TransAction: ICL-SJTU Submission to EPIC-Kitchens Action Anticipation Challenge 2021

• URL: http://arxiv.org/abs/2107.13259v1
• Date: Wed, 28 Jul 2021 10:42:47 GMT
• Title: TransAction: ICL-SJTU Submission to EPIC-Kitchens Action Anticipation Challenge 2021
• Authors: Xiao Gu, Jianing Qiu, Yao Guo, Benny Lo, Guang-Zhong Yang
• Abstract summary: We developed a hierarchical attention model for action anticipation. In terms of Mean Top-5 Recall of action, our submission with team name ICL-SJTU achieved 13.39%. It is noteworthy that our submission ranked 1st in terms of verb class in all three (sub)sets.
• Score: 42.35018041385645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this report, the technical details of our submission to the EPIC-Kitchens Action Anticipation Challenge 2021 are given. We developed a hierarchical attention model for action anticipation, which leverages Transformer-based attention mechanism to aggregate features across temporal dimension, modalities, symbiotic branches respectively. In terms of Mean Top-5 Recall of action, our submission with team name ICL-SJTU achieved 13.39% for overall testing set, 10.05% for unseen subsets and 11.88% for tailed subsets. Additionally, it is noteworthy that our submission ranked 1st in terms of verb class in all three (sub)sets.

Related papers

• Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks [89.1896982106731]
  We present a novel pipeline for creating contextual descriptions of human body poses in images using only auxiliary attributes. We demonstrate the effectiveness of our pose descriptions in enabling zero-shot human-centric classification using CLIP. Our models were pretrained on the MPII Pose Descriptions dataset and their zero-shot performance was evaluated on five unseen datasets.
  arXiv  Detail & Related papers  (2024-03-11T16:56:37Z)
• The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT [50.41526598153698]
  This paper presents the challenge report for the 2021 Kidney and Kidney Tumor Challenge (KiTS21) KiTS21 is a sequel to its first edition in 2019, and it features a variety of innovations in how the challenge was designed. The top-performing teams achieved a significant improvement over the state of the art set in 2019, and this performance is shown to inch ever closer to human-level performance.
  arXiv  Detail & Related papers  (2023-07-05T02:00:14Z)
• Predicting the Next Action by Modeling the Abstract Goal [18.873728614415946]
  We present an action anticipation model that leverages goal information for the purpose of reducing the uncertainty in future predictions. We derive a novel concept called abstract goal which is conditioned on observed sequences of visual features for action anticipation. Our method obtains impressive results on the very challenging Epic-Kitchens55 (EK55), EK100, and EGTEA Gaze+ datasets.
  arXiv  Detail & Related papers  (2022-09-12T06:52:42Z)
• NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022 [13.603712913129506]
  We describe the technical details of our submission for the EPIC-Kitchen-100 action anticipation challenge. Our modelings, the higher-order recurrent space-time transformer and the message-passing neural network with edge learning, are both recurrent-based architectures which observe only 2.5 seconds inference context to form the action anticipation prediction. By averaging the prediction scores from a set of models compiled with our proposed training pipeline, we achieved strong performance on the test set, which is 19.61% overall mean top-5 recall, recorded as second place on the public leaderboard.
  arXiv  Detail & Related papers  (2022-06-22T06:34:58Z)
• SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021 [80.05652375838073]
  This report presents the technical details of our submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021. Our submission, visible on the public leaderboard, achieved a top-1 action recognition accuracy of 44.82%, using only RGB.
  arXiv  Detail & Related papers  (2021-10-06T16:29:47Z)
• Team PyKale (xy9) Submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition [12.905251261775405]
  This report describes the technical details of our submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition. The EPIC-Kitchens dataset is more difficult than other video domain adaptation datasets due to multi-tasks with more modalities. Under the team name xy9, our submission achieved 5th place in terms of top-1 accuracy for verb class and all top-5 accuracies.
  arXiv  Detail & Related papers  (2021-06-22T19:17:03Z)
• Anticipative Video Transformer [105.20878510342551]
  Anticipative Video Transformer (AVT) is an end-to-end attention-based video modeling architecture. We train the model jointly to predict the next action in a video sequence, while also learning frame feature encoders that are predictive of successive future frames' features.
  arXiv  Detail & Related papers  (2021-06-03T17:57:55Z)
• FBK-HUPBA Submission to the EPIC-Kitchens Action Recognition 2020 Challenge [43.8525418821458]
  We describe the technical details of our submission to the EPIC-Kitchens Action Recognition 2020 Challenge. Our submission achieved top Ego-1 action recognition accuracy of 40.0% on S1 setting, and 21% on S2 setting, using only RGB.
  arXiv  Detail & Related papers  (2020-06-24T13:41:17Z)

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.