Shizhou Zhang, De Cheng, Yinghui Xing, Yanning Zhang, Wenlong Luo, Qingchun Yang, Lingyan Ran
We lifted 6 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| FHR-L/VSLA-CLIP | — | 0 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| PromptLearner_Learnable | Not yet run | FHR-L/VSLA-CLIP/model/make_model_clipvideoreid_reidadapter_pbp.py pointer only (licence: NONE) · get_code("3a056fd355cd25ce") |
| PromptLearner_base | Not yet run | FHR-L/VSLA-CLIP/model/make_model_clipvideoreid_reidadapter_pbp.py pointer only (licence: NONE) · get_code("1b6a8be84a157091") |
| build_transformer | Not yet run | FHR-L/VSLA-CLIP/model/make_model_clipvideoreid_reidadapter_pbp.py pointer only (licence: NONE) · get_code("a8f5824659641940") |
| load_clip_to_cpu | Not yet run | FHR-L/VSLA-CLIP/model/make_model_clipvideoreid_reidadapter_pbp.py pointer only (licence: NONE) · get_code("1a74fdcd6c2a7e50") |
| weights_init_classifier | Not yet run | FHR-L/VSLA-CLIP/model/make_model_clipvideoreid_reidadapter_pbp.py pointer only (licence: NONE) · get_code("dfe37c57c7332893") |
| weights_init_kaiming | Not yet run | FHR-L/VSLA-CLIP/model/make_model_clipvideoreid_reidadapter_pbp.py pointer only (licence: NONE) · get_code("b4cbbd7d698cbbbe") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In this paper, we construct a large-scale benchmark dataset for Ground-to-Aerial Video-based person Re-Identification, named G2A-VReID, which comprises 185,907 images and 5,576 tracklets, featuring 2,788 distinct identities. To our knowledge, this is the first dataset for video ReID under Ground-to-Aerial scenarios. G2A-VReID dataset has the following characteristics: 1) Drastic view changes; 2) Large number of annotated identities; 3) Rich outdoor scenarios; 4) Huge difference in resolution. Additionally, we propose a new benchmark approach for cross-platform ReID by transforming the cross-platform visual alignment problem into visual-semantic alignment through vision-language model (i.e., CLIP) and applying a parameter-efficient Video Set-Level-Adapter module to adapt image-based foundation model to video ReID tasks, termed VSLA-CLIP. Besides, to further reduce the great discrepancy across the platforms, we also devise the platform-bridge prompts for efficient visual feature alignment. Extensive experiments demonstrate the superiority of the proposed method on all existing video ReID datasets and our proposed G2A-VReID dataset. The code and datasets are available at https://github.com/FHR-L/VSLA-CLIP.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2408.07500")
get_code_for_paper("2408.07500")
have("2408.07500")
Connect an agent — have() is free.