Picture for Tianshui Chen

Tianshui Chen

Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior

Add code
Jun 02, 2024
Viaarxiv icon

Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition

Add code
Jan 20, 2024
Viaarxiv icon

Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation

Add code
Dec 18, 2023
Viaarxiv icon

MotionCtrl: A Unified and Flexible Motion Controller for Video Generation

Add code
Dec 06, 2023
Viaarxiv icon

SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting

Add code
Nov 16, 2023
Figure 1 for SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting
Figure 2 for SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting
Figure 3 for SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting
Figure 4 for SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting
Viaarxiv icon

Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search

Add code
Nov 15, 2023
Viaarxiv icon

Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation

Add code
Sep 23, 2023
Figure 1 for Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation
Figure 2 for Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation
Figure 3 for Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation
Figure 4 for Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation
Viaarxiv icon

Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs

Sep 04, 2023
Figure 1 for Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
Figure 2 for Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
Figure 3 for Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
Figure 4 for Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
Viaarxiv icon

RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs

Add code
Aug 14, 2023
Figure 1 for RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs
Figure 2 for RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs
Figure 3 for RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs
Figure 4 for RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs
Viaarxiv icon

Perception and Semantic Aware Regularization for Sequential Confidence Calibration

Add code
May 31, 2023
Figure 1 for Perception and Semantic Aware Regularization for Sequential Confidence Calibration
Figure 2 for Perception and Semantic Aware Regularization for Sequential Confidence Calibration
Figure 3 for Perception and Semantic Aware Regularization for Sequential Confidence Calibration
Figure 4 for Perception and Semantic Aware Regularization for Sequential Confidence Calibration
Viaarxiv icon