Hugging Face's logo

Searchium-ai
/
clip4clip-webvid150k

Text-to-Video
Transformers
PyTorch
Safetensors
clip
zero-shot-image-classification
text
vision
video
Inference Endpoints
Model card Files Community
5
Diangle commited on
Commit
3983829
•
1 Parent(s): dec972c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -3,7 +3,9 @@ tags:
3
  - text
4
  - vision
5
  - video
6
- pipeline_tag: text-to-image
 
 
7
  ---
8
 
9
 
@@ -56,6 +58,7 @@ We have evaluated the performance of differenet models on the last 10k video cli
56
 
57
  | Model | R1 | R5 | R10 | MedianR | MeanR
58
  |------------------------|-------|-------|-------|-----|---------|
 
59
  | CLIP4Clip weights trained on msr-vtt | 38.38 | 62.89 | 72.01 | 3.0 |39.3023
60
  | **CLIP4Clip trained on 150k Webvid** | 50.74 | 77.30 | 85.05 | 1.0 | 14.9535
61
  | Binarized CLIP4Clip trained on 150k Webvid with rerank100 | 50.56 | 76.39 | 83.51 | 1.0 | 43.2964
 
3
  - text
4
  - vision
5
  - video
6
+ pipeline_tag: text-to-video
7
+ datasets:
8
+ - HuggingFaceM4/webvid
9
  ---
10
 
11
 
 
58
 
59
  | Model | R1 | R5 | R10 | MedianR | MeanR
60
  |------------------------|-------|-------|-------|-----|---------|
61
+ | Zero-shot clip weights | 37.16 | 62.10 | 71.16 | 3.0 | 42.2128
62
  | CLIP4Clip weights trained on msr-vtt | 38.38 | 62.89 | 72.01 | 3.0 |39.3023
63
  | **CLIP4Clip trained on 150k Webvid** | 50.74 | 77.30 | 85.05 | 1.0 | 14.9535
64
  | Binarized CLIP4Clip trained on 150k Webvid with rerank100 | 50.56 | 76.39 | 83.51 | 1.0 | 43.2964