Update README.md

README.md

@@ -13,10 +13,10 @@ tags:
 
 # Motif Vision Encoder
 
-Motif Vision Encoder is a **unified image + video** self-supervised vision encoder on a ViT
-backbone. A single **3D-convolutional tokenizer** ingests both modalities — an image is a
-1-frame clip (`T=1`), a video is `T>1` — so the same weights produce **dense patch-level
-features** and a **language-aligned global (CLS) representation**.
+Motif Vision Encoder is a unified image + video self-supervised vision encoder on a ViT
+backbone. A single 3D-convolutional tokenizer ingests both modalities — an image is a
+1-frame clip (`T=1`), a video is `T>1` — so the same weights produce dense patch-level
+features and a language-aligned global (CLS) representation.
 
 Trained on **~1/3 the data of DINOv3** (0.5B vs 1.7B samples), it still reaches competitive
 performance across image and video benchmarks — and leads on DAVIS video tracking.
@@ -94,8 +94,8 @@ Outputs (`BaseModelOutputWithPooling`): `last_hidden_state` `(B, 1+4+N, 4096)`,
 ## Evaluation
 
 Compared against the strongest publicly reported self-supervised / vision backbones. Higher is
-better for every column **except KITTI depth** (lower is better). Best **comparable** value per
-column in **bold**, second best <u>underlined</u>; the footnoted figure (‡) is measured under a
+better for every column except KITTI depth (lower is better). Best comparable value per
+column in bold, second best <u>underlined</u>; the footnoted figure (‡) is measured under a
 different protocol and is excluded from the ranking.
 
 DAVIS S/M/L follow the DINOv3 protocol (J&F-mean at video short side 420/480, 840/960,
@@ -114,17 +114,18 @@ single-resolution (S) figure is available.
 
 <sub>‡ VideoMAEv2 ViT-g: K400 top-1 after **full fine-tuning**, not the frozen attentive-probe protocol used for the other rows.</sub>
 
-Motif sets a new **state of the art on DAVIS video segmentation**, leading at every resolution
-(74.0 / 80.5 / 83.5 J&F), and stays **competitive across the remaining image and video
-benchmarks** — despite training on only **~0.5B samples**, roughly **1/3 of DINOv3's data**.
-KITTI depth is still being evaluated and will be added as the run completes.
-
 Protocol: DINOv3-style linear/attentive probes for image tasks; V-JEPA 2-style protocol for
 video. Baseline DAVIS / ADE20K / K400 / KITTI figures are taken from the DINOv3 technical
 report's unified evaluation (Tab. 3, 5, 6) and ImageNet from Tab. 7; OpenCLIP and VideoMAEv2
 are not in that report; VideoMAEv2's K400 figure is cited from its own paper (see ‡), and
 OpenCLIP's remaining benchmarks are not reported under a comparable protocol.
 
+Motif sets a new state of the art on DAVIS video segmentation, leading at every resolution
+(74.0 / 80.5 / 83.5 J&F), and stays competitive across the remaining image and video
+benchmarks — despite training on only ~0.5B sample*, roughly 1/3 of DINOv3's data.
+KITTI depth is still being evaluated and will be added as the run completes.
+
+
 ## License
 
 Released under the **MIT License** (see `LICENSE`). The model was trained on data governed by the