Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+license: cc-by-4.0
+tags:
+- multimodal-retrieval
+- text-video-retrieval
+- audio-visual
+- hypergraph
+---
+
+# HyVol++: Weighted and Relational Hypergraph-Regularized Gramian Volumes
+
+Pretrained weights by Anindya Nag, Ambuj Mehrish and Sebastiano Vascon.
+
+HyVol++ extends HyVol ([CVML-CFU/HyVol](https://huggingface.co/CVML-CFU/HyVol)) with two
+hypergraph variants that add semantic relations between training samples before the
+volume loss is computed:
+
+- **wHyVol**: weighted hypergraph with learned per-edge weights and attention.
+- **wRHG**: weighted relational hypergraph with four edge families
+  (document, same-modality, cross-modality and friend).
+
+The hypergraph is removed after training, so the backbone, scoring function and
+retrieval cost are unchanged.
+
+## Checkpoints
+
+| File | Backbone |
+|---|---|
+| `wHyVol/GRAM_wHyVol/wHyVol_GRAM.pt` | GRAM + wHyVol |
+| `wHyVol/HyperGRAM_wHyVol/wHyVol_HyperGRAM.pt` | Hyperbolic GRAM + wHyVol |
+| `wRHG/GRAM_wRHG/wRHG_GRAM.pt` | GRAM + wRHG |
+| `wRHG/HyperGRAM_wRHG/wRHG_HyperGRAM.pt` | Hyperbolic GRAM + wRHG |
+
+All models are trained on a 150K-clip subset of VAST-27M and evaluated zero-shot.
+Each checkpoint is the ITM-best one on MSR-VTT (T-VAS).
+Load each checkpoint with the codebase of its backbone (GRAM or Hyperbolic GRAM).