Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022

• URL: http://arxiv.org/abs/2301.12436v1
• Date: Sun, 29 Jan 2023 12:29:24 GMT
• Title: Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022
• Authors: Yi Cheng, Dongyun Lin, Fen Fang, Hao Xuan Woon, Qianli Xu, Ying Sun
• Abstract summary: We present our submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022. This task aims to adapt an action recognition model trained on a labeled source domain to an unlabeled target domain. Our final submission achieved the first place in terms of top-1 action recognition accuracy.
• Score: 6.561596502471905
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this report, we present the technical details of our submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition 2022. This task aims to adapt an action recognition model trained on a labeled source domain to an unlabeled target domain. To achieve this goal, we propose an action-aware domain adaptation framework that leverages the prior knowledge induced from the action recognition task during the adaptation. Specifically, we disentangle the source features into action-relevant features and action-irrelevant features using the learned action classifier and then align the target features with the action-relevant features. To further improve the action prediction performance, we exploit the verb-noun co-occurrence matrix to constrain and refine the action predictions. Our final submission achieved the first place in terms of top-1 action recognition accuracy.

Related papers

• Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge [62.981429762309226]
  The ability to actively ground task instructions from an egocentric view is crucial for AI agents to accomplish tasks or assist humans virtually. We propose to improve phrase grounding models' ability on localizing the active objects by: learning the role of objects undergoing change and extracting them accurately from the instructions. We evaluate our framework on Ego4D and Epic-Kitchens datasets.
  arXiv  Detail & Related papers  (2023-10-23T16:14:05Z)
• EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge: Mixed Sequences Prediction [16.92053939360415]
  This report presents the technical details of our approach for the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition. Our approach is based on the idea that the order in which actions are performed is similar between the source and target domains. We generate a modified sequence by randomly combining actions from the source and target domains.
  arXiv  Detail & Related papers  (2023-07-24T14:35:46Z)
• A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023 [23.323548254515494]
  We present our findings from a study conducted on the EPIC-KITCHENS-100 Unsupervised Domain Adaptation task for Action Recognition. Our research focuses on the innovative application of a differentiable logic loss in the training to leverage the co-occurrence relations between verb and noun. Our final submission (entitled NS-LLM') achieved the first place in terms of top-1 action recognition accuracy.
  arXiv  Detail & Related papers  (2023-07-13T05:54:05Z)
• Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task [50.72283841720014]
  We propose a novel learning strategy that can improve reasoning about the effects of actions. We demonstrate the effectiveness of our proposed approach and discuss its advantages over previous baselines in terms of performance, data efficiency, and generalization capability.
  arXiv  Detail & Related papers  (2022-12-07T05:41:58Z)
• Transformer-based Action recognition in hand-object interacting scenarios [6.679721418508601]
  This report describes the 2nd place solution to the ECCV 2022 Human Body, Hands, and Activities (HBHA) from Egocentric and Multi-view Cameras Challenge: Action Recognition. We propose a framework that estimates keypoints of two hands and an object with a Transformer-based keypoint estimator and recognizes actions based on the estimated keypoints.
  arXiv  Detail & Related papers  (2022-10-20T16:27:37Z)
• Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021 [6.614021153407064]
  The EPIC-KITCHENS-100 dataset consists of daily kitchen activities focusing on the interaction between human hands and their surrounding objects. It is very challenging to accurately recognize these fine-grained activities, due to the presence of distracting objects and visually similar action classes. We propose to learn hand-centric features by leveraging the hand bounding box information for UDA on fine-grained action recognition. Our submission achieved the 1st place in terms of top-1 action recognition accuracy, using only RGB and optical flow modalities as input.
  arXiv  Detail & Related papers  (2022-06-03T07:37:48Z)
• Labeling Where Adapting Fails: Cross-Domain Semantic Segmentation with Point Supervision via Active Selection [81.703478548177]
  Training models dedicated to semantic segmentation require a large amount of pixel-wise annotated data. Unsupervised domain adaptation approaches aim at aligning the feature distributions between the labeled source and the unlabeled target data. Previous works attempted to include human interactions in this process under the form of sparse single-pixel annotations in the target data. We propose a new domain adaptation framework for semantic segmentation with annotated points via active selection.
  arXiv  Detail & Related papers  (2022-06-01T01:52:28Z)
• Audio-Adaptive Activity Recognition Across Video Domains [112.46638682143065]
  We leverage activity sounds for domain adaptation as they have less variance across domains and can reliably indicate which activities are not happening. We propose an audio-adaptive encoder and associated learning methods that discriminatively adjust the visual feature representation. We also introduce the new task of actor shift, with a corresponding audio-visual dataset, to challenge our method with situations where the activity appearance changes dramatically.
  arXiv  Detail & Related papers  (2022-03-27T08:15:20Z)
• PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition [15.545769463854915]
  This report describes our submission to the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition. We first exploited a recent Domain Generalization (DG) technique, called Relative Norm Alignment (RNA) In a second phase, we extended the approach to work on unlabelled target data, allowing the model to adapt to the target distribution in an unsupervised fashion. Our submission (entry 'plnet') is visible on the leaderboard and it achieved the 1st position for'verb', and the 3rd position for both 'noun' and 'action'
  arXiv  Detail & Related papers  (2021-07-01T10:02:44Z)
• ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation [84.90801699807426]
  We study what features should be aligned across domains and propose to make the domain alignment proactively serve classification. We explicitly decompose a feature in the source domain intoa task-related/discriminative feature that should be aligned, and a task-irrelevant feature that should be avoided/ignored.
  arXiv  Detail & Related papers  (2021-06-21T02:17:48Z)
• Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers [138.68213707587822]
  We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. We show that we can achieve this goal by compensating for the difference in dynamics by modifying the reward function. Our approach is applicable to domains with continuous states and actions and does not require learning an explicit model of the dynamics.
  arXiv  Detail & Related papers  (2020-06-24T17:47:37Z)

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.