Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos

• URL: http://arxiv.org/abs/2104.07905v1
• Date: Fri, 16 Apr 2021 06:10:10 GMT
• Title: Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
• Authors: Yanghao Li, Tushar Nagarajan, Bo Xiong, Kristen Grauman
• Abstract summary: We introduce an approach for pre-training egocentric video models using large-scale third-person video datasets. Our idea is to discover latent signals in third-person video that are predictive of key egocentric-specific properties. Our experiments show that our Ego-Exo framework can be seamlessly integrated into standard video models.
• Score: 92.38049744463149
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce an approach for pre-training egocentric video models using large-scale third-person video datasets. Learning from purely egocentric data is limited by low dataset scale and diversity, while using purely exocentric (third-person) data introduces a large domain mismatch. Our idea is to discover latent signals in third-person video that are predictive of key egocentric-specific properties. Incorporating these signals as knowledge distillation losses during pre-training results in models that benefit from both the scale and diversity of third-person video data, as well as representations that capture salient egocentric properties. Our experiments show that our Ego-Exo framework can be seamlessly integrated into standard video models; it outperforms all baselines when fine-tuned for egocentric activity recognition, achieving state-of-the-art results on Charades-Ego and EPIC-Kitchens-100.

Related papers

• Unlocking Exocentric Video-Language Data for Egocentric Video Representation Learning [80.37314291927889]
  We present EMBED, a method designed to transform exocentric video-language data for egocentric video representation learning. Egocentric videos predominantly feature close-up hand-object interactions, whereas exocentric videos offer a broader perspective on human activities. By applying both vision and language style transfer, our framework creates a new egocentric dataset.
  arXiv  Detail & Related papers  (2024-08-07T06:10:45Z)
• EgoGen: An Egocentric Synthetic Data Generator [53.32942235801499]
  EgoGen is a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks. At the heart of EgoGen is a novel human motion synthesis model that directly leverages egocentric visual inputs of a virtual human to sense the 3D environment. We demonstrate EgoGen's efficacy in three tasks: mapping and localization for head-mounted cameras, egocentric camera tracking, and human mesh recovery from egocentric views.
  arXiv  Detail & Related papers  (2024-01-16T18:55:22Z)
• Retrieval-Augmented Egocentric Video Captioning [53.2951243928289]
  EgoInstructor is a retrieval-augmented multimodal captioning model that automatically retrieves semantically relevant third-person instructional videos. We train the cross-view retrieval module with a novel EgoExoNCE loss that pulls egocentric and exocentric video features closer by aligning them to shared text features that describe similar actions.
  arXiv  Detail & Related papers  (2024-01-01T15:31:06Z)
• Ego-Body Pose Estimation via Ego-Head Pose Estimation [22.08240141115053]
  Estimating 3D human motion from an egocentric video sequence plays a critical role in human behavior understanding and has various applications in VR/AR. We propose a new method, Ego-Body Pose Estimation via Ego-Head Pose Estimation (EgoEgo), which decomposes the problem into two stages, connected by the head motion as an intermediate representation. This disentanglement of head and body pose eliminates the need for training datasets with paired egocentric videos and 3D human motion.
  arXiv  Detail & Related papers  (2022-12-09T02:25:20Z)
• Egocentric Video-Language Pretraining [74.04740069230692]
  Video-Language Pretraining aims to learn transferable representation to advance a wide range of video-text downstream tasks. We exploit the recently released Ego4D dataset to pioneer Egocentric training along three directions. We demonstrate strong performance on five egocentric downstream tasks across three datasets.
  arXiv  Detail & Related papers  (2022-06-03T16:28:58Z)
• Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision [72.36132924512299]
  We present a new egocentric pose estimation method, which can be trained on a large-scale in-the-wild egocentric dataset. We propose a novel learning strategy to supervise the egocentric features with the high-quality features extracted by a pretrained external-view pose estimation model. Experiments show that our method predicts accurate 3D poses from a single in-the-wild egocentric image and outperforms the state-of-the-art methods both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2022-01-20T00:45:13Z)
• Enhancing Egocentric 3D Pose Estimation with Third Person Views [37.9683439632693]
  We propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera. We introduce First2Third-Pose, a new paired synchronized dataset of nearly 2,000 videos depicting human activities captured from both first- and third-view perspectives. Experimental results demonstrate that the joint multi-view embedded space learned with our dataset is useful to extract discriminatory features from arbitrary single-view egocentric videos.
  arXiv  Detail & Related papers  (2022-01-06T11:42:01Z)

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.