UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
By K. Soomro, Amir Zamir, Mubarak Shah. 2012
7,255 citations recorded by the source corpus.
We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data. The database consists of realistic user uploaded videos containing camera motion and cluttered background. Additionally, we provide baseline action recognition results on this new dataset using standard bag of words approach with overall performance of 44.5%. To the best of our knowledge, UCF101 is currently the most challenging dataset of actions due to its large number of classes, large number of clips and also unconstrained nature of such clips.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Jianfeng Gao
- Trevor Darrell
- Yoshua Bengio
- Dacheng Tao
- Quoc V. Le
- Sergey Levine
- Percy Liang
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Trevor Darrell
- Xiaogang Wang
- Jitendra Malik
- Andrew Zisserman
- Cordelia Schmid
In Evaluation & Benchmarks
- Jitendra Malik
- Andrew Zisserman
- Cordelia Schmid
- Trevor Darrell
- Abhinav Kumar Gupta
- Li Fei-Fei
- Antonio Torralba
- Kristen Grauman
Citations in the corpus
- Learning Transferable Visual Models From Natural Language Supervision (2021, background): “…(Stallkamp et al., 2011), the KITTI dataset (Geiger et al., 2012), PatchCamelyon (Veeling et al., 2018), the UCF101 action recognition dataset (Soomro et al., 2012), Kinetics 700 (Carreira et al., 2019), 2,500 random samples of the CLEVR dataset (Johnson et al., 2017), the Hateful Memes…”
- A Constructive Prediction of the Generalization Error Across Scales (2019, methodology): “UCF101 (Soomro et al., 2012): originally a video action recognition dataset, converted using the method of Bilen et al.”
- Late Temporal Modeling in 3D CNN Architectures with BERT for Action Recognition (2020, methodology): “Four datasets are relevant for our study: HMDB51 [16], UCF101 [25], Kinetics400 [1] and IG65M [9] datasets.”
- Self-Supervised MultiModal Versatile Networks (2020, methodology): “Some classification datasets have official splits (3 for UCF101/HMDB51 and 5 for ESC-50).”
- End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, positive): “In Table 3, we evaluate our learnt representations on the HMDB-51 [45] and UCF101 [69] action recognition benchmarks by extracting averaged pooled Mixed 5c features from the HowTo100M pretrained backbone.”
- Contrastive Multiview Coding (2019, methodology): “We follow the same spirit and evaluate the transferability of our RGB CaffeNet on UCF101 and HMDB51 datasets.”
- VideoGPT: Video Generation using VQ-VAE and Transformers (2021, neutral): “In addition, VideoGPT is able to generate realistic samples from complex natural video datasets, such as UCF-101 and the Tumblr GIF dataset 3.”
- Generating Videos with Scene Dynamics (2016, methodology): “Figure 4: Video Representation Learning: We evaluate the representation learned by the discriminator for action classification on UCF101 [36].”
- Deep multi-scale video prediction beyond mean square error (2015, methodology): “Generative adversarial networks were introduced by Goodfellow et al. (2014), where images patches are generated from random noise using two networks trained simultaneously.”
- Learning to Prompt for Vision-Language Models (2021, background): “For generic objects (ImageNet & Caltech101), scenes (SUN397) and actions (UCF101), using unified context is clearly better.”
- VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research (2019, methodology): “[28] first built an action list by combining previous video datasets [24, 31, 53, 3, 62], and then searched the videos from YouTube for candidates, which eventually were filtered by Amazon Mechanical Turkers.”
- Long-term recurrent convolutional networks for visual recognition and description (2014, methodology): “[33] report the results on UCF-101 by computing a weighted average between flow and RGB networks (86.4% for split 1 and 87.6% averaging over all splits).”
- ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models (2022, background): “Visual recognition has become ubiquitous in our society [60], with applications in geolocalization [51], action recognition [57], street number transcription [44], satellite remote sensing [22], medical imaging [62], self-driving cars [19], etc.”
- Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “Existing collections like Kinetics [108], AVA [92], UCF [207], Ac-tivityNet [61], HowTo100M [157], ImageNet [49], and COCO [143] focus on third-person Web data, which have the benefit and bias of a human photographer.”
- Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100 (2020, background): “Several datasets have been collected to focus on action recognition, from [52,53] to recent large-scale ones [5,41,43,44,45,46], all offering a challenge with a held-out test set.”