Heng Tao Shen

17

Papers

87

Total Citations

Papers (17)

DePT: Decoupled Prompt Tuning

ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models

TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident

PHGC: Procedural Heterogeneous Graph Completion for Natural Language Task Verification in Egocentric Videos

CDTR: Semantic Alignment for Video Moment Retrieval Using Concept Decomposition Transformer

T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Large Language Model Signals for Science Question Answering

Weakly-Supervised Mirror Detection via Scribble Annotations

Adaptive Uncertainty-Based Learning for Text-Based Person Retrieval

ScanERU: Interactive 3D Visual Grounding Based on Embodied Reference Understanding

Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves

Ensemble Diversity Facilitates Adversarial Transferability

Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather

CoSMIC: Continual Self-supervised Learning for Multi-Domain Medical Imaging via Conditional Mutual Information Maximization

Implicit Counterfactual Learning for Audio-Visual Segmentation

Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy