Truyen Tran

papers

473

total citations

papers (12)

Hierarchical Conditional Relation Networks for Video Question Answering

CVPR 2020arXiv

285

citations

Clustering by Maximizing Mutual Information Across Views

ICCV 2021arXiv

citations

Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation

NEURIPS 2022arXiv

citations

Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models

AAAI 2025arXiv

citations

Persistent-Transient Duality: A Multi-Mechanism Approach for Modeling Human-Object Interaction

ICCV 2023arXiv

citations

Functional Indirection Neural Estimator for Better Out-of-distribution Generalization

NEURIPS 2022arXiv

citations

Learning Structural Causal Models from Ordering: Identifiable Flow Models

AAAI 2025arXiv

citations

Truyen Tran

papers (12)

Hierarchical Conditional Relation Networks for Video Question Answering

Clustering by Maximizing Mutual Information Across Views

Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation

Learning Asynchronous and Sparse Human-Object Interaction in Videos

Model-Based Episodic Memory Induces Dynamic Hybrid Controls

Video Dialog As Conversation about Objects Living in Space-Time

Towards Effective and Robust Neural Trojan Defenses via Input Filtering

Root Cause Explanation of Outliers under Noisy Mechanisms

Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models

Persistent-Transient Duality: A Multi-Mechanism Approach for Modeling Human-Object Interaction

Functional Indirection Neural Estimator for Better Out-of-distribution Generalization

Learning Structural Causal Models from Ordering: Identifiable Flow Models

papers (12)

Hierarchical Conditional Relation Networks for Video Question Answering

Clustering by Maximizing Mutual Information Across Views

Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation

Learning Asynchronous and Sparse Human-Object Interaction in Videos

Model-Based Episodic Memory Induces Dynamic Hybrid Controls

Video Dialog As Conversation about Objects Living in Space-Time

Towards Effective and Robust Neural Trojan Defenses via Input Filtering

Root Cause Explanation of Outliers under Noisy Mechanisms

Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models

Persistent-Transient Duality: A Multi-Mechanism Approach for Modeling Human-Object Interaction

Functional Indirection Neural Estimator for Better Out-of-distribution Generalization

Learning Structural Causal Models from Ordering: Identifiable Flow Models