mlsanityData to 7 Oct 2026

Exploring State Change Capture of Heterogeneous Backbones @ Ego4D Hands and Objects Challenge 2022

arXiv 2211.08728 ↗First posted 16 Nov 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Capturing the state changes of interacting objects is a key technology for understanding human-object interactions. This technical report describes our method using heterogeneous backbones for the Ego4D Object State Change Classification and PNR Temporal Localization Challenge. In the challenge, we used the heterogeneous video understanding backbones, namely CSN with 3D convolution as operator and VideoMAE with Transformer as operator. Our method achieves an accuracy of 0.796 on OSCC while achieving an absolute temporal localization error of 0.516 on PNR. These excellent results rank 1st on the leaderboard of Ego4D OSCC & PNR-TL Challenge 2022.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 32 references that are in the map. First posted on arXiv 16 Nov 2022.

Builds on

30 of 32 references.

References · 30

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  3. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  4. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  5. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
  6. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  7. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  8. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  9. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  10. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  11. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
  12. 2017Learning Spatio-Temporal Representation with Pseudo-3D Residual Networkscited by 386
18 more
  1. 2019BMN: Boundary-Matching Network for Temporal Action Proposal Generationcited by 327
  2. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 308
  3. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
  4. 2018BSN: Boundary Sensitive Network for Temporal Action Proposal Generationcited by 271
  5. 2022ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learningcited by 192
  6. 2020TDN: Temporal Difference Networks for Efficient Action Recognitioncited by 183
  7. 2020TEA: Temporal Excitation and Aggregation for Action Recognitioncited by 165
  8. 2020Temporal Pyramid Network for Action Recognitioncited by 163
  9. 2021Learning Salient Boundary Feature for Anchor-free Temporal Action Localizationcited by 156
  10. 2019Gaussian Temporal Awareness Networks for Action Localizationcited by 135
  11. 2017Single Shot Temporal Action Detectioncited by 123
  12. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 111
  13. 2019TEINet: Towards an Efficient Architecture for Video Recognitioncited by 92
  14. 2021MGSampler: An Explainable Sampling Strategy for Video Action Recognitioncited by 49
  15. 2022An Empirical Study of End-to-End Temporal Action Detectioncited by 40
  16. 2021DCAN: Improving Temporal Action Detection via Dual Context Aggregationcited by 36
  17. 2020Dynamic Sampling Networks for Efficient Action Recognition in Videoscited by 34
  18. 2022BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detectioncited by 28

Built on by

Not cited yet.