Picture for Limin Wang

Limin Wang

Learning Human Skill Generators at Key-Step Levels

Add code
Feb 12, 2025
Viaarxiv icon

InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling

Add code
Jan 21, 2025
Viaarxiv icon

Motion-Aware Generative Frame Interpolation

Add code
Jan 07, 2025
Viaarxiv icon

Fine-grained Video-Text Retrieval: A New Benchmark and Method

Add code
Dec 31, 2024
Viaarxiv icon

Online Video Understanding: A Comprehensive Benchmark and Memory-Augmented Method

Add code
Dec 31, 2024
Figure 1 for Online Video Understanding: A Comprehensive Benchmark and Memory-Augmented Method
Figure 2 for Online Video Understanding: A Comprehensive Benchmark and Memory-Augmented Method
Figure 3 for Online Video Understanding: A Comprehensive Benchmark and Memory-Augmented Method
Figure 4 for Online Video Understanding: A Comprehensive Benchmark and Memory-Augmented Method
Viaarxiv icon

VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

Add code
Dec 31, 2024
Viaarxiv icon

Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model

Add code
Dec 30, 2024
Viaarxiv icon

A Large-Scale Study on Video Action Dataset Condensation

Add code
Dec 30, 2024
Viaarxiv icon

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment

Add code
Dec 26, 2024
Viaarxiv icon

LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

Add code
Dec 19, 2024
Viaarxiv icon