paper-with-me

UCF101

UCF101 Human Actions dataset

홈페이지 · 논문 1,863편

UCF101 dataset is an extension of UCF50 and consists of 13,320 video clips, which are classified into 101 categories. These 101 categories can be classified into 5 types (Body motion, Human-human interactions, Human-object interactions, Playing musical instruments and Sports). The total length of these video clips is over 27 hours. All the videos are collected from YouTube and have a fixed frame rate of 25 FPS with the resolution of 320 × 240. Source: Two-stream Collaborative Learning with Spatial-Temporal Attention for Video Classification Image Source: https://www.crcv.ucf.edu/data/UCF101.php

Videos Korean

벤치마크

Action Recognition on UCF101 결과 186개
Self-Supervised Action Recognition on UCF101 결과 106개
Video Generation on UCF-101 결과 96개
Video Frame Interpolation on UCF101 결과 38개
Zero-Shot Action Recognition on UCF101 결과 35개
Self-Supervised Action Recognition on UCF101 (finetuned) 결과 28개
Action Recognition In Videos on UCF101 결과 15개
Few Shot Action Recognition on UCF101 결과 14개
Prompt Engineering on UCF101 결과 14개
Video Generation on UCF-101 16 frames, 64x64, Unconditional 결과 14개
Video Generation on UCF-101 16 frames, Unconditional, Single GPU 결과 14개
Video Generation on UCF-101 16 frames, 128x128, Unconditional 결과 12개
Text-to-Video Generation on UCF-101 결과 10개
Skeleton Based Action Recognition on UCF101 결과 9개
Action Recognition on UCF-101 결과 6개
Human Activity Recognition on UCF 101 결과 3개
Action Recognition on UCF 101 결과 2개
Few-Shot Learning on UCF101 결과 2개
Image Clustering on UCF101 결과 2개
Open Set Action Recognition on UCF101-MiTv2 결과 2개
Zero-Shot Learning on UCF101 결과 2개
Action Classification on UCF101 결과 1개
Transductive Zero-Shot Classification on UCF101 결과 1개