Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos

• URL: http://arxiv.org/abs/2402.08875v4
• Date: Mon, 15 Jul 2024 21:35:39 GMT
• Title: Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos
• Authors: Yang Qian, Yinan Sun, Ali Kargarandehkordi, Parnian Azizian, Onur Cezmi Mutlu, Saimourya Surabhi, Pingyi Chen, Zain Jabbar, Dennis Paul Wall, Peter Washington,
• Abstract summary: We use 283,582 unique, unlabeled TikTok video clips, categorized into 386 hashtags, to train a domain-specific foundation model for action recognition. Our model achieves state-of-the-art results: 99.05% on UCF101, 86.08% on HMDB51, 85.51% on Kinetics-400, and 74.27% on Something-Something V2 using the ViT-giant backbone.
• Score: 2.3247413495885647
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The increasing variety and quantity of tagged multimedia content on a variety of online platforms offer a unique opportunity to advance the field of human action recognition. In this study, we utilize 283,582 unique, unlabeled TikTok video clips, categorized into 386 hashtags, to train a domain-specific foundation model for action recognition. We employ VideoMAE V2, an advanced model integrating Masked Autoencoders (MAE) with Vision Transformers (ViT), pre-trained on this diverse collection of unstructured videos. Our model, fine-tuned on established action recognition benchmarks such as UCF101 and HMDB51, achieves state-of-the-art results: 99.05% on UCF101, 86.08% on HMDB51, 85.51% on Kinetics-400, and 74.27% on Something-Something V2 using the ViT-giant backbone. These results highlight the potential of using unstructured and unlabeled videos as a valuable source of diverse and dynamic content for training foundation models. Our investigation confirms that while initial increases in pre-training data volume significantly enhance model performance, the gains diminish as the dataset size continues to expand. Our findings emphasize two critical axioms in self-supervised learning for computer vision: (1) additional pre-training data can yield diminishing benefits for some datasets and (2) quality is more important than quantity in self-supervised learning, especially when building foundation models.

Related papers

• Revisiting Feature Prediction for Learning Visual Representations from Video [62.08833572467379]
  V-JEPA is a collection of vision models trained solely using a feature prediction objective. The models are trained on 2 million videos collected from public datasets. Our results show that learning by predicting video features leads to versatile visual representations that perform well on both motion and appearance-based tasks.
  arXiv  Detail & Related papers  (2024-02-15T18:59:11Z)
• ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action Recognition [4.36572039512405]
  We present the first pose augmented Vision-language model (VLM) for Video Action Recognition. Notably, our scheme achieves an accuracy of 92.81% and 73.02% on two popular human video action recognition benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-07T20:50:54Z)
• VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking [57.552798046137646]
  Video masked autoencoder (VideoMAE) is a scalable and general self-supervised pre-trainer for building video foundation models. We successfully train a video ViT model with a billion parameters, which achieves a new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-03-29T14:28:41Z)
• Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models [149.1331903899298]
  We propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge. We present a Temporal Concept Spotting mechanism that uses the Text-to-Video expertise to capture temporal saliency in a parameter-free manner. Our best model achieves a state-of-the-art accuracy of 88.6% on the challenging Kinetics-400 using the released CLIP model.
  arXiv  Detail & Related papers  (2022-12-31T11:36:53Z)
• InternVideo: General Video Foundation Models via Generative and Discriminative Learning [52.69422763715118]
  We present general video foundation models, InternVideo, for dynamic and complex video-level understanding tasks. InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives. InternVideo achieves state-of-the-art performance on 39 video datasets from extensive tasks including video action recognition/detection, video-language alignment, and open-world video applications.
  arXiv  Detail & Related papers  (2022-12-06T18:09:49Z)
• Revisiting Classifier: Transferring Vision-Language Models for Video Recognition [102.93524173258487]
  Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. In this study, we focus on transferring knowledge for video classification tasks. We utilize the well-pretrained language model to generate good semantic target for efficient transferring learning.
  arXiv  Detail & Related papers  (2022-07-04T10:00:47Z)
• Auxiliary Learning for Self-Supervised Video Representation via Similarity-based Knowledge Distillation [2.6519061087638014]
  We propose a novel approach to complement self-supervised pretraining via an auxiliary pretraining phase, based on knowledge similarity distillation, auxSKD. Our method deploys a teacher network that iteratively distils its knowledge to the student model by capturing the similarity information between segments of unlabelled video data. We also introduce a novel pretext task, Video Segment Pace Prediction or VSPP, which requires our model to predict the playback speed of a randomly selected segment of the input video to provide more reliable self-supervised representations.
  arXiv  Detail & Related papers  (2021-12-07T21:50:40Z)
• ViViT: A Video Vision Transformer [75.74690759089529]
  We present pure-transformer based models for video classification. Our model extracts-temporal tokens from the input video, which are then encoded by a series of transformer layers. We show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets.
  arXiv  Detail & Related papers  (2021-03-29T15:27:17Z)
• Creating a Large-scale Synthetic Dataset for Human Activity Recognition [0.8250374560598496]
  We use 3D rendering tools to generate a synthetic dataset of videos, and show that a classifier trained on these videos can generalise to real videos. We fine tune a pre-trained I3D model on our videos, and find that the model is able to achieve a high accuracy of 73% on the HMDB51 dataset over three classes.
  arXiv  Detail & Related papers  (2020-07-21T22:20:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.