UCF101

UCF101 Human Actions dataset

Dataset Information
Modalities
Videos
Languages
Korean
Introduced
2012
License
MIT
Homepage
Official Website
Contents

Overview

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

Variants: UCF101-skeleton, UCF101-MiTv2, UCF-101 Zero-shot, 256x256, class-conditional, UCF101 (finetuned), UCF 101, UCF101, UCF-101 16 frames, Unconditional, Single GPU, UCF-101 16 frames, 64x64, Unconditional, UCF-101 16 frames, 128x128, Unconditional, UCF-101

Associated Benchmarks

This dataset is used in 8 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Prompt Engineering MMRL++ MMRL++: Parameter-Efficient and Interaction-Aware Representation … 2025-05-15
Action Recognition CA2ST(B/16) CA^2ST: Cross-Attention in Audio, Space, … 2025-03-30
Prompt Engineering MMRL MMRL: Multi-Modal Representation Learning for … 2025-03-11
Prompt Engineering HPT++ HPT++: Hierarchically Prompting Vision-Language Models … 2024-08-27
Video Frame Interpolation VFIMamba VFIMamba: Video Frame Interpolation with … 2024-07-02
Image Clustering TURTLE (CLIP + DINOv2) Let Go of Your Labels … 2024-06-11
Zero-Shot Action Recognition TC-CLIP Leveraging Temporal Contextualization for Video … 2024-04-15
Zero-Shot Learning ZLaP* Label Propagation for Zero-shot Classification … 2024-04-05
Zero-Shot Learning ZLaP Label Propagation for Zero-shot Classification … 2024-04-05
Prompt Engineering ProMetaR Prompt Learning via Meta-Regularization 2024-04-01
Action Recognition FTP-UniFormerV2-L/14 Enhancing Video Transformers for Action … 2024-03-24
Prompt Engineering PromptKD PromptKD: Unsupervised Prompt Distillation for … 2024-03-05
Zero-Shot Action Recognition EZ-CLIP EZ-CLIP: Efficient Zeroshot Video Action … 2023-12-13
Prompt Engineering HPT Learning Hierarchical Prompt with Structured … 2023-12-11
Zero-Shot Action Recognition OST OST: Refining Text Knowledge with … 2023-11-30
Action Recognition OmniVec OmniVec: Learning robust representations with … 2023-11-07
Action Recognition AMD(ViT-B/16) Asymmetric Masked Distillation for Pre-Training … 2023-11-06
Image Clustering TAC Image Clustering with External Guidance 2023-10-18
Action Recognition ZeroI2V ViT-L/14 ZeroI2V: Zero-Cost Adaptation of Pre-trained … 2023-10-02
Prompt Engineering DePT DePT: Decoupled Prompt Tuning 2023-09-14

Research Papers

Recent papers with results on this dataset:

External Links: