Loading from the huggingface remote path is not tested. It is recommended to download this checkpoint to your local environment to prevent potential bugs.

For Retrieval Tasks

python

from utils.video import read_frames_decord
from models.modeling_encoders import AutoEncoder
from torch.nn.functional import cosine_similarity

encoder = AutoEncoder.from_pretrained('path/to/checkpoints/Tarsier-7B-RA')
frames = read_frames_decord(video_path='assets/demo.mp4', num_frames=32)
text = "This video features a man slicing tomatoes in the kitchen."
vision_emb = encoder.encode_vision(frames.unsqueeze(0))
text_emb = encoder.encode_text(text)
print(f'Vision embedding shape: {vision_emb.shape}')
print(f'Text embedding shape: {text_emb.shape}')
print(f'Cosine similarity: {cosine_similarity(vision_emb, text_emb)}')

MCG-NJU/Tarsier-7B-RA

Logo CaReBench: A Fine-grained Benchmark for Video Captioning and Retrieval

📝 Introduction

Usage

For Retrieval Tasks

MCG-NJU/
Tarsier-7B-RA

Logo
CaReBench: A Fine-grained Benchmark for Video Captioning and Retrieval