visual-features 开源项目推荐（8 个）

v-iashin /video_features

Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.

naver /kapture

kapture 是一种文件格式，也是一组用于处理数据集的工具，尤其适用于视觉定位和运动恢复结构数据。

multimodal /multimodal

A collection of multimodal datasets, and visual features for VQA and captionning in pytorch. Just run "pip install multimodal"

gcunhase /Emotional-Video-to-Audio-with-ANFIS-DeepRNN

Emotional Video to Audio Transformation with ANFIS-DeepRNN (Vanilla RNN and LSTM-DeepRNN) [MPE 2020]

michelecafagna26 /vinvl-visualbackbone

Original VinVL visual backbone with simplified APIs to easily extract features, boxes, object detections, in a few lines of Python code.

cuixing158 /Visual-Based-Odometry-Estimation1-cpp

Stitching and fusion of on-board surround view BEV real world image sequences, odometer estimation and output of large pixel map

cuixing158 /Visual-Based-Odometry-Estimation-cpp

Stitching and fusion of on-board surround view BEV real world image sequences, odometer estimation and output of large pixel map

ritika-0111 /Amazon-Apparel-Recommendations

Recommends Apparel based on Text, Visual features, and weighted similarity using brand and color similarity.