LMTrajectory
LMTrajectory copied to clipboard
InhwanBae
Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)"
Hi, thank you for the work you have done, very nice! When will the code for the release be ready? Thank you, Alessio
Hello, your work has been of great help to me. I was wondering if it would be possible for you to share the code, configuration, or pretrained weights for the...
Hi, I am trying to run ChatGPT 4.0 for zero-shot trajectory prediction. However, I found that using gpt-4-0314 requires unreasonable running hours and costs. May I ask what your consumption...
Hello, Thank you for the great work! What is the meaning of setting top_k to 0, and why set it to 0, in the config files when conducting stochastic trajectory...
Hi, Thank you for your work and code. The following problem occurred while I was executing: './zero-shot/chatgpt_sequential_v3.sh: line 25: python3: command not found' Why did this error occur? Is it...
Thanks for your work! I wonder if there are models pretrained for ETH-UCY in meter coordinates,cuz the models released online are in the name of xxx-pixel-multimodal-xxxx,or these can be also...
Hello, thank you for your work! I have few questions about your work. 1. The BLIP-2 model is used to create captions of images to be used as prompts for...
Thanks for your work. I want to know if the zero-shot results on ETH/UCY are all calculated by multimodal predictions? If predictions are all multimodal, is the K equal to...
Hello @InhwanBae, Thank you for your work and research. I’ve been trying to reproduce the results from the paper, especially since `gpt-4-0314` is no longer accessible via the API. I’d...
Hello @InhwanBae I am currently exploring zero-shot prediction and went through the evaluation section of the zero-shot approach. I noticed that you have a visualization of prediction results for zero-shot...