Repository of "Improving Cross-Modal Retrieval With Set of Diverse Embeddings" (CVPR'23, Highlight)
active 2023-08-15 → 2025-10-15 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 793 days from 2023-08-15 to 2025-10-15. Pushes: 3 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 4 in a day. Comments: 17 total, peak 4 in a day. Stars: 35 total, peak 3 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| kdwonn | 18 | 3 | 0 | 11 |
| AllenLiang96 | 5 | 0 | 0 | 3 |
| ShaneeyS | 2 | 0 | 0 | 1 |
| Asakinevergup | 2 | 0 | 0 | 1 |
| xiaoxiaoxiaofufu | 2 | 0 | 0 | 1 |
| NJNUwhb | 1 | 0 | 0 | 0 |
| leeynnnn | 1 | 0 | 0 | 0 |
| lengyibin | 1 | 0 | 0 | 0 |
| 2950906781 | 1 | 0 | 0 | 0 |
| battlezzq | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#11Asakinevergup2024-04-03 09:45how to reproduce ResNet-152 + Bi-GRU on COCO experiment
- Issue#12NJNUwhb2024-03-25 14:20training script
- Issue#11Asakinevergup2024-03-20 12:04how to reproduce ResNet-152 + Bi-GRU on COCO experiment
- Issue#10lengyibin2024-02-29 13:10Dataset
- Issue comment#9AllenLiang962023-12-05 10:13training scripts for flickr30k
- Issue comment#9kdwonn2023-12-05 08:59training scripts for flickr30k
- Issue comment#9AllenLiang962023-12-05 06:35training scripts for flickr30k
- Issue comment#9kdwonn2023-12-02 16:30training scripts for flickr30k
- Issue comment#9kdwonn2023-11-30 14:06training scripts for flickr30k
- Issue comment#9AllenLiang962023-11-30 14:02training scripts for flickr30k
- Issue#8kdwonn2023-11-30 13:39Figure 2.(b) Details of our attention maps that slots of each iteration produce.
- Issue comment#8kdwonn2023-11-30 13:39Figure 2.(b) Details of our attention maps that slots of each iteration produce.
- Issue comment#9kdwonn2023-11-30 13:33training scripts for flickr30k
- Issue#7AllenLiang962023-11-30 13:31which version of nvidia driver is suitable for running code
- Issue#9AllenLiang962023-11-30 13:21training scripts for flickr30k
- Issue#829509067812023-11-30 08:04Figure 2.(b) Details of our attention maps that slots of each iteration produce.
- Issue comment#6kdwonn2023-11-15 22:07how can I get the dataset_flickr30k.json ?
- Issue#6kdwonn2023-11-15 22:07how can I get the dataset_flickr30k.json ?
- Issue#6xiaoxiaoxiaofufu2023-11-15 10:05how can I get the dataset_flickr30k.json ?
- Issue comment#5kdwonn2023-11-10 16:46Purpose of "recovery" in train? and "txt_len"?
- Issue#5kdwonn2023-11-10 16:46Purpose of "recovery" in train? and "txt_len"?
- Issue comment#3kdwonn2023-11-10 16:39How to prepare the data please?
- Issue#3kdwonn2023-11-10 16:39How to prepare the data please?
- Issue comment#4kdwonn2023-11-10 16:35How to reproduce results on Flickr30K and w/ ResNeXt-101 + BERT?
- Issue comment#4xiaoxiaoxiaofufu2023-11-10 12:51How to reproduce results on Flickr30K and w/ ResNeXt-101 + BERT?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 35 stars here means stars gained during the window, not the repo's star count.