Lune

Profiles2019-2022

Tao Mei

JD Explore Academy

33Papers
26Last author
53Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers33

  1. Gait Recognition in the Wild with Dense 3D Representations and A BenchmarkAuthor 6 of 6CVPR 2022 · 228 citations
  2. Putting People in their Place: Monocular Regression of 3D People in DepthAuthor 5 of 6CVPR 2022 · 152 citations
  3. Comprehending and Ordering Semantics for Image CaptioningAuthor 4 of 4CVPR 2022 · 124 citations
  4. Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction DetectionAuthor 5 of 6CVPR 2022 · 88 citations
  5. Stand-Alone Inter-Frame Attention in Video ModelsAuthor 6 of 6CVPR 2022 · 68 citations
  6. Memory-Augmented Non-Local Attention for Video Super-ResolutionAuthor 4 of 4CVPR 2022 · 47 citations
  7. Directional Self-supervised Learning for Heavy Image AugmentationsAuthor 4 of 4CVPR 2022 · 20 citations
  8. MLP-3D: A MLP-like 3D Architecture with Grouped Time MixingAuthor 4 of 4CVPR 2022 · 18 citations
  9. MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action RecognitionAuthor 5 of 6ACM MM 2022 · 14 citations
  10. Out-of-Distribution Detection via Conditional Kernel Independence ModelAuthor 7 of 7NeurIPS 2022 · 9 citations
  11. CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-IdentificationAuthor 5 of 6ICCV 2021 · 150 citations
  12. SeCo: Exploring Sequence Supervision for Unsupervised Representation LearningAuthor 5 of 5AAAI 2021 · 118 citations
  13. Weakly Supervised Semantic Segmentation for Large-Scale Point CloudAuthor 6 of 6AAAI 2021 · 116 citations
  14. Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder NetworkAuthor 5 of 5AAAI 2021 · 59 citations
  15. A Style and Semantic Memory Mechanism for Domain Generalization*Author 6 of 6ICCV 2021 · 47 citations
  16. CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and DenoisingAuthor 6 of 6ACM MM 2021 · 36 citations
  17. Transferrable Contrastive Learning for Visual Domain AdaptationAuthor 6 of 7ACM MM 2021 · 21 citations
  18. Condensing a Sequence to One Informative Frame for Video RecognitionAuthor 5 of 5ICCV 2021 · 13 citations
  19. Improving Self-supervised Learning with Automated Unsupervised Outlier ArbitrationAuthor 6 of 6NeurIPS 2021 · 13 citations
  20. Boosting Video Representation Learning With Multi-Faceted IntegrationAuthor 6 of 6CVPR 2021
  21. Group-aware Label Transfer for Domain Adaptive Person Re-identificationAuthor 4 of 6CVPR 2021
  22. Representing Videos As Discriminative Sub-Graphs for Action RecognitionAuthor 6 of 6CVPR 2021
  23. Beyond the Parts: Learning Multi-view Cross-part Correlation for Vehicle Re-identificationAuthor 5 of 5ACM MM 2020 · 97 citations
  24. A New Dataset and Boundary-Attention Semantic Segmentation for Face ParsingAuthor 6 of 6AAAI 2020 · 88 citations
  25. Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-IdentificationAuthor 5 of 6ACM MM 2020 · 30 citations
  26. Exploring Category-Agnostic Clusters for Open-Set Domain AdaptationAuthor 5 of 5CVPR 2020
  27. Learning a Unified Sample Weighting Network for Object DetectionAuthor 6 of 6CVPR 2020
  28. Look-Into-Object: Self-Supervised Structure Modeling for Object RecognitionAuthor 5 of 5CVPR 2020
  29. Transferring and Regularizing Prediction for Semantic SegmentationAuthor 6 of 6CVPR 2020
  30. X-Linear Attention Networks for Image CaptioningAuthor 4 of 4CVPR 2020

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines