Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

NMS Threshold matters for Ego4D Moment Queries -- 2nd place solution to the Ego4D Moment Queries Challenge 2023 (2307.02025v1)

Published 5 Jul 2023 in cs.CV

Abstract: This report describes our submission to the Ego4D Moment Queries Challenge 2023. Our submission extends ActionFormer, a latest method for temporal action localization. Our extension combines an improved ground-truth assignment strategy during training and a refined version of SoftNMS at inference time. Our solution is ranked 2nd on the public leaderboard with 26.62% average mAP and 45.69% Recall@1x at tIoU=0.5 on the test set, significantly outperforming the strong baseline from 2023 challenge. Our code is available at https://github.com/happyharrycn/actionformer_release.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (11)
  1. Diagnosing error in temporal action detectors. In Eur. Conf. Comput. Vis., pages 256–272, 2018.
  2. Soft-NMS–improving object detection with one line of code. In ICCV, 2017.
  3. InternVideo-Ego4D: A pack of champion solutions to Ego4D challenges. arXiv preprint arXiv:2211.09529, 2022.
  4. Ota: Optimal transport assignment for object detection. In CVPR, 2021.
  5. Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430, 2021.
  6. Omnivore: A single model for many visual modalities. In CVPR, 2022.
  7. Egocentric video-language pretraining. In NeurIPS, 2022.
  8. Decoupled weight decay regularization. In ICLR, 2019.
  9. Where a strong backbone meets strong features–actionformer for ego4d moment queries challenge. arXiv preprint arXiv:2211.09074, 2022.
  10. Fcos: Fully convolutional one-stage object detection. In ICCV, 2019.
  11. ActionFormer: Localizing moments of actions with transformers. In ECCV, 2022.
Citations (2)

Summary

We haven't generated a summary for this paper yet.