Zechao Li

CDTP: A Large-Scale Chinese Data-Text Pair Dataset for Comprehensive Evaluation of Chinese LLMs

Zero-shot HOI Detection with MLLM-based Detector-agnostic Interaction Recognition

A Fine-Grained Approach to Explaining Catastrophic Forgetting of Interactions in Class-Incremental Learning

Textual and Temporal-Guided Feature Decoupling for Video Temporal Grounding

Dense and Indiscernible Object Counting in Agricultural Scenes

Evoking Generalized Cognition for Exemplar Free Continual Learning via Granular Ball Representation

Robust Semantic Sample Filtering for Partially View-aligned Clustering

See the Text: From Tokenization to Visual Reading

EGH-Net: Energy-Guided Hypergraph for Two-View Correspondence Learning

Revitalizing SVD for Global Covariance Pooling: Halley’s Method to Overcome Over-Flattening

Refining Norms: A Post-hoc Framework for OOD Detection in Graph Neural Networks

CSGO: Content-Style Composition in Text-to-Image Generation

FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts

Improving Multi-modal Large Language Model through Boosting Vision Capabilities

CSGO: Content-Style Composition in Text-to-Image Generation

Why pre-training is beneficial for downstream classification tasks?