Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding

• URL: http://arxiv.org/abs/2503.09143v1
• Date: Wed, 12 Mar 2025 08:10:33 GMT
• Title: Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding
• Authors: Haoyu Zhang, Qiaohui Chu, Meng Liu, Yunxiao Wang, Bin Wen, Fan Yang, Tingting Gao, Di Zhang, Yaowei Wang, Liqiang Nie,
• Abstract summary: Current MLLMs primarily focus on third-person (exocentric) vision, overlooking the unique aspects of first-person (egocentric) videos.<n>We propose learning the mapping between exocentric and egocentric domains to enhance egocentric video understanding.<n>We introduce Ego-ExoClip, a pre-training dataset comprising 1.1M synchronized ego-exo clip-text pairs.
• Score: 69.96199605596138
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI personal assistants, deployed through robots or wearables, require embodied understanding to collaborate effectively with humans. Current Multimodal Large Language Models (MLLMs) primarily focus on third-person (exocentric) vision, overlooking the unique aspects of first-person (egocentric) videos. Additionally, high acquisition costs limit data size, impairing MLLM performance. To address these challenges, we propose learning the mapping between exocentric and egocentric domains, leveraging the extensive exocentric knowledge within existing MLLMs to enhance egocentric video understanding. To this end, we introduce Ego-ExoClip, a pre-training dataset comprising 1.1M synchronized ego-exo clip-text pairs derived from Ego-Exo4D. Our approach features a progressive training pipeline with three stages: Teacher Self-Preparation, Teacher-Student Guidance, and Student Self-Practice. Additionally, we propose an instruction-tuning data EgoIT from multiple sources to strengthen the model's instruction-following capabilities, along with the EgoBench benchmark comprising eight different tasks for thorough evaluation. Extensive experiments across diverse egocentric tasks reveal that existing MLLMs perform inadequately in egocentric video understanding, while our model significantly outperforms these leading models.

Related papers

• From My View to Yours: Ego-Augmented Learning in Large Vision Language Models for Understanding Exocentric Daily Living Activities [7.057604866667723]
  We propose an online ego2exo distillation approach to learn ego-augmented exo representations in LVLMs.<n>While effective, this approach requires paired ego-exo training data, which is impractical to collect for real-world ADL scenarios.<n>We develop EgoMimic, a skeleton-guided method that can generate mimicked ego views from exocentric videos.
  arXiv  Detail & Related papers  (2025-01-10T05:01:58Z)
• VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI [17.763461523794806]
  VidEgoThink is a benchmark for evaluating egocentric video understanding capabilities in Embodied AI. We design four key interrelated tasks: video question-answering, hierarchy planning, visual grounding and reward modeling. We conduct extensive experiments with three types of models: API-based MLLMs, open-source image-based MLLMs, and open-source video-based MLLMs.
  arXiv  Detail & Related papers  (2024-10-15T14:08:53Z)
• MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA [72.47344411599322]
  This research aims to explore building a multimodal foundation model for egocentric video understanding. We automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data. We contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memorizing visual details across videos of varying lengths.
  arXiv  Detail & Related papers  (2024-10-09T17:59:59Z)
• 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)
• EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World [44.34800426136217]
  We introduce EgoExoLearn, a dataset that emulates the human demonstration following process. EgoExoLearn contains egocentric and demonstration video data spanning 120 hours. We present benchmarks such as cross-view association, cross-view action planning, and cross-view referenced skill assessment.
  arXiv  Detail & Related papers  (2024-03-24T15:00:44Z)
• 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)
• EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding [90.9111678470214]
  We propose EgoDistill, a distillation-based approach that learns to reconstruct heavy egocentric video clip features. Our method leads to significant improvements in efficiency, requiring 200x fewer GFLOPs than equivalent video models. We demonstrate its effectiveness on the Ego4D and EPICKitchens datasets, where our method outperforms state-of-the-art efficient video understanding methods.
  arXiv  Detail & Related papers  (2023-01-05T18:39:23Z)
• Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos [92.38049744463149]
  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.
  arXiv  Detail & Related papers  (2021-04-16T06:10:10Z)

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.