Picture for Jiajun Liang

Jiajun Liang

Solution of Multiview Egocentric Hand Tracking Challenge ECCV2024

Add code
Sep 28, 2024
Viaarxiv icon

Cascade Prompt Learning for Vision-Language Model Adaptation

Add code
Sep 26, 2024
Figure 1 for Cascade Prompt Learning for Vision-Language Model Adaptation
Figure 2 for Cascade Prompt Learning for Vision-Language Model Adaptation
Figure 3 for Cascade Prompt Learning for Vision-Language Model Adaptation
Figure 4 for Cascade Prompt Learning for Vision-Language Model Adaptation
Viaarxiv icon

Revisiting Prompt Pretraining of Vision-Language Models

Add code
Sep 10, 2024
Viaarxiv icon

MegActor-$Σ$: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer

Add code
Aug 27, 2024
Viaarxiv icon

Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory

Add code
Jul 09, 2024
Viaarxiv icon

MegActor: Harness the Power of Raw Video for Vivid Portrait Animation

Add code
May 31, 2024
Viaarxiv icon

Towards RGB-NIR Cross-modality Image Registration and Beyond

Add code
May 30, 2024
Viaarxiv icon

MCSDNet: Mesoscale Convective System Detection Network via Multi-scale Spatiotemporal Information

Add code
Apr 26, 2024
Viaarxiv icon

Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects

Add code
Mar 25, 2024
Viaarxiv icon

A Simple Baseline for Efficient Hand Mesh Reconstruction

Add code
Mar 04, 2024
Viaarxiv icon