

Figure 1 for Hypotheses Tree Building for One-Shot Temporal Sentence Localization
Figure 2 for Hypotheses Tree Building for One-Shot Temporal Sentence Localization
Figure 3 for Hypotheses Tree Building for One-Shot Temporal Sentence Localization
Figure 4 for Hypotheses Tree Building for One-Shot Temporal Sentence Localization
Viaarxiv icon

Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval

Sep 23, 2022
Xiang Fang, Daizong Liu, Pan Zhou, YuChong Hu

Figure 1 for Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval
Figure 2 for Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval
Figure 3 for Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval
Figure 4 for Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval
Viaarxiv icon

Hierarchical Local-Global Transformer for Temporal Sentence Grounding

Aug 31, 2022
Xiang Fang, Daizong Liu, Pan Zhou, Zichuan Xu, Ruixuan Li

Figure 1 for Hierarchical Local-Global Transformer for Temporal Sentence Grounding
Figure 2 for Hierarchical Local-Global Transformer for Temporal Sentence Grounding
Figure 3 for Hierarchical Local-Global Transformer for Temporal Sentence Grounding
Figure 4 for Hierarchical Local-Global Transformer for Temporal Sentence Grounding
Viaarxiv icon

Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding

Mar 06, 2022
Daizong Liu, Xiang Fang, Wei Hu, Pan Zhou

Figure 1 for Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding
Figure 2 for Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding
Figure 3 for Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding
Figure 4 for Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding
Viaarxiv icon

V3H: Incomplete Multi-view Clustering via View Variation and View Heredity

Nov 23, 2020
Xiang Fang, Yuchong Hu, Pan Zhou, Dapeng Oliver Wu

Figure 1 for V3H: Incomplete Multi-view Clustering via View Variation and View Heredity
Figure 2 for V3H: Incomplete Multi-view Clustering via View Variation and View Heredity
Figure 3 for V3H: Incomplete Multi-view Clustering via View Variation and View Heredity
Figure 4 for V3H: Incomplete Multi-view Clustering via View Variation and View Heredity
Viaarxiv icon

Double Self-weighted Multi-view Clustering via Adaptive View Fusion

Nov 20, 2020
Xiang Fang, Yuchong Hu

Figure 1 for Double Self-weighted Multi-view Clustering via Adaptive View Fusion
Figure 2 for Double Self-weighted Multi-view Clustering via Adaptive View Fusion
Figure 3 for Double Self-weighted Multi-view Clustering via Adaptive View Fusion
Figure 4 for Double Self-weighted Multi-view Clustering via Adaptive View Fusion
Viaarxiv icon