EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?

• URL: http://arxiv.org/abs/2405.17719v2
• Date: Mon, 3 Jun 2024 07:29:18 GMT
• Title: EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?
• Authors: Boshen Xu, Ziheng Wang, Yang Du, Zhinan Song, Sipeng Zheng, Qin Jin,
• Abstract summary: We introduce a novel asymmetric contrastive objective for EgoHOI named EgoNCE++. Our experiments demonstrate that EgoNCE++ significantly boosts open-vocabulary HOI recognition, multi-instance retrieval, and action recognition tasks.
• Score: 48.702973928321946
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Egocentric video-language pretraining is a crucial paradigm to advance the learning of egocentric hand-object interactions (EgoHOI). Despite the great success on existing testbeds, these benchmarks focus more on closed-set visual concepts or limited scenarios. Due to the occurrence of diverse EgoHOIs in the real world, we propose an open-vocabulary benchmark named EgoHOIBench to reveal the diminished performance of current egocentric video-language models (EgoVLM) on fined-grained concepts, indicating that these models still lack a full spectrum of egocentric understanding. We attribute this performance gap to insufficient fine-grained supervision and strong bias towards understanding objects rather than temporal dynamics in current methods. To tackle these issues, we introduce a novel asymmetric contrastive objective for EgoHOI named EgoNCE++. For video-to-text loss, we enhance text supervision through the generation of negative captions by leveraging the in-context learning of large language models to perform HOI-related word substitution. For text-to-video loss, we propose an object-centric positive video sampling strategy that aggregates video representations by the same nouns. Our extensive experiments demonstrate that EgoNCE++ significantly boosts open-vocabulary HOI recognition, multi-instance retrieval, and action recognition tasks across various egocentric models, with improvements of up to +26.55%. Our code is available at https://github.com/xuboshen/EgoNCEpp.

Related papers

• EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding [27.881857222850083]
  EgoExo-Fitness is a new full-body action understanding dataset. It features fitness sequence videos recorded from synchronized egocentric and fixed exocentric cameras. EgoExo-Fitness provides new resources to study egocentric and exocentric full-body action understanding.
  arXiv  Detail & Related papers  (2024-06-13T07:28:45Z)
• Object Aware Egocentric Online Action Detection [23.504280692701272]
  We introduce an Object-Aware Module that integrates egocentric-specific priors into existing Online Action Detection frameworks. Our work can be seamlessly integrated into existing models with minimal overhead and bring consistent performance enhancements.
  arXiv  Detail & Related papers  (2024-06-03T07:58:40Z)
• 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)
• Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos [27.209391862016574]
  We propose a novel benchmark for cross-view knowledge transfer of dense video captioning. We adapt models from web instructional videos with exocentric views to an egocentric view.
  arXiv  Detail & Related papers  (2023-11-28T02:51:13Z)
• 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)
• 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)
• 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)
• Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries [51.48859591280838]
  We present EgoACO, a deep neural architecture for video action recognition. It learns to pool action-context-object descriptors from frame level features. Cap uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions.
  arXiv  Detail & Related papers  (2021-02-16T10:26:04Z)

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.