Picture for Xuwu Wang

Xuwu Wang

Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval

Add code
Apr 01, 2024
Figure 1 for Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval
Figure 2 for Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval
Figure 3 for Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval
Figure 4 for Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval
Viaarxiv icon

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing

Add code
Mar 25, 2024
Viaarxiv icon

OVEL: Large Language Model as Memory Manager for Online Video Entity Linking

Add code
Mar 03, 2024
Figure 1 for OVEL: Large Language Model as Memory Manager for Online Video Entity Linking
Figure 2 for OVEL: Large Language Model as Memory Manager for Online Video Entity Linking
Figure 3 for OVEL: Large Language Model as Memory Manager for Online Video Entity Linking
Figure 4 for OVEL: Large Language Model as Memory Manager for Online Video Entity Linking
Viaarxiv icon

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

Add code
Jan 10, 2024
Viaarxiv icon

WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types

Add code
Apr 13, 2022
Figure 1 for WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types
Figure 2 for WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types
Figure 3 for WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types
Figure 4 for WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types
Viaarxiv icon

Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding

Add code
Mar 29, 2022
Figure 1 for Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding
Figure 2 for Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding
Figure 3 for Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding
Figure 4 for Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding
Viaarxiv icon

Multi-Modal Knowledge Graph Construction and Application: A Survey

Add code
Feb 11, 2022
Figure 1 for Multi-Modal Knowledge Graph Construction and Application: A Survey
Figure 2 for Multi-Modal Knowledge Graph Construction and Application: A Survey
Figure 3 for Multi-Modal Knowledge Graph Construction and Application: A Survey
Figure 4 for Multi-Modal Knowledge Graph Construction and Application: A Survey
Viaarxiv icon

Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks

Add code
Aug 28, 2019
Figure 1 for Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
Figure 2 for Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
Figure 3 for Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
Figure 4 for Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
Viaarxiv icon